{"meta":{"source":"https://openrouter.ai/api/v1/models","endpoint_source":"https://openrouter.ai/api/v1/models/{id}/endpoints","fetched_at":"2026-08-28T09:21:35.367522+00:00","model_count":387,"enriched_count":368},"data":[{"id":"tencent/hy4-preview","canonical_slug":"tencent/hy4-preview-20260827","hugging_face_id":null,"name":"Tencent: Hy4 preview","created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000834","completion":"0.000002501","input_cache_read":"0.000000042"},"top_provider":{"context_length":1048576,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy4-preview-20260827/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"_prompt_per_m":8.34e-07,"_completion_per_m":2.501e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.2e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Tencent | tencent/hy4-preview-20260827","model_id":"tencent/hy4-preview","model_name":"Tencent: Hy4 preview","context_length":1048576,"pricing":{"prompt":"0.000000834","completion":"0.000002501","input_cache_read":"0.000000042","discount":0},"provider_name":"Tencent","tag":"tencent/fp8","quantization":"fp8","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","stop","max_completion_tokens","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.34e-07,"_completion_per_m":2.501e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.2e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Tencent","_cheapest_blended_per_m":1.3340999999999999e-06,"_priciest_blended_per_m":1.3340999999999999e-06,"_provider_spread_multiplier":1.0},{"id":"z-ai/glm-5.3-flash","canonical_slug":"z-ai/glm-5.3-flash-20260826","hugging_face_id":"zai-org/GLM-5.3-Flash","name":"Z.ai: GLM 5.3 Flash","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1310720,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000075","completion":"0.00000025","input_cache_read":"0.000000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2098-12-31","links":{"details":"/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":57.5,"coding_index":71.5,"agentic_index":58.2}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"_prompt_per_m":7.5e-08,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Z.AI | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.000000075","completion":"0.00000025","input_cache_read":"0.000000015","discount":0.5},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":97.23868567885927,"uptime_last_5m":96.03685398538259,"uptime_last_1d":98.10851307459593,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-08,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null},{"name":"Novita | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.000000075","completion":"0.00000025","input_cache_read":"0.000000015","discount":0.5},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.25087141564119,"uptime_last_5m":99.31536157466839,"uptime_last_1d":98.82993185896605,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-08,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null},{"name":"GMICloud | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.000000075","completion":"0.00000025","input_cache_read":"0.000000015","discount":0.5},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-5,"uptime_last_30m":78.20411789147909,"uptime_last_5m":97.4003466204506,"uptime_last_1d":83.12328799401497,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-08,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null},{"name":"Modal | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.000000149985","completion":"0.00000049995","input_cache_read":"0.000000029997","discount":0.6667},"provider_name":"Modal","tag":"modal/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","max_tokens","response_format","structured_outputs","tools","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":false,"required":false,"function":false},"status":0,"uptime_last_30m":99.88164333674747,"uptime_last_5m":99.7887621461766,"uptime_last_1d":96.24868911839141,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.49985e-07,"_completion_per_m":4.9995e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.9997e-08,"_cached_write_per_m":null},{"name":"Parasail | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":97.70431588613407,"uptime_last_5m":99.41672067401166,"uptime_last_1d":99.29599494463899,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Reka | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"Reka","tag":"reka/fp8","quantization":"fp8","max_completion_tokens":48000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.65934468240893,"uptime_last_5m":96.93325315694527,"uptime_last_1d":90.63498302662141,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Together | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048575,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":943717,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.79525241538167,"uptime_last_5m":99.90892531876139,"uptime_last_1d":98.83500022798883,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Wafer | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"Wafer","tag":"wafer","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","logit_bias","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.245630174793,"uptime_last_5m":99.70414201183432,"uptime_last_1d":95.91618142514947,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"DigitalOcean | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.09100937672366,"uptime_last_5m":83.4319526627219,"uptime_last_1d":98.40449926380072,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Morph | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"Morph","tag":"morph/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":18.772563176895307,"uptime_last_5m":0,"uptime_last_1d":37.93250383500937,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Cloudflare | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1310720,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":1179648,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.2608567643162,"uptime_last_5m":99.34256055363322,"uptime_last_1d":98.71512894627487,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"DeepInfra | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":82.42424242424242,"uptime_last_5m":null,"uptime_last_1d":95.70402065392045,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Io Net | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"Io Net","tag":"io-net/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","seed","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.02728926622194,"uptime_last_5m":51.515151515151516,"uptime_last_1d":94.56473082813052,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"BaseTen | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"BaseTen","tag":"baseten/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.67051070840198,"uptime_last_5m":100,"uptime_last_1d":99.63160281115393,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Venice | z-ai/glm-5.3-flash-20260826","model_id":"z-ai/glm-5.3-flash","model_name":"Z.ai: GLM 5.3 Flash","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":67.81002638522428,"uptime_last_5m":31.48558758314856,"uptime_last_1d":72.20439631098195,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Z.AI","_cheapest_blended_per_m":1.275e-07,"_priciest_blended_per_m":2.55e-07,"_provider_spread_multiplier":2.0},{"id":"meta/muse-spark-1.2-contributor","canonical_slug":"meta/muse-spark-1.2-contributor-20260805","hugging_face_id":null,"name":"Meta: Muse Spark 1.2 Contributor","created":1787336476,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000002","web_search":"0.0025","input_cache_read":"0.000000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-spark-1.2-contributor-20260805/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":1e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-09,"_cached_write_per_m":null,"_endpoints":[{"name":"Meta | meta/muse-spark-1.2-contributor-20260805","model_id":"meta/muse-spark-1.2-contributor","model_name":"Meta: Muse Spark 1.2 Contributor","context_length":1048576,"pricing":{"prompt":"0.0000001","completion":"0.0000002","web_search":"0.0025","input_cache_read":"0.000000002","discount":0},"provider_name":"Meta","tag":"meta","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9995857523669,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-09,"_cached_write_per_m":null}],"_cheapest_provider":"Meta","_cheapest_blended_per_m":1.2999999999999997e-07,"_priciest_blended_per_m":1.2999999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"inclusionai/ling-3.0-flash-fin:free","canonical_slug":"inclusionai/ling-3.0-flash-fin-20260827","hugging_face_id":null,"name":"Ling 3.0 Flash Fin (free)","created":1787846290,"description":"Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/inclusionai/ling-3.0-flash-fin-20260827/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | inclusionai/ling-3.0-flash-fin-20260827:free","model_id":"inclusionai/ling-3.0-flash-fin:free","model_name":"Ling 3.0 Flash Fin","context_length":262144,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Novita","tag":"novita","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.64515705086082,"uptime_last_5m":99.42922374429224,"uptime_last_1d":99.9295457952331,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"deepseek/deepseek-v4-flash-vision-exp","canonical_slug":"deepseek/deepseek-v4-flash-vision-exp-20260821","hugging_face_id":null,"name":"DeepSeek: DeepSeek V4 Flash Vision Exp","created":1787311563,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014","overrides":[{"utc_days":["saturday","sunday"],"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":0,"utc_end":100,"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":100,"utc_end":400,"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":400,"utc_end":600,"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":600,"utc_end":1000,"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":1000,"utc_end":0,"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-vision-exp-20260821/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"high"},"_prompt_per_m":4.4e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepSeek | deepseek/deepseek-v4-flash-vision-exp-20260821","model_id":"deepseek/deepseek-v4-flash-vision-exp","model_name":"DeepSeek: DeepSeek V4 Flash Vision Exp","context_length":1048576,"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014","discount":0,"overrides":[{"utc_days":["saturday","sunday"],"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"},{"utc_start":0,"utc_end":100,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"},{"utc_start":100,"utc_end":400,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014"},{"utc_start":400,"utc_end":600,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"},{"utc_start":600,"utc_end":1000,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014"},{"utc_start":1000,"utc_end":0,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"}]},"provider_name":"DeepSeek","tag":"deepseek","quantization":"unknown","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-08,"_cached_write_per_m":null}],"_cheapest_provider":"DeepSeek","_cheapest_blended_per_m":7.04e-07,"_priciest_blended_per_m":7.04e-07,"_provider_spread_multiplier":1.0},{"id":"tencent/hy-mt2-1.8b","canonical_slug":"tencent/hy-mt2-1.8b-20260521","hugging_face_id":"tencent/Hy-MT2-1.8B","name":"Tencent: Hy-MT2-1.8B","created":1787231581,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000044","completion":"0.000000177"},"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","stop","temperature"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy-mt2-1.8b-20260521/endpoints"},"_prompt_per_m":4.4e-08,"_completion_per_m":1.77e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Tencent | tencent/hy-mt2-1.8b-20260521","model_id":"tencent/hy-mt2-1.8b","model_name":"Tencent: Hy-MT2-1.8B","context_length":8192,"pricing":{"prompt":"0.000000044","completion":"0.000000177","discount":0},"provider_name":"Tencent","tag":"tencent/fp8","quantization":"fp8","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["temperature","stop","max_completion_tokens","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-08,"_completion_per_m":1.77e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Tencent","_cheapest_blended_per_m":8.39e-08,"_priciest_blended_per_m":8.39e-08,"_provider_spread_multiplier":1.0},{"id":"~z-ai/glm-latest","canonical_slug":"~z-ai/glm-latest","alias_target":{"name":"Z.ai: GLM 5.3","slug":"z-ai/glm-5.3"},"hugging_face_id":null,"name":"Z.ai: GLM Latest","created":1787151053,"description":"This model always redirects to the latest GLM model from Z.ai.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2098-12-31","links":{"details":"/api/v1/models/~z-ai/glm-latest/endpoints"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":2.3e-06,"_priciest_blended_per_m":2.3e-06,"_provider_spread_multiplier":null},{"id":"qwen/qwen3.8-flash","canonical_slug":"qwen/qwen3.8-flash-20260826","hugging_face_id":null,"name":"Qwen: Qwen3.8 Flash","created":1787773060,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.00000047","input_cache_read":"0.000000016","input_cache_write":"0.0000002"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-flash-20260826/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"_prompt_per_m":1.5e-07,"_completion_per_m":4.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-08,"_cached_write_per_m":2e-07,"_endpoints":[{"name":"Alibaba | qwen/qwen3.8-flash-20260826","model_id":"qwen/qwen3.8-flash","model_name":"Qwen: Qwen3.8 Flash","context_length":1000000,"pricing":{"prompt":"0.00000015","completion":"0.00000047","input_cache_read":"0.000000016","input_cache_write":"0.0000002","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","structured_outputs","top_k","frequency_penalty","stop","logprobs","top_logprobs","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.9735659529474,"uptime_last_5m":100,"uptime_last_1d":99.97971418739019,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":4.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-08,"_cached_write_per_m":2e-07}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":2.46e-07,"_priciest_blended_per_m":2.46e-07,"_provider_spread_multiplier":1.0},{"id":"tencent/hy-mt2-30b-a3b","canonical_slug":"tencent/hy-mt2-30b-a3b-20260521","hugging_face_id":"tencent/Hy-MT2-30B-A3B","name":"Tencent: Hy-MT2-30B-A3B","created":1787231561,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000074","completion":"0.000000295"},"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy-mt2-30b-a3b-20260521/endpoints"},"_prompt_per_m":7.4e-08,"_completion_per_m":2.95e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Tencent | tencent/hy-mt2-30b-a3b-20260521","model_id":"tencent/hy-mt2-30b-a3b","model_name":"Tencent: Hy-MT2-30B-A3B","context_length":8192,"pricing":{"prompt":"0.000000074","completion":"0.000000295","discount":0},"provider_name":"Tencent","tag":"tencent/fp8","quantization":"fp8","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["temperature","stop","max_completion_tokens","max_tokens","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.4e-08,"_completion_per_m":2.95e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Tencent","_cheapest_blended_per_m":1.403e-07,"_priciest_blended_per_m":1.403e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.8-27b","canonical_slug":"qwen/qwen3.8-27b-20260814","hugging_face_id":"Qwen/Qwen3.8-27B","name":"Qwen: Qwen3.8 27B","created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000000425","completion":"0.00000255","input_cache_read":"0.000000085","input_cache_write":"0.00000053125"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-27b-20260814/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":52,"coding_index":68.1,"agentic_index":50.9}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","medium","low"],"default_effort":"xhigh"},"_prompt_per_m":4.25e-07,"_completion_per_m":2.55e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8.5e-08,"_cached_write_per_m":5.3125e-07,"_endpoints":[{"name":"Chutes | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":262144,"pricing":{"prompt":"0.00000035","completion":"0.00000275","input_cache_read":"0.000000035","discount":0},"provider_name":"Chutes","tag":"chutes/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.80624426078971,"uptime_last_5m":99.07038512616202,"uptime_last_1d":98.9032630935979,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-07,"_completion_per_m":2.75e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-08,"_cached_write_per_m":null},{"name":"AkashML | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":262144,"pricing":{"prompt":"0.0000004","completion":"0.00000255","input_cache_read":"0.00000005","discount":0},"provider_name":"AkashML","tag":"akashml/bf16","quantization":"bf16","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.93029373081981,"uptime_last_5m":99.88950276243094,"uptime_last_1d":99.44417764271488,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":2.55e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Phala | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":262144,"pricing":{"prompt":"0.0000004","completion":"0.000003","input_cache_read":"0.00000015","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.9266802443992,"uptime_last_5m":96.94656488549617,"uptime_last_1d":86.20956034149785,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"CoreWeave | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":262144,"pricing":{"prompt":"0.0000004","completion":"0.000003","input_cache_read":"0.00000015","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.44893460690669,"uptime_last_5m":100,"uptime_last_1d":97.77156255000591,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":1000000,"pricing":{"prompt":"0.00000042","completion":"0.000003","input_cache_read":"0.000000085","discount":0},"provider_name":"Novita","tag":"novita","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.87819732034104,"uptime_last_5m":100,"uptime_last_1d":99.60174331229335,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.2e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8.5e-08,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":1000000,"pricing":{"prompt":"0.000000425","completion":"0.00000255","input_cache_read":"0.000000085","input_cache_write":"0.00000053125","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.99224986437262,"uptime_last_5m":100,"uptime_last_1d":99.89376503066438,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.25e-07,"_completion_per_m":2.55e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8.5e-08,"_cached_write_per_m":5.3125e-07},{"name":"Cloudflare | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":262144,"pricing":{"prompt":"0.00000045","completion":"0.0000032","input_cache_read":"0.00000005","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":90.0709219858156,"uptime_last_5m":91.42857142857143,"uptime_last_1d":91.46203904555314,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Reka | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":262144,"pricing":{"prompt":"0.00000045","completion":"0.0000032","input_cache_read":"0.00000005","discount":0},"provider_name":"Reka","tag":"reka/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.21743991056456,"uptime_last_5m":100,"uptime_last_1d":99.06562163823574,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":262144,"pricing":{"prompt":"0.00000045","completion":"0.0000032","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.22804314329738,"uptime_last_5m":100,"uptime_last_1d":99.09025245924194,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":262144,"pricing":{"prompt":"0.00000045","completion":"0.0000032","input_cache_read":"0.00000005","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":97.51655629139073,"uptime_last_5m":null,"uptime_last_1d":99.76944636991048,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Io Net | qwen/qwen3.8-27b-20260814","model_id":"qwen/qwen3.8-27b","model_name":"Qwen: Qwen3.8 27B","context_length":65500,"pricing":{"prompt":"0.00000048","completion":"0.0000034","input_cache_read":"0.00000025","discount":0},"provider_name":"Io Net","tag":"io-net/fp8","quantization":"fp8","max_completion_tokens":58950,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","seed","structured_outputs","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":false,"required":false,"function":false},"status":0,"uptime_last_30m":95.23809523809523,"uptime_last_5m":98.52941176470588,"uptime_last_1d":97.12589521296646,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.8e-07,"_completion_per_m":3.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"AkashML","_cheapest_blended_per_m":1.045e-06,"_priciest_blended_per_m":1.3559999999999998e-06,"_provider_spread_multiplier":1.2976076555023923},{"id":"z-ai/glm-5.3","canonical_slug":"z-ai/glm-5.3-20260816","hugging_face_id":"zai-org/GLM-5.3","name":"Z.ai: GLM 5.3","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2098-12-31","links":{"details":"/api/v1/models/z-ai/glm-5.3-20260816/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":59.5,"coding_index":74.8,"agentic_index":59.1}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Z.AI | z-ai/glm-5.3-20260816","model_id":"z-ai/glm-5.3","model_name":"Z.ai: GLM 5.3","context_length":1048576,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99921655429031,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Z.AI","_cheapest_blended_per_m":2.3e-06,"_priciest_blended_per_m":2.3e-06,"_provider_spread_multiplier":1.0},{"id":"tencent/hy-mt2-7b","canonical_slug":"tencent/hy-mt2-7b-20260521","hugging_face_id":"tencent/Hy-MT2-7B","name":"Tencent: Hy-MT2-7B","created":1787148797,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000074","completion":"0.000000295"},"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy-mt2-7b-20260521/endpoints"},"_prompt_per_m":7.4e-08,"_completion_per_m":2.95e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Tencent | tencent/hy-mt2-7b-20260521","model_id":"tencent/hy-mt2-7b","model_name":"Tencent: Hy-MT2-7B","context_length":8192,"pricing":{"prompt":"0.000000074","completion":"0.000000295","discount":0},"provider_name":"Tencent","tag":"tencent/fp8","quantization":"fp8","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["temperature","stop","max_completion_tokens","max_tokens","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.4e-08,"_completion_per_m":2.95e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Tencent","_cheapest_blended_per_m":1.403e-07,"_priciest_blended_per_m":1.403e-07,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3.7-flash","canonical_slug":"google/gemini-3.7-flash-20260813","hugging_face_id":null,"name":"Google: Gemini 3.7 Flash","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","web_search":"0.014","internal_reasoning":"0.000001875","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.7-flash-20260813/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1235,"win_rate":51.9,"rank":7},{"arena":"agents","category":"androidnative","elo":1273,"win_rate":59.3,"rank":3},{"arena":"agents","category":"fullstack","elo":1228,"win_rate":45,"rank":15},{"arena":"agents","category":"mobileapps","elo":1250,"win_rate":51.8,"rank":7},{"arena":"agents","category":"webapps","elo":1240,"win_rate":47.2,"rank":13},{"arena":"models","category":"3d","elo":1357,"win_rate":65.1,"rank":5},{"arena":"models","category":"codecategories","elo":1328,"win_rate":58.6,"rank":6},{"arena":"models","category":"dataviz","elo":1348,"win_rate":62.3,"rank":5},{"arena":"models","category":"gamedev","elo":1348,"win_rate":59.8,"rank":5},{"arena":"models","category":"uicomponent","elo":1308,"win_rate":54.2,"rank":12},{"arena":"models","category":"website","elo":1321,"win_rate":58.1,"rank":6}],"artificial_analysis":{"intelligence_index":56,"coding_index":76.1,"agentic_index":45.1}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":3.75e-07,"_completion_per_m":1.875e-06,"_image_per_m":3.75e-07,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":2.08333333333333e-08,"_endpoints":[{"name":"Google | google/gemini-3.7-flash-20260813","model_id":"google/gemini-3.7-flash","model_name":"Google: Gemini 3.7 Flash","context_length":1048576,"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","web_search":"0.014","internal_reasoning":"0.000001875","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","discount":0.75},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.25381617163869,"uptime_last_5m":98.74983286535634,"uptime_last_1d":98.53987641094344,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.75e-07,"_completion_per_m":1.875e-06,"_image_per_m":3.75e-07,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":2.08333333333333e-08},{"name":"Google | google/gemini-3.7-flash-20260813","model_id":"google/gemini-3.7-flash","model_name":"Google: Gemini 3.7 Flash","context_length":1048576,"pricing":{"prompt":"0.0000001875","completion":"0.0000009375","image":"0.0000001875","audio":"0.0000001875","input_audio_cache":"0.00000001875","web_search":"0.014","internal_reasoning":"0.0000009375","input_cache_read":"0.00000001875","input_cache_write":"0.0000000104166666666667","discount":0.75},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.25381617163869,"uptime_last_5m":98.74983286535634,"uptime_last_1d":98.53987641094344,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.875e-07,"_completion_per_m":9.375e-07,"_image_per_m":1.875e-07,"_request_per_m":null,"_cached_read_per_m":1.875e-08,"_cached_write_per_m":1.04166666666667e-08},{"name":"Google | google/gemini-3.7-flash-20260813","model_id":"google/gemini-3.7-flash","model_name":"Google: Gemini 3.7 Flash","context_length":1048576,"pricing":{"prompt":"0.000000675","completion":"0.000003375","image":"0.000000675","audio":"0.000000675","input_audio_cache":"0.0000000675","web_search":"0.014","internal_reasoning":"0.000003375","input_cache_read":"0.0000000675","input_cache_write":"0.0000000375","discount":0.75},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.25381617163869,"uptime_last_5m":98.74983286535634,"uptime_last_1d":98.53987641094344,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.75e-07,"_completion_per_m":3.375e-06,"_image_per_m":6.75e-07,"_request_per_m":null,"_cached_read_per_m":6.75e-08,"_cached_write_per_m":3.75e-08},{"name":"Google AI Studio | google/gemini-3.7-flash-20260813","model_id":"google/gemini-3.7-flash","model_name":"Google: Gemini 3.7 Flash","context_length":1048576,"pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","audio":"0.00000075","input_audio_cache":"0.000000075","web_search":"0.014","internal_reasoning":"0.00000375","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","discount":0.5},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.7014472219411,"uptime_last_5m":99.62674961119751,"uptime_last_1d":99.57932815059624,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":3.75e-06,"_image_per_m":7.5e-07,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-3.7-flash-20260813","model_id":"google/gemini-3.7-flash","model_name":"Google: Gemini 3.7 Flash","context_length":1048576,"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","web_search":"0.014","internal_reasoning":"0.000001875","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","discount":0.5},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.7014472219411,"uptime_last_5m":99.62674961119751,"uptime_last_1d":99.57932815059624,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.75e-07,"_completion_per_m":1.875e-06,"_image_per_m":3.75e-07,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":2.08333333333333e-08},{"name":"Google AI Studio | google/gemini-3.7-flash-20260813","model_id":"google/gemini-3.7-flash","model_name":"Google: Gemini 3.7 Flash","context_length":1048576,"pricing":{"prompt":"0.00000135","completion":"0.00000675","image":"0.00000135","audio":"0.00000135","input_audio_cache":"0.000000135","web_search":"0.014","internal_reasoning":"0.00000675","input_cache_read":"0.000000135","input_cache_write":"0.000000075","discount":0.5},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.7014472219411,"uptime_last_5m":99.62674961119751,"uptime_last_1d":99.57932815059624,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.35e-06,"_completion_per_m":6.75e-06,"_image_per_m":1.35e-06,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":7.5e-08}],"_cheapest_provider":"Google","_cheapest_blended_per_m":4.1249999999999997e-07,"_priciest_blended_per_m":2.9699999999999995e-06,"_provider_spread_multiplier":7.199999999999999},{"id":"dots-studio/dots-3-note-preview:free","canonical_slug":"dots-studio/dots-3-note-preview-20260813","hugging_face_id":null,"name":"Dots Studio: Dots3-Note Preview (free)","created":1786680361,"description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...","context_length":512000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":512000,"max_completion_tokens":460800,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2026-09-30","links":{"details":"/api/v1/models/dots-studio/dots-3-note-preview-20260813/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"AtlasCloud | dots-studio/dots-3-note-preview-20260813:free","model_id":"dots-studio/dots-3-note-preview:free","model_name":"Dots Studio: Dots3-Note Preview","context_length":512000,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":460800,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99447707354328,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"AtlasCloud","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"bytedance-seed/seed-2-1-turbo","canonical_slug":"bytedance-seed/seed-2-1-turbo-20260810","hugging_face_id":null,"name":"ByteDance Seed: Seed 2.1 Turbo","created":1786552176,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000025"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-2-1-turbo-20260810/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":5e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Seed | bytedance-seed/seed-2-1-turbo-20260810","model_id":"bytedance-seed/seed-2-1-turbo","model_name":"ByteDance Seed: Seed 2.1 Turbo","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.0000025","discount":0},"provider_name":"Seed","tag":"seed/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","stop","tools","response_format","structured_outputs","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Seed","_cheapest_blended_per_m":1.1e-06,"_priciest_blended_per_m":1.1e-06,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3.7-flash:batch","canonical_slug":"google/gemini-3.7-flash-20260813","hugging_face_id":null,"name":"Google: Gemini 3.7 Flash (batch)","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000001875","completion":"0.0000009375","image":"0.0000001875","audio":"0.0000001875","input_audio_cache":"0.00000001875","web_search":"0.014","internal_reasoning":"0.0000009375","input_cache_read":"0.00000001875","input_cache_write":"0.0000000208333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.7-flash-20260813/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1235,"win_rate":51.9,"rank":7},{"arena":"agents","category":"androidnative","elo":1273,"win_rate":59.3,"rank":3},{"arena":"agents","category":"fullstack","elo":1228,"win_rate":45,"rank":15},{"arena":"agents","category":"mobileapps","elo":1250,"win_rate":51.8,"rank":7},{"arena":"agents","category":"webapps","elo":1240,"win_rate":47.2,"rank":13},{"arena":"models","category":"3d","elo":1357,"win_rate":65.1,"rank":5},{"arena":"models","category":"codecategories","elo":1328,"win_rate":58.6,"rank":6},{"arena":"models","category":"dataviz","elo":1348,"win_rate":62.3,"rank":5},{"arena":"models","category":"gamedev","elo":1348,"win_rate":59.8,"rank":5},{"arena":"models","category":"uicomponent","elo":1308,"win_rate":54.2,"rank":12},{"arena":"models","category":"website","elo":1321,"win_rate":58.1,"rank":6}],"artificial_analysis":{"intelligence_index":56,"coding_index":76.1,"agentic_index":45.1}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":1.875e-07,"_completion_per_m":9.375e-07,"_image_per_m":1.875e-07,"_request_per_m":null,"_cached_read_per_m":1.875e-08,"_cached_write_per_m":2.08333333333333e-08,"_endpoints":[{"name":"Google | google/gemini-3.7-flash-20260813:batch","model_id":"google/gemini-3.7-flash:batch","model_name":"Google: Gemini 3.7 Flash","context_length":1048576,"pricing":{"prompt":"0.0000001875","completion":"0.0000009375","image":"0.0000001875","audio":"0.0000001875","input_audio_cache":"0.00000001875","web_search":"0.014","internal_reasoning":"0.0000009375","input_cache_read":"0.00000001875","input_cache_write":"0.0000000208333333333333","discount":0.75},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.875e-07,"_completion_per_m":9.375e-07,"_image_per_m":1.875e-07,"_request_per_m":null,"_cached_read_per_m":1.875e-08,"_cached_write_per_m":2.08333333333333e-08}],"_cheapest_provider":"Google","_cheapest_blended_per_m":4.1249999999999997e-07,"_priciest_blended_per_m":4.1249999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.8-2.4t-a95b","canonical_slug":"qwen/qwen3.8-2.4t-a95b-20260812","hugging_face_id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen: Qwen3.8 2.4T A95B","created":1786551702,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-2.4t-a95b-20260812/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":57.7,"coding_index":71.9,"agentic_index":57.1}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","medium","low"],"default_effort":"xhigh"},"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | qwen/qwen3.8-2.4t-a95b-20260812","model_id":"qwen/qwen3.8-2.4t-a95b","model_name":"Qwen: Qwen3.8 2.4T A95B","context_length":262144,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":-2,"uptime_last_30m":89.80582524271846,"uptime_last_5m":58.57142857142858,"uptime_last_1d":97.24994455533378,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3.8-2.4t-a95b-20260812","model_id":"qwen/qwen3.8-2.4t-a95b","model_name":"Qwen: Qwen3.8 2.4T A95B","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","discount":0},"provider_name":"Novita","tag":"novita","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97673336435552,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3.8-2.4t-a95b-20260812","model_id":"qwen/qwen3.8-2.4t-a95b","model_name":"Qwen: Qwen3.8 2.4T A95B","context_length":1048576,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.98852421390865,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null},{"name":"Modal | qwen/qwen3.8-2.4t-a95b-20260812","model_id":"qwen/qwen3.8-2.4t-a95b","model_name":"Qwen: Qwen3.8 2.4T A95B","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","discount":0},"provider_name":"Modal","tag":"modal/nvfp4","quantization":"nvfp4","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.6933756361391,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3.8-2.4t-a95b-20260812","model_id":"qwen/qwen3.8-2.4t-a95b","model_name":"Qwen: Qwen3.8 2.4T A95B","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","input_cache_write":"0.0000025","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","top_k","frequency_penalty","stop","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.89351992698509,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":2.5e-06},{"name":"Together | qwen/qwen3.8-2.4t-a95b-20260812","model_id":"qwen/qwen3.8-2.4t-a95b","model_name":"Qwen: Qwen3.8 2.4T A95B","context_length":1010000,"pricing":{"prompt":"0.0000025","completion":"0.00000625","input_cache_read":"0.0000005","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":909000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":96.01388888888889,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":6.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3.8-2.4t-a95b-20260812","model_id":"qwen/qwen3.8-2.4t-a95b","model_name":"Qwen: Qwen3.8 2.4T A95B","context_length":262144,"pricing":{"prompt":"0.0000025","completion":"0.0000075","input_cache_read":"0.0000003125","discount":0},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":98.71698113207547,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":7.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.125e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":3.2e-06,"_priciest_blended_per_m":4e-06,"_provider_spread_multiplier":1.25},{"id":"bytedance-seed/seed-2.0-code","canonical_slug":"bytedance-seed/seed-2.0-code-20260730","hugging_face_id":null,"name":"ByteDance Seed: Seed-2.0-Code","created":1786550701,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000003","overrides":[{"min_prompt_tokens":128000,"prompt":"0.000001","completion":"0.000006"}]},"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-2.0-code-20260730/endpoints"},"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Seed | bytedance-seed/seed-2.0-code-20260730","model_id":"bytedance-seed/seed-2.0-code","model_name":"ByteDance Seed: Seed-2.0-Code","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.000003","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.000001","completion":"0.000006"}]},"provider_name":"Seed","tag":"seed/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Seed","_cheapest_blended_per_m":1.2499999999999999e-06,"_priciest_blended_per_m":1.2499999999999999e-06,"_provider_spread_multiplier":1.0},{"id":"liquid/lfm-2.5-2.6b:free","canonical_slug":"liquid/lfm-2.5-2.6b-20260811","hugging_face_id":"LiquidAI/LFM2.5-2.6B","name":"LiquidAI: LFM2.5-2.6B (free)","created":1786470519,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":65536,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.1,"top_k":50,"repetition_penalty":1.1},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/liquid/lfm-2.5-2.6b-20260811/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Liquid | liquid/lfm-2.5-2.6b-20260811:free","model_id":"liquid/lfm-2.5-2.6b:free","model_name":"LiquidAI: LFM2.5-2.6B","context_length":65536,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Liquid","tag":"liquid/fp8","quantization":"fp8","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","max_completion_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.56622284512964,"uptime_last_5m":97.40259740259741,"uptime_last_1d":94.09763944975212,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Liquid","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"deepseek/deepseek-v4-pro-0813","canonical_slug":"deepseek/deepseek-v4-pro-20260813","hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","created":1786549364,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044","overrides":[{"utc_days":["saturday","sunday"],"prompt":"0.00000066","completion":"0.00000198","input_cache_read":"0.000000022"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":0,"utc_end":100,"prompt":"0.00000066","completion":"0.00000198","input_cache_read":"0.000000022"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":100,"utc_end":400,"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":400,"utc_end":600,"prompt":"0.00000066","completion":"0.00000198","input_cache_read":"0.000000022"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":600,"utc_end":1000,"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":1000,"utc_end":0,"prompt":"0.00000066","completion":"0.00000198","input_cache_read":"0.000000022"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":1},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-20260813/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":53.2,"coding_index":68.8,"agentic_index":49.6}},"reasoning":{"mandatory":false,"supported_efforts":["max","high","low"],"default_effort":"high"},"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"StreamLake | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1024000,"pricing":{"prompt":"0.0000011154","completion":"0.0000033462","input_cache_read":"0.00000003718","discount":0.155},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.89032682605836,"uptime_last_5m":99.92716678805536,"uptime_last_1d":99.92843653712355,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1154e-06,"_completion_per_m":3.3462e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.718e-08,"_cached_write_per_m":null},{"name":"GMICloud | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048575,"pricing":{"prompt":"0.000001122","completion":"0.000003366","input_cache_read":"0.0000000374","discount":0.15},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":943717,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":98.52717886425751,"uptime_last_5m":99.47183098591549,"uptime_last_1d":98.72037309883174,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.122e-06,"_completion_per_m":3.366e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.74e-08,"_cached_write_per_m":null},{"name":"Alibaba | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1000000,"pricing":{"prompt":"0.000001122","completion":"0.000003366","input_cache_read":"0.0000001122","discount":0,"overrides":[{"utc_start":0,"utc_end":1400,"prompt":"0.000001122","completion":"0.000003366","input_cache_read":"0.0000001122"},{"utc_start":1400,"utc_end":0,"prompt":"0.0000005808","completion":"0.0000017424","input_cache_read":"0.00000005808"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.96477632969355,"uptime_last_5m":100,"uptime_last_1d":99.96483682435809,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.122e-06,"_completion_per_m":3.366e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.122e-07,"_cached_write_per_m":null},{"name":"DeepInfra | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.0000013","completion":"0.0000026","input_cache_read":"0.0000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":85.25547445255475,"uptime_last_5m":66.94214876033058,"uptime_last_1d":89.71071846608328,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-06,"_completion_per_m":2.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"DeepSeek | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044","discount":0,"overrides":[{"utc_days":["saturday","sunday"],"prompt":"0.00000066","completion":"0.00000198","input_cache_read":"0.000000022"},{"utc_start":0,"utc_end":100,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000066","completion":"0.00000198","input_cache_read":"0.000000022"},{"utc_start":100,"utc_end":400,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044"},{"utc_start":400,"utc_end":600,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000066","completion":"0.00000198","input_cache_read":"0.000000022"},{"utc_start":600,"utc_end":1000,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044"},{"utc_start":1000,"utc_end":0,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000066","completion":"0.00000198","input_cache_read":"0.000000022"}]},"provider_name":"DeepSeek","tag":"deepseek","quantization":"unknown","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99723178675389,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null},{"name":"Together | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.00000013","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":93.8337801608579,"uptime_last_5m":95.27027027027027,"uptime_last_1d":94.33859553620033,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null},{"name":"Novita | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000132","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.78203745968626,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.32e-07,"_cached_write_per_m":null},{"name":"Parasail | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.87218045112782,"uptime_last_5m":99.60474308300395,"uptime_last_1d":98.52448119443977,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.00000044","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.88583233663151,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-07,"_cached_write_per_m":null},{"name":"BaseTen | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000132","discount":0},"provider_name":"BaseTen","tag":"baseten/fp4","quantization":"fp4","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.33774834437085,"uptime_last_5m":null,"uptime_last_1d":99.65432478107236,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.32e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.19857524487978,"uptime_last_5m":100,"uptime_last_1d":99.12037181446708,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null},{"name":"Cloudflare | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.67707212055974,"uptime_last_5m":99.3006993006993,"uptime_last_1d":99.8176162872897,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null},{"name":"Fireworks | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.92790194664744,"uptime_last_5m":100,"uptime_last_1d":99.8436597219862,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null},{"name":"Phala | deepseek/deepseek-v4-pro-20260813","model_id":"deepseek/deepseek-v4-pro-0813","model_name":"DeepSeek: DeepSeek V4 Pro 0813","context_length":1048576,"pricing":{"prompt":"0.00000145","completion":"0.00000436","input_cache_read":"0.00000015","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.74368039596959,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.45e-06,"_completion_per_m":4.36e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.69e-06,"_priciest_blended_per_m":2.3229999999999996e-06,"_provider_spread_multiplier":1.3745562130177513},{"id":"x-ai/grok-4.6","canonical_slug":"x-ai/grok-4.6-20260810","hugging_face_id":null,"name":"SpaceXAI: Grok 4.6","created":1786548957,"description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","web_search":"0.005","input_cache_read":"0.0000005","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.000001"}]},"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-4.6-20260810/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1204,"win_rate":46.2,"rank":10},{"arena":"agents","category":"androidnative","elo":1319,"win_rate":65.8,"rank":1},{"arena":"agents","category":"fullstack","elo":1285,"win_rate":55.8,"rank":6},{"arena":"agents","category":"mobileapps","elo":1270,"win_rate":57.6,"rank":3},{"arena":"agents","category":"python-pptxslides","elo":1253,"win_rate":55.5,"rank":6},{"arena":"agents","category":"webapps","elo":1275,"win_rate":57.3,"rank":6},{"arena":"models","category":"3d","elo":1325,"win_rate":53.5,"rank":9},{"arena":"models","category":"asciiart","elo":1305,"win_rate":61.7,"rank":5},{"arena":"models","category":"codecategories","elo":1325,"win_rate":53.6,"rank":7},{"arena":"models","category":"dataviz","elo":1312,"win_rate":52,"rank":9},{"arena":"models","category":"gamedev","elo":1340,"win_rate":55.8,"rank":6},{"arena":"models","category":"svg","elo":1269,"win_rate":52,"rank":8},{"arena":"models","category":"uicomponent","elo":1338,"win_rate":58.5,"rank":6},{"arena":"models","category":"website","elo":1320,"win_rate":53.7,"rank":7}],"artificial_analysis":{"intelligence_index":60.9,"coding_index":76.8,"agentic_index":58.7}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"xAI | x-ai/grok-4.6-20260810","model_id":"x-ai/grok-4.6","model_name":"SpaceXAI: Grok 4.6","context_length":500000,"pricing":{"prompt":"0.000002","completion":"0.000006","web_search":"0.005","input_cache_read":"0.0000005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.000001"}]},"provider_name":"xAI","tag":"xai/zdr","quantization":"unknown","max_completion_tokens":450000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.88195947275231,"uptime_last_5m":99.87515605493134,"uptime_last_1d":99.94326869566626,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.6-20260810","model_id":"x-ai/grok-4.6","model_name":"SpaceXAI: Grok 4.6","context_length":500000,"pricing":{"prompt":"0.000004","completion":"0.000012","web_search":"0.005","input_cache_read":"0.000001","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000008","completion":"0.000024","input_cache_read":"0.000002"}]},"provider_name":"xAI","tag":"xai/zdr/priority","quantization":"unknown","max_completion_tokens":450000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.88195947275231,"uptime_last_5m":99.87515605493134,"uptime_last_1d":99.94326869566626,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.6-20260810","model_id":"x-ai/grok-4.6","model_name":"SpaceXAI: Grok 4.6","context_length":500000,"pricing":{"prompt":"0.000002","completion":"0.000006","web_search":"0.005","input_cache_read":"0.0000005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.000001"}]},"provider_name":"xAI","tag":"xai","quantization":"unknown","max_completion_tokens":450000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.92401215805471,"uptime_last_5m":100,"uptime_last_1d":99.91093733867645,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.6-20260810","model_id":"x-ai/grok-4.6","model_name":"SpaceXAI: Grok 4.6","context_length":500000,"pricing":{"prompt":"0.000004","completion":"0.000012","web_search":"0.005","input_cache_read":"0.000001","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000008","completion":"0.000024","input_cache_read":"0.000002"}]},"provider_name":"xAI","tag":"xai/priority","quantization":"unknown","max_completion_tokens":450000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.92401215805471,"uptime_last_5m":100,"uptime_last_1d":99.91093733867645,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":null},{"name":"Amazon Bedrock | x-ai/grok-4.6-20260810","model_id":"x-ai/grok-4.6","model_name":"SpaceXAI: Grok 4.6","context_length":500000,"pricing":{"prompt":"0.0000022","completion":"0.0000066","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000044","completion":"0.0000132","input_cache_read":"0.0000011","input_cache_write":"0"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us-west-2","quantization":"unknown","max_completion_tokens":450000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":6.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":0.0}],"_cheapest_provider":"xAI","_cheapest_blended_per_m":3.2e-06,"_priciest_blended_per_m":6.4e-06,"_provider_spread_multiplier":2.0},{"id":"nvidia/nemotron-3.5-lightning","canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","hugging_face_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","name":"NVIDIA: Nemotron 3.5 Lightning","created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.00000025","input_cache_read":"0.00000005"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-lightning-20260807/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":23.6,"coding_index":26.8,"agentic_index":13.8}},"reasoning":{"mandatory":false},"_prompt_per_m":1e-07,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | nvidia/nemotron-3.5-lightning-20260807","model_id":"nvidia/nemotron-3.5-lightning","model_name":"NVIDIA: Nemotron 3.5 Lightning","context_length":262144,"pricing":{"prompt":"0.00000008","completion":"0.0000002","input_cache_read":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.95818523938951,"uptime_last_5m":99.83831851253031,"uptime_last_1d":99.83492134723413,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-08,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"CoreWeave | nvidia/nemotron-3.5-lightning-20260807","model_id":"nvidia/nemotron-3.5-lightning","model_name":"NVIDIA: Nemotron 3.5 Lightning","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.00000025","input_cache_read":"0.00000005","discount":0},"provider_name":"CoreWeave","tag":"coreweave/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.90874281467265,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.1599999999999999e-07,"_priciest_blended_per_m":1.45e-07,"_provider_spread_multiplier":1.25},{"id":"sakana/sakana-namazu","canonical_slug":"sakana/namazu-20260811","hugging_face_id":null,"name":"Sakana: Sakana Namazu","created":1786410129,"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000095","completion":"0.000004","web_search":"0.007","input_cache_read":"0.00000015"},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/sakana/namazu-20260811/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","none"],"default_effort":"high"},"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Sakana AI | sakana/namazu-20260811","model_id":"sakana/sakana-namazu","model_name":"Sakana: Sakana Namazu","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","web_search":"0.007","input_cache_read":"0.00000015","discount":0},"provider_name":"Sakana AI","tag":"sakana","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","structured_outputs","web_search_options","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Sakana AI","_cheapest_blended_per_m":1.865e-06,"_priciest_blended_per_m":1.865e-06,"_provider_spread_multiplier":1.0},{"id":"meta/muse-glimmer-30b","canonical_slug":"meta/muse-glimmer-30b-20260810","hugging_face_id":"meta-models/Muse-Glimmer-30B","name":"Meta: Muse Glimmer 30B","created":1786302394,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000035","completion":"0.0000015","input_cache_read":"0.00000004"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-glimmer-30b-20260810/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"_prompt_per_m":3.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Phala | meta/muse-glimmer-30b-20260810","model_id":"meta/muse-glimmer-30b","model_name":"Meta: Muse Glimmer 30B","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.0000011","input_cache_read":"0.00000004","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.75150205095909,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Parasail | meta/muse-glimmer-30b-20260810","model_id":"meta/muse-glimmer-30b","model_name":"Meta: Muse Glimmer 30B","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.0000011","input_cache_read":"0.00000004","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97524829058507,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"DeepInfra | meta/muse-glimmer-30b-20260810","model_id":"meta/muse-glimmer-30b","model_name":"Meta: Muse Glimmer 30B","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.96277165061194,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Together | meta/muse-glimmer-30b-20260810","model_id":"meta/muse-glimmer-30b","model_name":"Meta: Muse Glimmer 30B","context_length":131072,"pricing":{"prompt":"0.00000035","completion":"0.0000015","input_cache_read":"0.00000004","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.83317886932345,"uptime_last_5m":99.822695035461,"uptime_last_1d":99.92892295093367,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Fireworks | meta/muse-glimmer-30b-20260810","model_id":"meta/muse-glimmer-30b","model_name":"Meta: Muse Glimmer 30B","context_length":131072,"pricing":{"prompt":"0.00000035","completion":"0.0000015","input_cache_read":"0.00000004","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":98.30394500896593,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Phala","_cheapest_blended_per_m":5.4e-07,"_priciest_blended_per_m":6.949999999999999e-07,"_provider_spread_multiplier":1.2870370370370368},{"id":"upstage/solar-pro4","canonical_slug":"upstage/solar-pro4-20260810","hugging_face_id":null,"name":"Upstage: Solar Pro 4","created":1786371636,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000003","completion":"0.00000012","input_cache_read":"0.000000006"},"top_provider":{"context_length":524288,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/upstage/solar-pro4-20260810/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1187,"win_rate":41.3,"rank":52},{"arena":"models","category":"codecategories","elo":1178,"win_rate":36,"rank":65},{"arena":"models","category":"dataviz","elo":1099,"win_rate":27.3,"rank":90},{"arena":"models","category":"gamedev","elo":1150,"win_rate":31.6,"rank":70},{"arena":"models","category":"uicomponent","elo":1182,"win_rate":36.4,"rank":61},{"arena":"models","category":"website","elo":1183,"win_rate":36.6,"rank":66}],"artificial_analysis":{"intelligence_index":41.6,"coding_index":52.7,"agentic_index":33.6}},"reasoning":{"mandatory":false},"_prompt_per_m":3e-08,"_completion_per_m":1.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-09,"_cached_write_per_m":null,"_endpoints":[{"name":"Upstage | upstage/solar-pro4-20260810","model_id":"upstage/solar-pro4","model_name":"Upstage: Solar Pro 4","context_length":524288,"pricing":{"prompt":"0.00000003","completion":"0.00000012","input_cache_read":"0.000000006","discount":0.9},"provider_name":"Upstage","tag":"upstage/zdr","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.42571785268414,"uptime_last_5m":99.10669975186104,"uptime_last_1d":99.17189304771996,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":1.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-09,"_cached_write_per_m":null},{"name":"Upstage | upstage/solar-pro4-20260810","model_id":"upstage/solar-pro4","model_name":"Upstage: Solar Pro 4","context_length":524288,"pricing":{"prompt":"0.00000003","completion":"0.00000012","input_cache_read":"0.000000006","discount":0.9},"provider_name":"Upstage","tag":"upstage","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.35207241543593,"uptime_last_5m":99.23619271445358,"uptime_last_1d":99.04674347228676,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":1.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-09,"_cached_write_per_m":null}],"_cheapest_provider":"Upstage","_cheapest_blended_per_m":5.6999999999999994e-08,"_priciest_blended_per_m":5.6999999999999994e-08,"_provider_spread_multiplier":1.0},{"id":"meta/muse-spark-1.2","canonical_slug":"meta/muse-spark-1.2-20260805","hugging_face_id":null,"name":"Meta: Muse Spark 1.2","created":1785959287,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00000425","web_search":"0.0025","input_cache_read":"0.00000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-spark-1.2-20260805/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1172,"win_rate":41.4,"rank":16},{"arena":"agents","category":"androidnative","elo":1247,"win_rate":56.5,"rank":10},{"arena":"agents","category":"fullstack","elo":1237,"win_rate":49.9,"rank":13},{"arena":"agents","category":"htmlslides","elo":1171,"win_rate":43.8,"rank":15},{"arena":"agents","category":"mobileapps","elo":1212,"win_rate":49.2,"rank":14},{"arena":"agents","category":"python-pptxslides","elo":1223,"win_rate":48.7,"rank":11},{"arena":"agents","category":"webapps","elo":1257,"win_rate":52.6,"rank":9},{"arena":"models","category":"3d","elo":1346,"win_rate":62.6,"rank":6},{"arena":"models","category":"codecategories","elo":1341,"win_rate":58.8,"rank":3},{"arena":"models","category":"dataviz","elo":1364,"win_rate":63.5,"rank":3},{"arena":"models","category":"gamedev","elo":1352,"win_rate":60.3,"rank":4},{"arena":"models","category":"uicomponent","elo":1348,"win_rate":59.7,"rank":4},{"arena":"models","category":"website","elo":1332,"win_rate":57.1,"rank":2}],"artificial_analysis":{"intelligence_index":56.8,"coding_index":72.2,"agentic_index":49.3}},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":1.25e-06,"_completion_per_m":4.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Meta | meta/muse-spark-1.2-20260805","model_id":"meta/muse-spark-1.2","model_name":"Meta: Muse Spark 1.2","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00000425","web_search":"0.0025","input_cache_read":"0.00000015","discount":0},"provider_name":"Meta","tag":"meta","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99916097880212,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":4.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Meta","_cheapest_blended_per_m":2.1499999999999997e-06,"_priciest_blended_per_m":2.1499999999999997e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.8-max","canonical_slug":"qwen/qwen3.8-max-20260803","hugging_face_id":null,"name":"Qwen: Qwen3.8 Max","created":1785731612,"description":"Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","input_cache_write":"0.0000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-max-20260803/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"fullstack","elo":1332,"win_rate":65.3,"rank":4},{"arena":"agents","category":"mobileapps","elo":1259,"win_rate":55.8,"rank":5},{"arena":"agents","category":"webapps","elo":1332,"win_rate":63.6,"rank":1},{"arena":"models","category":"3d","elo":1371,"win_rate":59.3,"rank":3},{"arena":"models","category":"codecategories","elo":1319,"win_rate":55,"rank":8},{"arena":"models","category":"dataviz","elo":1275,"win_rate":52,"rank":20},{"arena":"models","category":"gamedev","elo":1340,"win_rate":57.7,"rank":7},{"arena":"models","category":"uicomponent","elo":1353,"win_rate":60.2,"rank":3},{"arena":"models","category":"website","elo":1301,"win_rate":53.3,"rank":13}],"artificial_analysis":{"intelligence_index":58.1,"coding_index":71.8,"agentic_index":58.4}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"},"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":2.5e-06,"_endpoints":[{"name":"Alibaba | qwen/qwen3.8-max-20260803","model_id":"qwen/qwen3.8-max","model_name":"Qwen: Qwen3.8 Max","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","input_cache_write":"0.0000025","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99857874724223,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":2.5e-06}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":3.2e-06,"_priciest_blended_per_m":3.2e-06,"_provider_spread_multiplier":1.0},{"id":"~deepseek/deepseek-v4-flash-latest","canonical_slug":"~deepseek/deepseek-v4-flash-latest","alias_target":{"name":"DeepSeek: DeepSeek V4 Flash 0731","slug":"deepseek/deepseek-v4-flash-0731"},"hugging_face_id":null,"name":"DeepSeek V4 Flash Latest","created":1785606009,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","context_length":1310720,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.00000003","completion":"0.0000001","input_cache_read":"0.000000007"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":[],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~deepseek/deepseek-v4-flash-latest/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"high"},"_prompt_per_m":3e-08,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-09,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":5.0999999999999993e-08,"_priciest_blended_per_m":5.0999999999999993e-08,"_provider_spread_multiplier":null},{"id":"nvidia/nemotron-3.5-lightning:free","canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","hugging_face_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","name":"NVIDIA: Nemotron 3.5 Lightning (free)","created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-lightning-20260807/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":23.6,"coding_index":26.8,"agentic_index":13.8}},"reasoning":{"mandatory":false},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Nvidia | nvidia/nemotron-3.5-lightning-20260807:free","model_id":"nvidia/nemotron-3.5-lightning:free","model_name":"NVIDIA: Nemotron 3.5 Lightning","context_length":1000000,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Nvidia","tag":"nvidia/nvfp4","quantization":"nvfp4","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":0,"uptime_last_5m":0,"uptime_last_1d":86.55800177579603,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Nvidia","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"deepseek/deepseek-v4-flash-0731","canonical_slug":"deepseek/deepseek-v4-flash-20260731","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","context_length":1310720,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000007","completion":"0.00000014","input_cache_read":"0.000000014"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":[],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260731/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1251,"win_rate":50.5,"rank":33},{"arena":"models","category":"codecategories","elo":1256,"win_rate":47.5,"rank":35},{"arena":"models","category":"dataviz","elo":1198,"win_rate":40.8,"rank":51},{"arena":"models","category":"gamedev","elo":1249,"win_rate":46.1,"rank":33},{"arena":"models","category":"uicomponent","elo":1265,"win_rate":47.7,"rank":30},{"arena":"models","category":"website","elo":1261,"win_rate":47.6,"rank":33}],"artificial_analysis":{"intelligence_index":51.8,"coding_index":69.1,"agentic_index":48.4}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"high"},"_prompt_per_m":7e-08,"_completion_per_m":1.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenInference | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000003","completion":"0.0000001","input_cache_read":"0.000000007","discount":0},"provider_name":"OpenInference","tag":"open-inference/fp4","quantization":"fp4","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","stop","seed","top_p","frequency_penalty","presence_penalty","structured_outputs","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.9812414023094,"uptime_last_5m":99.97517131790644,"uptime_last_1d":99.99175169567286,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-09,"_cached_write_per_m":null},{"name":"Relace | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000007","completion":"0.00000014","input_cache_read":"0.000000014","discount":0},"provider_name":"Relace","tag":"relace/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","temperature","top_p","top_k","min_p","stop","max_tokens","logit_bias","frequency_penalty","presence_penalty","repetition_penalty","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.68955822247678,"uptime_last_5m":99.8491260349586,"uptime_last_1d":99.83352992096127,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":1.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-08,"_cached_write_per_m":null},{"name":"DeepInfra | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000008","completion":"0.00000018","input_cache_read":"0.000000016","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.60130574305632,"uptime_last_5m":99.19009265698966,"uptime_last_1d":99.01719225383667,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-08,"_completion_per_m":1.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-08,"_cached_write_per_m":null},{"name":"Ambient | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000008","completion":"0.00000018","input_cache_read":"0.000000016","discount":0},"provider_name":"Ambient","tag":"ambient/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","frequency_penalty","logit_bias","min_p","presence_penalty","repetition_penalty","seed","stop","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.50531443755536,"uptime_last_5m":99.18075649294056,"uptime_last_1d":98.9744097007151,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-08,"_completion_per_m":1.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-08,"_cached_write_per_m":null},{"name":"Makora | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1000000,"pricing":{"prompt":"0.00000009","completion":"0.000000195","input_cache_read":"0.0000000196","discount":0},"provider_name":"Makora","tag":"makora","quantization":"unknown","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":84.32917487415189,"uptime_last_5m":90.40097205346294,"uptime_last_1d":95.10646128114398,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":1.95e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.96e-08,"_cached_write_per_m":null},{"name":"Morph | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000009875","completion":"0.000000278","input_cache_read":"0.000000025","discount":0},"provider_name":"Morph","tag":"morph/bf16","quantization":"bf16","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.56053154755676,"uptime_last_5m":99.85665137614679,"uptime_last_1d":97.99262404216628,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.875e-08,"_completion_per_m":2.78e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null},{"name":"GMICloud | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048575,"pricing":{"prompt":"0.000000112","completion":"0.000000224","input_cache_read":"0.0000000224","discount":0.2},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":943717,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":95.19404415287657,"uptime_last_5m":95.51869274572914,"uptime_last_1d":95.68768299744721,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.12e-07,"_completion_per_m":2.24e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.24e-08,"_cached_write_per_m":null},{"name":"BaseTen | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000013","completion":"0.00000026","input_cache_read":"0.000000028","discount":0},"provider_name":"BaseTen","tag":"baseten/fp8","quantization":"fp8","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":85.24514338575393,"uptime_last_5m":29.933481152993345,"uptime_last_1d":96.51871106969445,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":2.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"Inceptron | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000013","completion":"0.00000028","input_cache_read":"0.00000003","discount":0},"provider_name":"Inceptron","tag":"inceptron/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.49832775919732,"uptime_last_5m":99.2725509214355,"uptime_last_1d":99.66808537969936,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"CoreWeave | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":262144,"pricing":{"prompt":"0.00000013","completion":"0.00000028","input_cache_read":"0.00000007","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.97514983189592,"uptime_last_5m":99.9847850893876,"uptime_last_1d":99.97000390558284,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"Baidu | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.000000028","discount":0},"provider_name":"Baidu","tag":"baidu/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.30129390018483,"uptime_last_5m":99.10514541387025,"uptime_last_1d":99.90321961166488,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"AkashML | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.00000002","discount":0},"provider_name":"AkashML","tag":"akashml/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.70508931580721,"uptime_last_5m":100,"uptime_last_1d":99.77168828548521,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null},{"name":"Parasail | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.00000005","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.94610824543845,"uptime_last_5m":99.93718592964824,"uptime_last_1d":97.69353714132475,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Together | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.00000003","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.81837052413077,"uptime_last_5m":100,"uptime_last_1d":99.71297523795556,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"DigitalOcean | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.000000028","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97586290127927,"uptime_last_5m":100,"uptime_last_1d":99.67055431577919,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"Mancer 2 | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000016","completion":"0.00000045","discount":0},"provider_name":"Mancer 2","tag":"mancer/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","response_format","logprobs","top_logprobs","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":97.51013317892298,"uptime_last_5m":97.87234042553192,"uptime_last_1d":97.8446009883293,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.6e-07,"_completion_per_m":4.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Venice | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1000000,"pricing":{"prompt":"0.000000175","completion":"0.00000035","input_cache_read":"0.000000035","discount":0},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.54333576110706,"uptime_last_5m":96.85534591194968,"uptime_last_1d":97.93623882184768,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.75e-07,"_completion_per_m":3.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-08,"_cached_write_per_m":null},{"name":"StreamLake | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1024000,"pricing":{"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007","discount":0.5},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","tools","tool_choice","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.9123063431745,"uptime_last_5m":99.9096657633243,"uptime_last_1d":99.87020740856111,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":6.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-09,"_cached_write_per_m":null},{"name":"Fireworks | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.13893414009775,"uptime_last_5m":95.99358974358975,"uptime_last_1d":99.48530002589125,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":6.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-09,"_cached_write_per_m":null},{"name":"Reka | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":262144,"pricing":{"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007","discount":0},"provider_name":"Reka","tag":"reka/fp4","quantization":"fp4","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.95317677568075,"uptime_last_5m":99.96202771976456,"uptime_last_1d":96.76343993228038,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":6.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-09,"_cached_write_per_m":null},{"name":"Phala | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.00000007","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.51152073732719,"uptime_last_5m":99.16434540389972,"uptime_last_1d":96.60509570548986,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":6.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000028","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.20919128618323,"uptime_last_5m":99.8623537508603,"uptime_last_1d":99.6397744820711,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":6.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"Wafer | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000028","completion":"0.00000056","input_cache_read":"0.00000007","discount":0},"provider_name":"Wafer","tag":"wafer/fast","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","logit_bias","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.91280612631739,"uptime_last_5m":100,"uptime_last_1d":97.40731772793548,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.8e-07,"_completion_per_m":5.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"Alibaba | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1000000,"pricing":{"prompt":"0.000000352","completion":"0.000001056","input_cache_read":"0.0000000352","discount":0,"overrides":[{"utc_start":0,"utc_end":1400,"prompt":"0.000000352","completion":"0.000001056","input_cache_read":"0.0000000352"},{"utc_start":1400,"utc_end":0,"prompt":"0.000000176","completion":"0.000000528","input_cache_read":"0.0000000176"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98906903905699,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.52e-07,"_completion_per_m":1.056e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.52e-08,"_cached_write_per_m":null},{"name":"Novita | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000028","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","response_format","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.98043490413103,"uptime_last_5m":99.98762376237624,"uptime_last_1d":99.90461693836662,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"DeepSeek | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014","discount":0,"overrides":[{"utc_days":["saturday","sunday"],"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"},{"utc_start":0,"utc_end":100,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"},{"utc_start":100,"utc_end":400,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014"},{"utc_start":400,"utc_end":600,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"},{"utc_start":600,"utc_end":1000,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014"},{"utc_start":1000,"utc_end":0,"utc_days":["monday","tuesday","wednesday","thursday","friday"],"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007"}]},"provider_name":"DeepSeek","tag":"deepseek","quantization":"unknown","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.98421163427128,"uptime_last_5m":99.92920711974111,"uptime_last_1d":99.97389593645812,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-08,"_cached_write_per_m":null},{"name":"NextBit | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000016","discount":0},"provider_name":"NextBit","tag":"nextbit/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.31660737689572,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-08,"_cached_write_per_m":null},{"name":"AtlasCloud | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1048576,"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000028","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp4","quantization":"fp4","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.67243799719232,"uptime_last_5m":100,"uptime_last_1d":99.4057211067059,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"Cloudflare | deepseek/deepseek-v4-flash-20260731","model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek: DeepSeek V4 Flash 0731","context_length":1310720,"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":1179648,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97382720264004,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-08,"_cached_write_per_m":null}],"_cheapest_provider":"OpenInference","_cheapest_blended_per_m":5.0999999999999993e-08,"_priciest_blended_per_m":7.04e-07,"_provider_spread_multiplier":13.803921568627452},{"id":"anthropic/claude-opus-5-fast","canonical_slug":"anthropic/claude-opus-5-fast-20260723","hugging_face_id":null,"name":"Claude Opus 5 (Fast)","created":1784912546,"description":"Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5-fast-20260723/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05,"_endpoints":[{"name":"Anthropic | anthropic/claude-opus-5-fast-20260723","model_id":"anthropic/claude-opus-5-fast","model_name":"Claude Opus 5 (Fast)","context_length":1000000,"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":2.2e-05,"_priciest_blended_per_m":2.2e-05,"_provider_spread_multiplier":1.0},{"id":"thinkingmachines/inkling-small:free","canonical_slug":"thinkingmachines/inkling-small-20260730","hugging_face_id":"thinkingmachines/Inkling-Small","name":"Thinking Machines: Inkling Small (free)","created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","context_length":1048576,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","seed","stop","temperature","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/thinkingmachines/inkling-small-20260730/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":41.2,"coding_index":52.9,"agentic_index":31.9}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Thinking Machines | thinkingmachines/inkling-small-20260730:free","model_id":"thinkingmachines/inkling-small:free","model_name":"Thinking Machines: Inkling Small","context_length":1048576,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Thinking Machines","tag":"thinkingmachines/nvfp4","quantization":"nvfp4","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","frequency_penalty","presence_penalty","seed","tools","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":false,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9651260880425,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Thinking Machines","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"anthropic/claude-opus-5:batch","canonical_slug":"anthropic/claude-opus-5-20260723","hugging_face_id":null,"name":"Claude Opus 5 (batch)","created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5-20260723/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1264,"win_rate":54.2,"rank":2},{"arena":"agents","category":"fullstack","elo":1347,"win_rate":69.1,"rank":3},{"arena":"agents","category":"webapps","elo":1270,"win_rate":56,"rank":7},{"arena":"models","category":"3d","elo":1373,"win_rate":63.2,"rank":2},{"arena":"models","category":"asciiart","elo":1393,"win_rate":71.3,"rank":1},{"arena":"models","category":"codecategories","elo":1348,"win_rate":59.2,"rank":2},{"arena":"models","category":"dataviz","elo":1356,"win_rate":60.6,"rank":4},{"arena":"models","category":"gamedev","elo":1382,"win_rate":62.3,"rank":3},{"arena":"models","category":"svg","elo":1362,"win_rate":62.7,"rank":1},{"arena":"models","category":"uicomponent","elo":1373,"win_rate":62.1,"rank":2},{"arena":"models","category":"website","elo":1331,"win_rate":57.4,"rank":3},{"arena":"agents","category":"mobileapps","elo":1280,"win_rate":58.6,"rank":1}],"artificial_analysis":{"intelligence_index":63.1,"coding_index":78,"agentic_index":59.2}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-opus-5-20260723:batch","model_id":"anthropic/claude-opus-5:batch","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":5.5e-06,"_priciest_blended_per_m":5.5e-06,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-opus-5","canonical_slug":"anthropic/claude-opus-5-20260723","hugging_face_id":null,"name":"Claude Opus 5","created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5-20260723/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1264,"win_rate":54.2,"rank":2},{"arena":"agents","category":"fullstack","elo":1347,"win_rate":69.1,"rank":3},{"arena":"agents","category":"webapps","elo":1270,"win_rate":56,"rank":7},{"arena":"models","category":"3d","elo":1373,"win_rate":63.2,"rank":2},{"arena":"models","category":"asciiart","elo":1393,"win_rate":71.3,"rank":1},{"arena":"models","category":"codecategories","elo":1348,"win_rate":59.2,"rank":2},{"arena":"models","category":"dataviz","elo":1356,"win_rate":60.6,"rank":4},{"arena":"models","category":"gamedev","elo":1382,"win_rate":62.3,"rank":3},{"arena":"models","category":"svg","elo":1362,"win_rate":62.7,"rank":1},{"arena":"models","category":"uicomponent","elo":1373,"win_rate":62.1,"rank":2},{"arena":"models","category":"website","elo":1331,"win_rate":57.4,"rank":3},{"arena":"agents","category":"mobileapps","elo":1280,"win_rate":58.6,"rank":1}],"artificial_analysis":{"intelligence_index":63.1,"coding_index":78,"agentic_index":59.2}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06,"_endpoints":[{"name":"Claude Platform on AWS | anthropic/claude-opus-5-20260723","model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Claude Platform on AWS","tag":"claude-on-aws","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98529772114678,"uptime_last_5m":100,"uptime_last_1d":99.93581521291345,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Azure | anthropic/claude-opus-5-20260723","model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Azure","tag":"azure/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.87116722494203,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Anthropic | anthropic/claude-opus-5-20260723","model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9332523542075,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Google | anthropic/claude-opus-5-20260723","model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.7039230199852,"uptime_last_5m":99.62121212121212,"uptime_last_1d":99.86284433798247,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Azure | anthropic/claude-opus-5-20260723","model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Amazon Bedrock | anthropic/claude-opus-5-20260723","model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97133027522935,"uptime_last_5m":100,"uptime_last_1d":99.90682665697892,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Amazon Bedrock | anthropic/claude-opus-5-20260723","model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us-east-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06},{"name":"Google | anthropic/claude-opus-5-20260723","model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06},{"name":"Google | anthropic/claude-opus-5-20260723","model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Google","tag":"google-vertex/europe","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06}],"_cheapest_provider":"Claude Platform on AWS","_cheapest_blended_per_m":1.1e-05,"_priciest_blended_per_m":1.21e-05,"_provider_spread_multiplier":1.0999999999999999},{"id":"qwen/qwen3.7-flash","canonical_slug":"qwen/qwen3.7-flash-20260727","hugging_face_id":null,"name":"Qwen: Qwen3.7 Flash","created":1785190561,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000003","completion":"0.00000013","input_cache_read":"0.000000006","input_cache_write":"0.000000038","overrides":[{"min_prompt_tokens":32000,"prompt":"0.0000001","completion":"0.0000004","input_cache_read":"0.00000002","input_cache_write":"0.000000125"},{"min_prompt_tokens":256000,"prompt":"0.0000002","completion":"0.0000008","input_cache_read":"0.00000004","input_cache_write":"0.00000025"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.7-flash-20260727/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"_prompt_per_m":3e-08,"_completion_per_m":1.3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-09,"_cached_write_per_m":3.8e-08,"_endpoints":[{"name":"Alibaba | qwen/qwen3.7-flash-20260727","model_id":"qwen/qwen3.7-flash","model_name":"Qwen: Qwen3.7 Flash","context_length":1000000,"pricing":{"prompt":"0.00000003","completion":"0.00000013","input_cache_read":"0.000000006","input_cache_write":"0.000000038","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.0000001","completion":"0.0000004","input_cache_read":"0.00000002","input_cache_write":"0.000000125"},{"min_prompt_tokens":256000,"prompt":"0.0000002","completion":"0.0000008","input_cache_read":"0.00000004","input_cache_write":"0.00000025"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.99939460716058,"uptime_last_5m":99.9964331573691,"uptime_last_1d":99.99839872913476,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":1.3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-09,"_cached_write_per_m":3.8e-08}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":6e-08,"_priciest_blended_per_m":6e-08,"_provider_spread_multiplier":1.0},{"id":"inclusionai/ling-3.0-flash","canonical_slug":"inclusionai/ling-3.0-flash-20260723","hugging_face_id":"inclusionAI/Ling-3.0-flash","name":"Ling-3.0-flash","created":1784818580,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000021","completion":"0.000000063","input_cache_read":"0.0000000042"},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/inclusionai/ling-3.0-flash-20260723/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":37.8,"coding_index":50.6,"agentic_index":29.3}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":2.1e-08,"_completion_per_m":6.3e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.2e-09,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | inclusionai/ling-3.0-flash-20260723","model_id":"inclusionai/ling-3.0-flash","model_name":"Ling-3.0-flash","context_length":262144,"pricing":{"prompt":"0.000000021","completion":"0.000000063","input_cache_read":"0.0000000042","discount":0.65},"provider_name":"Novita","tag":"novita","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.70282825522612,"uptime_last_5m":98.10260014054813,"uptime_last_1d":99.85977980794469,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-08,"_completion_per_m":6.3e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.2e-09,"_cached_write_per_m":null},{"name":"DeepInfra | inclusionai/ling-3.0-flash-20260723","model_id":"inclusionai/ling-3.0-flash","model_name":"Ling-3.0-flash","context_length":131072,"pricing":{"prompt":"0.00000006","completion":"0.00000018","input_cache_read":"0.000000012","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":-5,"uptime_last_30m":73.84105960264901,"uptime_last_5m":52.11726384364821,"uptime_last_1d":92.13896051024562,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-08,"_completion_per_m":1.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":3.3599999999999996e-08,"_priciest_blended_per_m":9.599999999999999e-08,"_provider_spread_multiplier":2.857142857142857},{"id":"poolside/laguna-s-2.1","canonical_slug":"poolside/laguna-s-2.1-20260720","hugging_face_id":"poolside/Laguna-S-2.1","name":"Poolside: Laguna S 2.1","created":1784652683,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000009","completion":"0.00000018","input_cache_read":"0.000000009"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/poolside/laguna-s-2.1-20260720/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":9e-08,"_completion_per_m":1.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9e-09,"_cached_write_per_m":null,"_endpoints":[{"name":"Poolside | poolside/laguna-s-2.1-20260720","model_id":"poolside/laguna-s-2.1","model_name":"Poolside: Laguna S 2.1","context_length":1048576,"pricing":{"prompt":"0.00000009","completion":"0.00000018","input_cache_read":"0.000000009","discount":0.1},"provider_name":"Poolside","tag":"poolside/fp4","quantization":"fp4","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","temperature","max_tokens"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9932963675889,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":1.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9e-09,"_cached_write_per_m":null}],"_cheapest_provider":"Poolside","_cheapest_blended_per_m":1.1699999999999999e-07,"_priciest_blended_per_m":1.1699999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"poolside/laguna-s-2.1:free","canonical_slug":"poolside/laguna-s-2.1-20260720","hugging_face_id":"poolside/Laguna-S-2.1","name":"Poolside: Laguna S 2.1 (free)","created":1784652683,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/poolside/laguna-s-2.1-20260720/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Poolside | poolside/laguna-s-2.1-20260720:free","model_id":"poolside/laguna-s-2.1:free","model_name":"Poolside: Laguna S 2.1","context_length":262144,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Poolside","tag":"poolside/fp4","quantization":"fp4","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99402115806652,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Poolside","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"google/gemini-3.6-flash:batch","canonical_slug":"google/gemini-3.6-flash-20260721","hugging_face_id":null,"name":"Google: Gemini 3.6 Flash (batch)","created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","web_search":"0.014","internal_reasoning":"0.000001875","input_cache_read":"0.0000000375","input_cache_write":"0.0000000416666666666667"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.6-flash-20260721/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1181,"win_rate":48,"rank":12},{"arena":"agents","category":"androidnative","elo":1220,"win_rate":53.8,"rank":13},{"arena":"agents","category":"fullstack","elo":1207,"win_rate":46.3,"rank":19},{"arena":"agents","category":"htmlslides","elo":1158,"win_rate":41.3,"rank":19},{"arena":"agents","category":"mobileapps","elo":1238,"win_rate":52.5,"rank":10},{"arena":"agents","category":"python-pptxslides","elo":1172,"win_rate":39.1,"rank":16},{"arena":"agents","category":"webapps","elo":1230,"win_rate":47.4,"rank":19},{"arena":"models","category":"3d","elo":1320,"win_rate":53.8,"rank":10},{"arena":"models","category":"asciiart","elo":1280,"win_rate":57,"rank":11},{"arena":"models","category":"codecategories","elo":1318,"win_rate":54.3,"rank":9},{"arena":"models","category":"dataviz","elo":1321,"win_rate":53.4,"rank":8},{"arena":"models","category":"gamedev","elo":1297,"win_rate":51.9,"rank":19},{"arena":"models","category":"uicomponent","elo":1331,"win_rate":56,"rank":8},{"arena":"models","category":"website","elo":1323,"win_rate":56.3,"rank":4}],"artificial_analysis":{"intelligence_index":51.6,"coding_index":69.2,"agentic_index":40.5}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":3.75e-07,"_completion_per_m":1.875e-06,"_image_per_m":3.75e-07,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":4.16666666666667e-08,"_endpoints":[{"name":"Google | google/gemini-3.6-flash-20260721:batch","model_id":"google/gemini-3.6-flash:batch","model_name":"Google: Gemini 3.6 Flash","context_length":1048576,"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","web_search":"0.014","internal_reasoning":"0.000001875","input_cache_read":"0.0000000375","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.75e-07,"_completion_per_m":1.875e-06,"_image_per_m":3.75e-07,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":4.16666666666667e-08}],"_cheapest_provider":"Google","_cheapest_blended_per_m":8.249999999999999e-07,"_priciest_blended_per_m":8.249999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3.5-flash-lite:batch","canonical_slug":"google/gemini-3.5-flash-lite-20260721","hugging_face_id":null,"name":"Google: Gemini 3.5 Flash Lite (batch)","created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","audio":"0.00000015","input_audio_cache":"0.000000015","web_search":"0.014","internal_reasoning":"0.00000125","input_cache_read":"0.000000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.5-flash-lite-20260721/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":37.4,"coding_index":49.3,"agentic_index":27.2}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"},"_prompt_per_m":1.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":1.5e-07,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | google/gemini-3.5-flash-lite-20260721:batch","model_id":"google/gemini-3.5-flash-lite:batch","model_name":"Google: Gemini 3.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","audio":"0.00000015","input_audio_cache":"0.000000015","web_search":"0.014","internal_reasoning":"0.00000125","input_cache_read":"0.000000015","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":1.5e-07,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Google","_cheapest_blended_per_m":4.8e-07,"_priciest_blended_per_m":4.8e-07,"_provider_spread_multiplier":1.0},{"id":"meituan/longcat-2.0","canonical_slug":"meituan/longcat-2.0-20260720","hugging_face_id":"meituan-longcat/LongCat-2.0","name":"Meituan: LongCat 2.0","created":1784554658,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","context_length":1048756,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},"top_provider":{"context_length":1048756,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meituan/longcat-2.0-20260720/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":34,"coding_index":45.3,"agentic_index":22}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-09,"_cached_write_per_m":null,"_endpoints":[{"name":"AtlasCloud | meituan/longcat-2.0-20260720","model_id":"meituan/longcat-2.0","model_name":"Meituan: LongCat 2.0","context_length":1048756,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006","discount":0.6},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","stop","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-09,"_cached_write_per_m":null}],"_cheapest_provider":"AtlasCloud","_cheapest_blended_per_m":5.699999999999999e-07,"_priciest_blended_per_m":5.699999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3.6-flash","canonical_slug":"google/gemini-3.6-flash-20260721","hugging_face_id":null,"name":"Google: Gemini 3.6 Flash","created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","audio":"0.00000075","input_audio_cache":"0.000000075","web_search":"0.014","internal_reasoning":"0.00000375","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.6-flash-20260721/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1181,"win_rate":48,"rank":12},{"arena":"agents","category":"androidnative","elo":1220,"win_rate":53.8,"rank":13},{"arena":"agents","category":"fullstack","elo":1207,"win_rate":46.3,"rank":19},{"arena":"agents","category":"htmlslides","elo":1158,"win_rate":41.3,"rank":19},{"arena":"agents","category":"mobileapps","elo":1238,"win_rate":52.5,"rank":10},{"arena":"agents","category":"python-pptxslides","elo":1172,"win_rate":39.1,"rank":16},{"arena":"agents","category":"webapps","elo":1230,"win_rate":47.4,"rank":19},{"arena":"models","category":"3d","elo":1320,"win_rate":53.8,"rank":10},{"arena":"models","category":"asciiart","elo":1280,"win_rate":57,"rank":11},{"arena":"models","category":"codecategories","elo":1318,"win_rate":54.3,"rank":9},{"arena":"models","category":"dataviz","elo":1321,"win_rate":53.4,"rank":8},{"arena":"models","category":"gamedev","elo":1297,"win_rate":51.9,"rank":19},{"arena":"models","category":"uicomponent","elo":1331,"win_rate":56,"rank":8},{"arena":"models","category":"website","elo":1323,"win_rate":56.3,"rank":4}],"artificial_analysis":{"intelligence_index":51.6,"coding_index":69.2,"agentic_index":40.5}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":7.5e-07,"_completion_per_m":3.75e-06,"_image_per_m":7.5e-07,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":4.16666666666667e-08,"_endpoints":[{"name":"Google AI Studio | google/gemini-3.6-flash-20260721","model_id":"google/gemini-3.6-flash","model_name":"Google: Gemini 3.6 Flash","context_length":1048576,"pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","audio":"0.00000075","input_audio_cache":"0.000000075","web_search":"0.014","internal_reasoning":"0.00000375","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.20496894409938,"uptime_last_5m":99.26315789473684,"uptime_last_1d":99.24189077414883,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":3.75e-06,"_image_per_m":7.5e-07,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-3.6-flash-20260721","model_id":"google/gemini-3.6-flash","model_name":"Google: Gemini 3.6 Flash","context_length":1048576,"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","web_search":"0.014","internal_reasoning":"0.000001875","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.20496894409938,"uptime_last_5m":99.26315789473684,"uptime_last_1d":99.24189077414883,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.75e-07,"_completion_per_m":1.875e-06,"_image_per_m":3.75e-07,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":2.08333333333333e-08},{"name":"Google AI Studio | google/gemini-3.6-flash-20260721","model_id":"google/gemini-3.6-flash","model_name":"Google: Gemini 3.6 Flash","context_length":1048576,"pricing":{"prompt":"0.00000135","completion":"0.00000675","image":"0.00000135","audio":"0.00000135","input_audio_cache":"0.000000135","web_search":"0.014","internal_reasoning":"0.00000675","input_cache_read":"0.000000135","input_cache_write":"0.000000075","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.20496894409938,"uptime_last_5m":99.26315789473684,"uptime_last_1d":99.24189077414883,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.35e-06,"_completion_per_m":6.75e-06,"_image_per_m":1.35e-06,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":7.5e-08},{"name":"Google | google/gemini-3.6-flash-20260721","model_id":"google/gemini-3.6-flash","model_name":"Google: Gemini 3.6 Flash","context_length":1048576,"pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","audio":"0.00000075","input_audio_cache":"0.000000075","web_search":"0.014","internal_reasoning":"0.00000375","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.2489270386266,"uptime_last_5m":99.95684074233924,"uptime_last_1d":99.63353654359888,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":3.75e-06,"_image_per_m":7.5e-07,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google | google/gemini-3.6-flash-20260721","model_id":"google/gemini-3.6-flash","model_name":"Google: Gemini 3.6 Flash","context_length":1048576,"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","web_search":"0.014","internal_reasoning":"0.000001875","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.2489270386266,"uptime_last_5m":99.95684074233924,"uptime_last_1d":99.63353654359888,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.75e-07,"_completion_per_m":1.875e-06,"_image_per_m":3.75e-07,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":2.08333333333333e-08},{"name":"Google | google/gemini-3.6-flash-20260721","model_id":"google/gemini-3.6-flash","model_name":"Google: Gemini 3.6 Flash","context_length":1048576,"pricing":{"prompt":"0.00000135","completion":"0.00000675","image":"0.00000135","audio":"0.00000135","input_audio_cache":"0.000000135","web_search":"0.014","internal_reasoning":"0.00000675","input_cache_read":"0.000000135","input_cache_write":"0.000000075","discount":0},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.2489270386266,"uptime_last_5m":99.95684074233924,"uptime_last_1d":99.63353654359888,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.35e-06,"_completion_per_m":6.75e-06,"_image_per_m":1.35e-06,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":7.5e-08},{"name":"Google | google/gemini-3.6-flash-20260721","model_id":"google/gemini-3.6-flash","model_name":"Google: Gemini 3.6 Flash","context_length":1048576,"pricing":{"prompt":"0.000000825","completion":"0.000004125","image":"0.000000825","audio":"0.000000825","input_audio_cache":"0.0000000825","web_search":"0.014","internal_reasoning":"0.000004125","input_cache_read":"0.0000000825","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.25e-07,"_completion_per_m":4.125e-06,"_image_per_m":8.25e-07,"_request_per_m":null,"_cached_read_per_m":8.25e-08,"_cached_write_per_m":4.16666666666667e-08}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":8.249999999999999e-07,"_priciest_blended_per_m":2.9699999999999995e-06,"_provider_spread_multiplier":3.5999999999999996},{"id":"google/gemini-3.5-flash-lite","canonical_slug":"google/gemini-3.5-flash-lite-20260721","hugging_face_id":null,"name":"Google: Gemini 3.5 Flash Lite","created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.0000003","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.5-flash-lite-20260721/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":37.4,"coding_index":49.3,"agentic_index":27.2}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"},"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08,"_endpoints":[{"name":"Google AI Studio | google/gemini-3.5-flash-lite-20260721","model_id":"google/gemini-3.5-flash-lite","model_name":"Google: Gemini 3.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.0000003","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.94040605149459,"uptime_last_5m":99.92334554126565,"uptime_last_1d":99.88076602900058,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-3.5-flash-lite-20260721","model_id":"google/gemini-3.5-flash-lite","model_name":"Google: Gemini 3.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","audio":"0.00000015","input_audio_cache":"0.000000015","web_search":"0.014","internal_reasoning":"0.00000125","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.94040605149459,"uptime_last_5m":99.92334554126565,"uptime_last_1d":99.88076602900058,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":1.5e-07,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-3.5-flash-lite-20260721","model_id":"google/gemini-3.5-flash-lite","model_name":"Google: Gemini 3.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000054","completion":"0.0000045","image":"0.00000054","audio":"0.00000054","input_audio_cache":"0.000000054","web_search":"0.014","internal_reasoning":"0.0000045","input_cache_read":"0.000000054","input_cache_write":"0.00000015","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.94040605149459,"uptime_last_5m":99.92334554126565,"uptime_last_1d":99.88076602900058,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.4e-07,"_completion_per_m":4.5e-06,"_image_per_m":5.4e-07,"_request_per_m":null,"_cached_read_per_m":5.4e-08,"_cached_write_per_m":1.5e-07},{"name":"Google | google/gemini-3.5-flash-lite-20260721","model_id":"google/gemini-3.5-flash-lite","model_name":"Google: Gemini 3.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.0000003","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.86342146734373,"uptime_last_5m":99.83507421660252,"uptime_last_1d":99.87638701327386,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google | google/gemini-3.5-flash-lite-20260721","model_id":"google/gemini-3.5-flash-lite","model_name":"Google: Gemini 3.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","audio":"0.00000015","input_audio_cache":"0.000000015","web_search":"0.014","internal_reasoning":"0.00000125","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.86342146734373,"uptime_last_5m":99.83507421660252,"uptime_last_1d":99.87638701327386,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":1.5e-07,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google | google/gemini-3.5-flash-lite-20260721","model_id":"google/gemini-3.5-flash-lite","model_name":"Google: Gemini 3.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000054","completion":"0.0000045","image":"0.00000054","audio":"0.00000054","input_audio_cache":"0.000000054","web_search":"0.014","internal_reasoning":"0.0000045","input_cache_read":"0.000000054","input_cache_write":"0.00000015","discount":0},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.86342146734373,"uptime_last_5m":99.83507421660252,"uptime_last_1d":99.87638701327386,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.4e-07,"_completion_per_m":4.5e-06,"_image_per_m":5.4e-07,"_request_per_m":null,"_cached_read_per_m":5.4e-08,"_cached_write_per_m":1.5e-07},{"name":"Google | google/gemini-3.5-flash-lite-20260721","model_id":"google/gemini-3.5-flash-lite","model_name":"Google: Gemini 3.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000033","completion":"0.00000275","image":"0.00000033","audio":"0.00000033","input_audio_cache":"0.000000033","web_search":"0.014","internal_reasoning":"0.00000275","input_cache_read":"0.000000033","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/eu","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-07,"_completion_per_m":2.75e-06,"_image_per_m":3.3e-07,"_request_per_m":null,"_cached_read_per_m":3.3e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google | google/gemini-3.5-flash-lite-20260721","model_id":"google/gemini-3.5-flash-lite","model_name":"Google: Gemini 3.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000033","completion":"0.00000275","image":"0.00000033","audio":"0.00000033","input_audio_cache":"0.000000033","web_search":"0.014","internal_reasoning":"0.00000275","input_cache_read":"0.000000033","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-07,"_completion_per_m":2.75e-06,"_image_per_m":3.3e-07,"_request_per_m":null,"_cached_read_per_m":3.3e-08,"_cached_write_per_m":8.33333333333333e-08}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":4.8e-07,"_priciest_blended_per_m":1.728e-06,"_provider_spread_multiplier":3.6000000000000005},{"id":"thinkingmachines/inkling","canonical_slug":"thinkingmachines/inkling-20260715","hugging_face_id":"thinkingmachines/Inkling","name":"Thinking Machines: Inkling","created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","context_length":1048576,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000095","completion":"0.00000405","input_cache_read":"0.00000016"},"top_provider":{"context_length":524288,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/thinkingmachines/inkling-20260715/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1203,"win_rate":43.9,"rank":47},{"arena":"models","category":"asciiart","elo":1131,"win_rate":36.4,"rank":51},{"arena":"models","category":"codecategories","elo":1219,"win_rate":42.1,"rank":44},{"arena":"models","category":"dataviz","elo":1189,"win_rate":39.3,"rank":55},{"arena":"models","category":"gamedev","elo":1192,"win_rate":38.4,"rank":54},{"arena":"models","category":"uicomponent","elo":1202,"win_rate":40.2,"rank":50},{"arena":"models","category":"website","elo":1227,"win_rate":42.9,"rank":44}],"artificial_analysis":{"intelligence_index":42.3,"coding_index":52.1,"agentic_index":34.1}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"},"_prompt_per_m":9.5e-07,"_completion_per_m":4.05e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | thinkingmachines/inkling-20260715","model_id":"thinkingmachines/inkling","model_name":"Thinking Machines: Inkling","context_length":524288,"pricing":{"prompt":"0.00000095","completion":"0.00000405","input_cache_read":"0.00000016","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.84946236559139,"uptime_last_5m":100,"uptime_last_1d":99.622791952895,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4.05e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"Together | thinkingmachines/inkling-20260715","model_id":"thinkingmachines/inkling","model_name":"Thinking Machines: Inkling","context_length":524288,"pricing":{"prompt":"0.000001","completion":"0.00000405","input_cache_read":"0.00000017","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":471859,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":77.57847533632287,"uptime_last_5m":74.54545454545455,"uptime_last_1d":99.32361439453639,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":4.05e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.7e-07,"_cached_write_per_m":null},{"name":"BaseTen | thinkingmachines/inkling-20260715","model_id":"thinkingmachines/inkling","model_name":"Thinking Machines: Inkling","context_length":1048576,"pricing":{"prompt":"0.000001","completion":"0.00000405","input_cache_read":"0.00000017","discount":0},"provider_name":"BaseTen","tag":"baseten/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96124782018988,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":4.05e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.7e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.88e-06,"_priciest_blended_per_m":1.915e-06,"_provider_spread_multiplier":1.0186170212765957},{"id":"thinkingmachines/inkling:batch","canonical_slug":"thinkingmachines/inkling-20260715","hugging_face_id":"thinkingmachines/Inkling","name":"Thinking Machines: Inkling (batch)","created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","context_length":524288,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.00000405","input_cache_read":"0.00000017"},"top_provider":{"context_length":524288,"max_completion_tokens":471859,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/thinkingmachines/inkling-20260715/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1203,"win_rate":43.9,"rank":47},{"arena":"models","category":"asciiart","elo":1131,"win_rate":36.4,"rank":51},{"arena":"models","category":"codecategories","elo":1219,"win_rate":42.1,"rank":44},{"arena":"models","category":"dataviz","elo":1189,"win_rate":39.3,"rank":55},{"arena":"models","category":"gamedev","elo":1192,"win_rate":38.4,"rank":54},{"arena":"models","category":"uicomponent","elo":1202,"win_rate":40.2,"rank":50},{"arena":"models","category":"website","elo":1227,"win_rate":42.9,"rank":44}],"artificial_analysis":{"intelligence_index":42.3,"coding_index":52.1,"agentic_index":34.1}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"},"_prompt_per_m":1e-06,"_completion_per_m":4.05e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.7e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Together | thinkingmachines/inkling-20260715:batch","model_id":"thinkingmachines/inkling:batch","model_name":"Thinking Machines: Inkling","context_length":524288,"pricing":{"prompt":"0.000001","completion":"0.00000405","input_cache_read":"0.00000017","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":471859,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":4.05e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.7e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Together","_cheapest_blended_per_m":1.915e-06,"_priciest_blended_per_m":1.915e-06,"_provider_spread_multiplier":1.0},{"id":"thinkingmachines/inkling:free","canonical_slug":"thinkingmachines/inkling-20260715","hugging_face_id":"thinkingmachines/Inkling","name":"Thinking Machines: Inkling (free)","created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","context_length":1048576,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","seed","stop","temperature","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/thinkingmachines/inkling-20260715/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1203,"win_rate":43.9,"rank":47},{"arena":"models","category":"asciiart","elo":1131,"win_rate":36.4,"rank":51},{"arena":"models","category":"codecategories","elo":1219,"win_rate":42.1,"rank":44},{"arena":"models","category":"dataviz","elo":1189,"win_rate":39.3,"rank":55},{"arena":"models","category":"gamedev","elo":1192,"win_rate":38.4,"rank":54},{"arena":"models","category":"uicomponent","elo":1202,"win_rate":40.2,"rank":50},{"arena":"models","category":"website","elo":1227,"win_rate":42.9,"rank":44}],"artificial_analysis":{"intelligence_index":42.3,"coding_index":52.1,"agentic_index":34.1}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Thinking Machines | thinkingmachines/inkling-20260715:free","model_id":"thinkingmachines/inkling:free","model_name":"Thinking Machines: Inkling","context_length":1048576,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Thinking Machines","tag":"thinkingmachines/nvfp4","quantization":"nvfp4","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","frequency_penalty","presence_penalty","seed","tools","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":false,"required":false,"function":false},"status":0,"uptime_last_30m":99.9269094895846,"uptime_last_5m":100,"uptime_last_1d":99.87705373515846,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Thinking Machines","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"openrouter/auto-beta","canonical_slug":"openrouter/auto-beta","hugging_face_id":null,"name":"Auto Router (Beta)","created":1784311165,"description":"Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregate spend, filtered by your...","context_length":2000000,"architecture":{"modality":"text+image+file+audio+video->text+image","input_modalities":["text","image","audio","file","video"],"output_modalities":["text","image"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","prediction","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","web_search_options"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openrouter/auto-beta/endpoints"},"_prompt_per_m":-1.0,"_completion_per_m":-1.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":-1.0,"_priciest_blended_per_m":-1.0,"_provider_spread_multiplier":null},{"id":"kwaipilot/kat-coder-air-v2.5","canonical_slug":"kwaipilot/kat-coder-air-v2.5-20260710","hugging_face_id":null,"name":"Kwaipilot: KAT-Coder-Air V2.5","created":1783714590,"description":"KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.00000003"},"top_provider":{"context_length":256000,"max_completion_tokens":80000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["logprobs","max_tokens","presence_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/kwaipilot/kat-coder-air-v2.5-20260710/endpoints"},"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"StreamLake | kwaipilot/kat-coder-air-v2.5-20260710","model_id":"kwaipilot/kat-coder-air-v2.5","model_name":"Kwaipilot: KAT-Coder-Air V2.5","context_length":256000,"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.00000003","discount":0},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":80000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","presence_penalty","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"StreamLake","_cheapest_blended_per_m":2.8499999999999997e-07,"_priciest_blended_per_m":2.8499999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"moonshotai/kimi-k3","canonical_slug":"moonshotai/kimi-k3-20260715","hugging_face_id":"moonshotai/Kimi-K3","name":"MoonshotAI: Kimi K3","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3-20260715/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1247,"win_rate":53.8,"rank":4},{"arena":"agents","category":"androidnative","elo":1256,"win_rate":56.7,"rank":6},{"arena":"agents","category":"fullstack","elo":1365,"win_rate":68.7,"rank":2},{"arena":"agents","category":"godotgamedev","elo":1199,"win_rate":48.5,"rank":11},{"arena":"agents","category":"htmlslides","elo":1264,"win_rate":59.1,"rank":2},{"arena":"agents","category":"mobileapps","elo":1280,"win_rate":57.4,"rank":2},{"arena":"agents","category":"python-pptxslides","elo":1296,"win_rate":59.6,"rank":4},{"arena":"agents","category":"webapps","elo":1329,"win_rate":63.4,"rank":2},{"arena":"models","category":"3d","elo":1442,"win_rate":69.3,"rank":1},{"arena":"models","category":"codecategories","elo":1403,"win_rate":65.7,"rank":1},{"arena":"models","category":"dataviz","elo":1374,"win_rate":64.9,"rank":1},{"arena":"models","category":"gamedev","elo":1431,"win_rate":68.2,"rank":1},{"arena":"models","category":"svg","elo":1350,"win_rate":65,"rank":2},{"arena":"models","category":"uicomponent","elo":1376,"win_rate":63.2,"rank":1},{"arena":"models","category":"website","elo":1367,"win_rate":62.2,"rank":1}],"artificial_analysis":{"intelligence_index":59.7,"coding_index":76.2,"agentic_index":54.3}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Makora | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.00000255","completion":"0.00001275","input_cache_read":"0.00000025599999","discount":0},"provider_name":"Makora","tag":"makora","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":90,"uptime_last_5m":null,"uptime_last_1d":84.65703971119135,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.55e-06,"_completion_per_m":1.275e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5599999e-07,"_cached_write_per_m":null},{"name":"Sail Research | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":974842,"pricing":{"prompt":"0.0000026","completion":"0.000013","input_cache_read":"0.00000029","discount":0},"provider_name":"Sail Research","tag":"sail-research/fp4","quantization":"fp4","max_completion_tokens":877357,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","stop","seed","max_tokens","tools","tool_choice","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.59404600811908,"uptime_last_5m":100,"uptime_last_1d":98.65710985398218,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-06,"_completion_per_m":1.3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.9e-07,"_cached_write_per_m":null},{"name":"Morph | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.0000028","completion":"0.000014","input_cache_read":"0.00000029","discount":0},"provider_name":"Morph","tag":"morph/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.79776728209532,"uptime_last_5m":98.82697947214076,"uptime_last_1d":94.7296372347707,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.8e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.9e-07,"_cached_write_per_m":null},{"name":"DeepInfra | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.00000285","completion":"0.00001425","input_cache_read":"0.000000285","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.05882352941177,"uptime_last_5m":90.57591623036649,"uptime_last_1d":96.23112872310641,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.85e-06,"_completion_per_m":1.425e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.85e-07,"_cached_write_per_m":null},{"name":"Parasail | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"provider_name":"Parasail","tag":"parasail/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.53694581280789,"uptime_last_5m":100,"uptime_last_1d":94.00635930047694,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"BaseTen | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"provider_name":"BaseTen","tag":"baseten/fp8","quantization":"fp8","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.76543209876543,"uptime_last_5m":100,"uptime_last_1d":99.33816183816184,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","logprobs","top_logprobs","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.91369841518907,"uptime_last_5m":99.88768251591165,"uptime_last_1d":99.5113511898835,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"Together | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.73465777656824,"uptime_last_5m":100,"uptime_last_1d":98.89289661728519,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"Moonshot AI | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"provider_name":"Moonshot AI","tag":"moonshotai/mxfp4","quantization":"mxfp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","frequency_penalty","presence_penalty","structured_outputs","response_format","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.89602495401104,"uptime_last_5m":99.94597514856835,"uptime_last_1d":98.64232325539774,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"Phala | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.27536231884058,"uptime_last_5m":97.77777777777777,"uptime_last_1d":94.86329150164623,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"Fireworks | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.91379310344828,"uptime_last_5m":100,"uptime_last_1d":98.00044178519636,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"Modal | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"provider_name":"Modal","tag":"modal/mxfp4","quantization":"mxfp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","max_tokens","response_format","structured_outputs","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97596346446599,"uptime_last_5m":99.95929995929997,"uptime_last_1d":99.7294267945813,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"Chutes | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"provider_name":"Chutes","tag":"chutes/mxfp4","quantization":"mxfp4","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.09523809523809,"uptime_last_5m":98.38274932614556,"uptime_last_1d":97.94847415479695,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"Fireworks | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.0000033","completion":"0.0000165","input_cache_read":"0.00000033","discount":0},"provider_name":"Fireworks","tag":"fireworks/us","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.92541087231352,"uptime_last_5m":99.7159090909091,"uptime_last_1d":97.81782658976145,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-07,"_cached_write_per_m":null},{"name":"Alibaba | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.00000345","completion":"0.00001725","input_cache_read":"0.000000345","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.7012987012987,"uptime_last_5m":null,"uptime_last_1d":99.44440157419554,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.45e-06,"_completion_per_m":1.725e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.45e-07,"_cached_write_per_m":null},{"name":"Fireworks | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.0000045","completion":"0.0000225","input_cache_read":"0.00000045","discount":0},"provider_name":"Fireworks","tag":"fireworks/fast","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.06542056074767,"uptime_last_5m":null,"uptime_last_1d":97.61994997347078,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-06,"_completion_per_m":2.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.5e-07,"_cached_write_per_m":null},{"name":"Morph | moonshotai/kimi-k3-20260715","model_id":"moonshotai/kimi-k3","model_name":"MoonshotAI: Kimi K3","context_length":1048576,"pricing":{"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","discount":0},"provider_name":"Morph","tag":"morph/fast","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":92.25523623964929,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-06,"_completion_per_m":2.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Makora","_cheapest_blended_per_m":5.61e-06,"_priciest_blended_per_m":1.095e-05,"_provider_spread_multiplier":1.951871657754011},{"id":"openai/gpt-5.6-luna-pro","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Luna Pro","created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000012","web_search":"0.01","input_cache_read":"0.00000002","input_cache_write":"0.00000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-luna-pro-20260709/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":2.5e-07,"_endpoints":[{"name":"Azure | openai/gpt-5.6-luna-pro-20260709","model_id":"openai/gpt-5.6-luna-pro","model_name":"OpenAI: GPT-5.6 Luna Pro","context_length":1050000,"pricing":{"prompt":"0.0000002","completion":"0.0000012","web_search":"0.01","input_cache_read":"0.00000002","input_cache_write":"0.00000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}]},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":82.77066356228173,"uptime_last_5m":54.90196078431373,"uptime_last_1d":92.160409556314,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":2.5e-07},{"name":"OpenAI | openai/gpt-5.6-luna-pro-20260709","model_id":"openai/gpt-5.6-luna-pro","model_name":"OpenAI: GPT-5.6 Luna Pro","context_length":1050000,"pricing":{"prompt":"0.0000002","completion":"0.0000012","web_search":"0.01","input_cache_read":"0.00000002","input_cache_write":"0.00000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.50741673663588,"uptime_last_5m":99.52963311382878,"uptime_last_1d":99.55498950537482,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":2.5e-07},{"name":"OpenAI | openai/gpt-5.6-luna-pro-20260709","model_id":"openai/gpt-5.6-luna-pro","model_name":"OpenAI: GPT-5.6 Luna Pro","context_length":1050000,"pricing":{"prompt":"0.0000001","completion":"0.0000006","web_search":"0.01","input_cache_read":"0.00000001","input_cache_write":"0.000000125","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000002","completion":"0.0000009","input_cache_read":"0.00000002","input_cache_write":"0.00000025"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.50741673663588,"uptime_last_5m":99.52963311382878,"uptime_last_1d":99.55498950537482,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":1.25e-07},{"name":"OpenAI | openai/gpt-5.6-luna-pro-20260709","model_id":"openai/gpt-5.6-luna-pro","model_name":"OpenAI: GPT-5.6 Luna Pro","context_length":1050000,"pricing":{"prompt":"0.0000004","completion":"0.0000024","web_search":"0.01","input_cache_read":"0.00000004","input_cache_write":"0.0000005","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000008","completion":"0.0000036","input_cache_read":"0.00000008","input_cache_write":"0.000001"}]},"provider_name":"OpenAI","tag":"openai/priority","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.50741673663588,"uptime_last_5m":99.52963311382878,"uptime_last_1d":99.55498950537482,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":5e-07},{"name":"Azure | openai/gpt-5.6-luna-pro-20260709","model_id":"openai/gpt-5.6-luna-pro","model_name":"OpenAI: GPT-5.6 Luna Pro","context_length":1050000,"pricing":{"prompt":"0.00000022","completion":"0.00000132","web_search":"0.01","input_cache_read":"0.000000022","input_cache_write":"0.000000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00000044","completion":"0.00000198","input_cache_read":"0.000000044","input_cache_write":"0.00000055"}]},"provider_name":"Azure","tag":"azure/eu","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-08,"_cached_write_per_m":2.75e-07}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.5e-07,"_priciest_blended_per_m":1e-06,"_provider_spread_multiplier":4.0},{"id":"meta/muse-spark-1.1","canonical_slug":"meta/muse-spark-1.1-20260709","hugging_face_id":null,"name":"Meta: Muse Spark 1.1","created":1784215741,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00000425","web_search":"0.0025","input_cache_read":"0.00000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-spark-1.1-20260709/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1183,"win_rate":48.3,"rank":11},{"arena":"agents","category":"androidnative","elo":1201,"win_rate":47.7,"rank":16},{"arena":"agents","category":"fullstack","elo":1232,"win_rate":48.4,"rank":14},{"arena":"agents","category":"godotgamedev","elo":1141,"win_rate":39.4,"rank":20},{"arena":"agents","category":"htmlslides","elo":1209,"win_rate":52,"rank":8},{"arena":"agents","category":"mobileapps","elo":1199,"win_rate":46,"rank":19},{"arena":"agents","category":"python-pptxslides","elo":1178,"win_rate":44.2,"rank":15},{"arena":"agents","category":"webapps","elo":1234,"win_rate":50.2,"rank":16},{"arena":"models","category":"3d","elo":1298,"win_rate":53.7,"rank":17},{"arena":"models","category":"asciiart","elo":1315,"win_rate":61.2,"rank":3},{"arena":"models","category":"codecategories","elo":1301,"win_rate":53.7,"rank":14},{"arena":"models","category":"dataviz","elo":1300,"win_rate":53.8,"rank":13},{"arena":"models","category":"gamedev","elo":1316,"win_rate":53.7,"rank":12},{"arena":"models","category":"svg","elo":1272,"win_rate":52.2,"rank":7},{"arena":"models","category":"uicomponent","elo":1317,"win_rate":54.5,"rank":10},{"arena":"models","category":"website","elo":1288,"win_rate":52.7,"rank":21}],"artificial_analysis":{"intelligence_index":53.2,"coding_index":71.3,"agentic_index":39.7}},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":1.25e-06,"_completion_per_m":4.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Meta | meta/muse-spark-1.1-20260709","model_id":"meta/muse-spark-1.1","model_name":"Meta: Muse Spark 1.1","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00000425","web_search":"0.0025","input_cache_read":"0.00000015","discount":0},"provider_name":"Meta","tag":"meta","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":4.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Meta","_cheapest_blended_per_m":2.1499999999999997e-06,"_priciest_blended_per_m":2.1499999999999997e-06,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.6-luna","canonical_slug":"openai/gpt-5.6-luna-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Luna","created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000012","web_search":"0.01","input_cache_read":"0.00000002","input_cache_write":"0.00000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":52.3,"coding_index":71.4,"agentic_index":46.9}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":2.5e-07,"_endpoints":[{"name":"Azure | openai/gpt-5.6-luna-20260709","model_id":"openai/gpt-5.6-luna","model_name":"OpenAI: GPT-5.6 Luna","context_length":1050000,"pricing":{"prompt":"0.0000002","completion":"0.0000012","web_search":"0.01","input_cache_read":"0.00000002","input_cache_write":"0.00000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}]},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":82.77392113361482,"uptime_last_5m":76.65041641275646,"uptime_last_1d":88.26819248006065,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":2.5e-07},{"name":"OpenAI | openai/gpt-5.6-luna-20260709","model_id":"openai/gpt-5.6-luna","model_name":"OpenAI: GPT-5.6 Luna","context_length":1050000,"pricing":{"prompt":"0.0000002","completion":"0.0000012","web_search":"0.01","input_cache_read":"0.00000002","input_cache_write":"0.00000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.47902872206036,"uptime_last_5m":99.28662622328032,"uptime_last_1d":97.73446586316985,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":2.5e-07},{"name":"OpenAI | openai/gpt-5.6-luna-20260709","model_id":"openai/gpt-5.6-luna","model_name":"OpenAI: GPT-5.6 Luna","context_length":1050000,"pricing":{"prompt":"0.0000001","completion":"0.0000006","web_search":"0.01","input_cache_read":"0.00000001","input_cache_write":"0.000000125","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000002","completion":"0.0000009","input_cache_read":"0.00000002","input_cache_write":"0.00000025"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.47902872206036,"uptime_last_5m":99.28662622328032,"uptime_last_1d":97.73446586316985,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":1.25e-07},{"name":"OpenAI | openai/gpt-5.6-luna-20260709","model_id":"openai/gpt-5.6-luna","model_name":"OpenAI: GPT-5.6 Luna","context_length":1050000,"pricing":{"prompt":"0.0000004","completion":"0.0000024","web_search":"0.01","input_cache_read":"0.00000004","input_cache_write":"0.0000005","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000008","completion":"0.0000036","input_cache_read":"0.00000008","input_cache_write":"0.000001"}]},"provider_name":"OpenAI","tag":"openai/priority","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.47902872206036,"uptime_last_5m":99.28662622328032,"uptime_last_1d":97.73446586316985,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":5e-07},{"name":"Amazon Bedrock | openai/gpt-5.6-luna-20260709","model_id":"openai/gpt-5.6-luna","model_name":"OpenAI: GPT-5.6 Luna","context_length":1050000,"pricing":{"prompt":"0.00000022","completion":"0.00000132","web_search":"0.01","input_cache_read":"0.000000022","input_cache_write":"0.000000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00000044","completion":"0.00000198","input_cache_read":"0.000000044","input_cache_write":"0.00000055"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us-east-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98486568293605,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-08,"_cached_write_per_m":2.75e-07},{"name":"Azure | openai/gpt-5.6-luna-20260709","model_id":"openai/gpt-5.6-luna","model_name":"OpenAI: GPT-5.6 Luna","context_length":1050000,"pricing":{"prompt":"0.00000022","completion":"0.00000132","web_search":"0.01","input_cache_read":"0.000000022","input_cache_write":"0.000000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00000044","completion":"0.00000198","input_cache_read":"0.000000044","input_cache_write":"0.00000055"}]},"provider_name":"Azure","tag":"azure/eu","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99947453325416,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-08,"_cached_write_per_m":2.75e-07},{"name":"Azure | openai/gpt-5.6-luna-20260709","model_id":"openai/gpt-5.6-luna","model_name":"OpenAI: GPT-5.6 Luna","context_length":1050000,"pricing":{"prompt":"0.00000022","completion":"0.00000132","web_search":"0.01","input_cache_read":"0.000000022","input_cache_write":"0.000000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00000044","completion":"0.00000198","input_cache_read":"0.000000044","input_cache_write":"0.00000055"}]},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":86.21587114515812,"uptime_last_5m":76.52173913043478,"uptime_last_1d":71.22496849525459,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-08,"_cached_write_per_m":2.75e-07}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.5e-07,"_priciest_blended_per_m":1e-06,"_provider_spread_multiplier":4.0},{"id":"kwaipilot/kat-coder-pro-v2.5","canonical_slug":"kwaipilot/kat-coder-pro-v2.5-20260710","hugging_face_id":null,"name":"Kwaipilot: KAT-Coder-Pro V2.5","created":1783714589,"description":"KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000074","completion":"0.00000296","input_cache_read":"0.00000015"},"top_provider":{"context_length":256000,"max_completion_tokens":80000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/kwaipilot/kat-coder-pro-v2.5-20260710/endpoints"},"_prompt_per_m":7.4e-07,"_completion_per_m":2.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"AtlasCloud | kwaipilot/kat-coder-pro-v2.5-20260710","model_id":"kwaipilot/kat-coder-pro-v2.5","model_name":"Kwaipilot: KAT-Coder-Pro V2.5","context_length":262144,"pricing":{"prompt":"0.00000074","completion":"0.00000296","input_cache_read":"0.00000015","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.59758551307847,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.4e-07,"_completion_per_m":2.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"StreamLake | kwaipilot/kat-coder-pro-v2.5-20260710","model_id":"kwaipilot/kat-coder-pro-v2.5","model_name":"Kwaipilot: KAT-Coder-Pro V2.5","context_length":256000,"pricing":{"prompt":"0.00000074","completion":"0.00000296","input_cache_read":"0.00000015","discount":0},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":80000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","presence_penalty","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.91780821917808,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.4e-07,"_completion_per_m":2.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"AtlasCloud","_cheapest_blended_per_m":1.406e-06,"_priciest_blended_per_m":1.406e-06,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.6-terra-pro","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Terra Pro","created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-terra-pro-20260709/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06,"_endpoints":[{"name":"Azure | openai/gpt-5.6-terra-pro-20260709","model_id":"openai/gpt-5.6-terra-pro","model_name":"OpenAI: GPT-5.6 Terra Pro","context_length":1050000,"pricing":{"prompt":"0.000002","completion":"0.000012","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"OpenAI | openai/gpt-5.6-terra-pro-20260709","model_id":"openai/gpt-5.6-terra-pro","model_name":"OpenAI: GPT-5.6 Terra Pro","context_length":1050000,"pricing":{"prompt":"0.000002","completion":"0.000012","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.40652818991099,"uptime_last_5m":100,"uptime_last_1d":99.42727818576509,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"OpenAI | openai/gpt-5.6-terra-pro-20260709","model_id":"openai/gpt-5.6-terra-pro","model_name":"OpenAI: GPT-5.6 Terra Pro","context_length":1050000,"pricing":{"prompt":"0.000001","completion":"0.000006","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.000009","input_cache_read":"0.0000002","input_cache_write":"0.0000025"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.40652818991099,"uptime_last_5m":100,"uptime_last_1d":99.42727818576509,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06},{"name":"OpenAI | openai/gpt-5.6-terra-pro-20260709","model_id":"openai/gpt-5.6-terra-pro","model_name":"OpenAI: GPT-5.6 Terra Pro","context_length":1050000,"pricing":{"prompt":"0.000004","completion":"0.000024","web_search":"0.01","input_cache_read":"0.0000004","input_cache_write":"0.000005","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000008","completion":"0.000036","input_cache_read":"0.0000008","input_cache_write":"0.00001"}]},"provider_name":"OpenAI","tag":"openai/priority","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.40652818991099,"uptime_last_5m":100,"uptime_last_1d":99.42727818576509,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-06,"_completion_per_m":2.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":5e-06},{"name":"Azure | openai/gpt-5.6-terra-pro-20260709","model_id":"openai/gpt-5.6-terra-pro","model_name":"OpenAI: GPT-5.6 Terra Pro","context_length":1050000,"pricing":{"prompt":"0.0000022","completion":"0.0000132","web_search":"0.01","input_cache_read":"0.00000022","input_cache_write":"0.00000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000044","completion":"0.0000198","input_cache_read":"0.00000044","input_cache_write":"0.0000055"}]},"provider_name":"Azure","tag":"azure/eu","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":1.32e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":2.75e-06}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.4999999999999998e-06,"_priciest_blended_per_m":9.999999999999999e-06,"_provider_spread_multiplier":4.0},{"id":"openai/gpt-5.6-sol-pro","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Sol Pro","created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06,"_endpoints":[{"name":"OpenAI | openai/gpt-5.6-sol-pro-20260709","model_id":"openai/gpt-5.6-sol-pro","model_name":"OpenAI: GPT-5.6 Sol Pro","context_length":1050000,"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.37010211980784,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"OpenAI | openai/gpt-5.6-sol-pro-20260709","model_id":"openai/gpt-5.6-sol-pro","model_name":"OpenAI: GPT-5.6 Sol Pro","context_length":1050000,"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.0000075","input_cache_read":"0.0000002","input_cache_write":"0.0000025"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.37010211980784,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06},{"name":"OpenAI | openai/gpt-5.6-sol-pro-20260709","model_id":"openai/gpt-5.6-sol-pro","model_name":"OpenAI: GPT-5.6 Sol Pro","context_length":1050000,"pricing":{"prompt":"0.000004","completion":"0.00002","web_search":"0.01","input_cache_read":"0.0000004","input_cache_write":"0.000005","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000008","completion":"0.00003","input_cache_read":"0.0000008","input_cache_write":"0.00001"}]},"provider_name":"OpenAI","tag":"openai/priority","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.37010211980784,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-06,"_completion_per_m":2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":5e-06},{"name":"Azure | openai/gpt-5.6-sol-pro-20260709","model_id":"openai/gpt-5.6-sol-pro","model_name":"OpenAI: GPT-5.6 Sol Pro","context_length":1050000,"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001","input_cache_write":"0.0000125"}]},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.98859749144812,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Azure | openai/gpt-5.6-sol-pro-20260709","model_id":"openai/gpt-5.6-sol-pro","model_name":"OpenAI: GPT-5.6 Sol Pro","context_length":1050000,"pricing":{"prompt":"0.0000055","completion":"0.000033","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000011","completion":"0.0000495","input_cache_read":"0.0000011","input_cache_write":"0.00001375"}]},"provider_name":"Azure","tag":"azure/eu","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":3.3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.2e-06,"_priciest_blended_per_m":1.3749999999999999e-05,"_provider_spread_multiplier":6.249999999999999},{"id":"openai/gpt-5.6-terra","canonical_slug":"openai/gpt-5.6-terra-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Terra","created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-terra-20260709/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":56.6,"coding_index":76.7,"agentic_index":50.2}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06,"_endpoints":[{"name":"OpenAI | openai/gpt-5.6-terra-20260709","model_id":"openai/gpt-5.6-terra","model_name":"OpenAI: GPT-5.6 Terra","context_length":1050000,"pricing":{"prompt":"0.000002","completion":"0.000012","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98671299943192,"uptime_last_5m":99.99372151792768,"uptime_last_1d":99.92797102526792,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"OpenAI | openai/gpt-5.6-terra-20260709","model_id":"openai/gpt-5.6-terra","model_name":"OpenAI: GPT-5.6 Terra","context_length":1050000,"pricing":{"prompt":"0.000001","completion":"0.000006","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.000009","input_cache_read":"0.0000002","input_cache_write":"0.0000025"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98671299943192,"uptime_last_5m":99.99372151792768,"uptime_last_1d":99.92797102526792,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06},{"name":"OpenAI | openai/gpt-5.6-terra-20260709","model_id":"openai/gpt-5.6-terra","model_name":"OpenAI: GPT-5.6 Terra","context_length":1050000,"pricing":{"prompt":"0.000004","completion":"0.000024","web_search":"0.01","input_cache_read":"0.0000004","input_cache_write":"0.000005","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000008","completion":"0.000036","input_cache_read":"0.0000008","input_cache_write":"0.00001"}]},"provider_name":"OpenAI","tag":"openai/priority","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98671299943192,"uptime_last_5m":99.99372151792768,"uptime_last_1d":99.92797102526792,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-06,"_completion_per_m":2.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":5e-06},{"name":"Azure | openai/gpt-5.6-terra-20260709","model_id":"openai/gpt-5.6-terra","model_name":"OpenAI: GPT-5.6 Terra","context_length":1050000,"pricing":{"prompt":"0.000002","completion":"0.000012","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.9545918946532,"uptime_last_5m":99.93769470404985,"uptime_last_1d":97.10426550710184,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"Amazon Bedrock | openai/gpt-5.6-terra-20260709","model_id":"openai/gpt-5.6-terra","model_name":"OpenAI: GPT-5.6 Terra","context_length":1050000,"pricing":{"prompt":"0.0000022","completion":"0.0000132","web_search":"0.01","input_cache_read":"0.00000022","input_cache_write":"0.00000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000044","completion":"0.0000198","input_cache_read":"0.00000044","input_cache_write":"0.0000055"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us-east-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":1.32e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":2.75e-06},{"name":"Azure | openai/gpt-5.6-terra-20260709","model_id":"openai/gpt-5.6-terra","model_name":"OpenAI: GPT-5.6 Terra","context_length":1050000,"pricing":{"prompt":"0.0000022","completion":"0.0000132","web_search":"0.01","input_cache_read":"0.00000022","input_cache_write":"0.00000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000044","completion":"0.0000198","input_cache_read":"0.00000044","input_cache_write":"0.0000055"}]},"provider_name":"Azure","tag":"azure/eu","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":1.32e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":2.75e-06},{"name":"Azure | openai/gpt-5.6-terra-20260709","model_id":"openai/gpt-5.6-terra","model_name":"OpenAI: GPT-5.6 Terra","context_length":1050000,"pricing":{"prompt":"0.0000022","completion":"0.0000132","web_search":"0.01","input_cache_read":"0.00000022","input_cache_write":"0.00000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000044","completion":"0.0000198","input_cache_read":"0.00000044","input_cache_write":"0.0000055"}]},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":91.85305003062012,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":1.32e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":2.75e-06}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.4999999999999998e-06,"_priciest_blended_per_m":9.999999999999999e-06,"_provider_spread_multiplier":4.0},{"id":"x-ai/grok-4.5","canonical_slug":"x-ai/grok-4.5-20260708","hugging_face_id":null,"name":"SpaceXAI: Grok 4.5","created":1783523154,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","web_search":"0.005","input_cache_read":"0.0000003","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.0000006"}]},"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-4.5-20260708/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1238,"win_rate":56.2,"rank":6},{"arena":"agents","category":"androidnative","elo":1266,"win_rate":67.7,"rank":5},{"arena":"agents","category":"fullstack","elo":1270,"win_rate":62.2,"rank":8},{"arena":"agents","category":"godotgamedev","elo":1270,"win_rate":62.2,"rank":3},{"arena":"agents","category":"htmlslides","elo":1218,"win_rate":52.6,"rank":6},{"arena":"agents","category":"mobileapps","elo":1260,"win_rate":55.7,"rank":4},{"arena":"agents","category":"python-pptxslides","elo":1249,"win_rate":53.9,"rank":8},{"arena":"agents","category":"webapps","elo":1245,"win_rate":54,"rank":12},{"arena":"models","category":"3d","elo":1306,"win_rate":50.8,"rank":14},{"arena":"models","category":"asciiart","elo":1293,"win_rate":59,"rank":8},{"arena":"models","category":"codecategories","elo":1305,"win_rate":51.6,"rank":12},{"arena":"models","category":"dataviz","elo":1295,"win_rate":49.9,"rank":15},{"arena":"models","category":"gamedev","elo":1305,"win_rate":49.6,"rank":15},{"arena":"models","category":"svg","elo":1266,"win_rate":52.2,"rank":10},{"arena":"models","category":"uicomponent","elo":1304,"win_rate":52.5,"rank":15},{"arena":"models","category":"website","elo":1305,"win_rate":53.7,"rank":12}],"artificial_analysis":{"intelligence_index":55.8,"coding_index":72.4,"agentic_index":48.9}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"high"},"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"xAI | x-ai/grok-4.5-20260708","model_id":"x-ai/grok-4.5","model_name":"SpaceXAI: Grok 4.5","context_length":500000,"pricing":{"prompt":"0.000002","completion":"0.000006","web_search":"0.005","input_cache_read":"0.0000003","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.0000006"}]},"provider_name":"xAI","tag":"xai/zdr","quantization":"unknown","max_completion_tokens":450000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97296566639632,"uptime_last_5m":100,"uptime_last_1d":99.80529465777217,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.5-20260708","model_id":"x-ai/grok-4.5","model_name":"SpaceXAI: Grok 4.5","context_length":500000,"pricing":{"prompt":"0.000004","completion":"0.000012","web_search":"0.005","input_cache_read":"0.0000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000008","completion":"0.000024","input_cache_read":"0.0000012"}]},"provider_name":"xAI","tag":"xai/zdr/priority","quantization":"unknown","max_completion_tokens":450000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97296566639632,"uptime_last_5m":100,"uptime_last_1d":99.80529465777217,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.5-20260708","model_id":"x-ai/grok-4.5","model_name":"SpaceXAI: Grok 4.5","context_length":500000,"pricing":{"prompt":"0.000002","completion":"0.000006","web_search":"0.005","input_cache_read":"0.0000003","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.0000006"}]},"provider_name":"xAI","tag":"xai","quantization":"unknown","max_completion_tokens":450000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.76244061015254,"uptime_last_5m":99.31305201177625,"uptime_last_1d":99.3273535405401,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.5-20260708","model_id":"x-ai/grok-4.5","model_name":"SpaceXAI: Grok 4.5","context_length":500000,"pricing":{"prompt":"0.000004","completion":"0.000012","web_search":"0.005","input_cache_read":"0.0000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000008","completion":"0.000024","input_cache_read":"0.0000012"}]},"provider_name":"xAI","tag":"xai/priority","quantization":"unknown","max_completion_tokens":450000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.76244061015254,"uptime_last_5m":99.31305201177625,"uptime_last_1d":99.3273535405401,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-06,"_completion_per_m":1.2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-07,"_cached_write_per_m":null}],"_cheapest_provider":"xAI","_cheapest_blended_per_m":3.2e-06,"_priciest_blended_per_m":6.4e-06,"_provider_spread_multiplier":2.0},{"id":"~x-ai/grok-latest","canonical_slug":"~x-ai/grok-latest","alias_target":{"name":"SpaceXAI: Grok 4.6","slug":"x-ai/grok-4.6"},"hugging_face_id":null,"name":"xAI: Grok Latest","created":1783519360,"description":"This model always redirects to the latest Grok model from xAI.","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","web_search":"0.005","input_cache_read":"0.0000005","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.000001"}]},"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~x-ai/grok-latest/endpoints"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":3.2e-06,"_priciest_blended_per_m":3.2e-06,"_provider_spread_multiplier":null},{"id":"openai/gpt-5.6-sol","canonical_slug":"openai/gpt-5.6-sol-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Sol","created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":60.9,"coding_index":77.4,"agentic_index":57.8}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06,"_endpoints":[{"name":"OpenAI | openai/gpt-5.6-sol-20260709","model_id":"openai/gpt-5.6-sol","model_name":"OpenAI: GPT-5.6 Sol","context_length":1050000,"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.91450723740456,"uptime_last_5m":99.93370584335638,"uptime_last_1d":99.3024746088067,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"OpenAI | openai/gpt-5.6-sol-20260709","model_id":"openai/gpt-5.6-sol","model_name":"OpenAI: GPT-5.6 Sol","context_length":1050000,"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.0000075","input_cache_read":"0.0000002","input_cache_write":"0.0000025"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.91450723740456,"uptime_last_5m":99.93370584335638,"uptime_last_1d":99.3024746088067,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06},{"name":"OpenAI | openai/gpt-5.6-sol-20260709","model_id":"openai/gpt-5.6-sol","model_name":"OpenAI: GPT-5.6 Sol","context_length":1050000,"pricing":{"prompt":"0.000004","completion":"0.00002","web_search":"0.01","input_cache_read":"0.0000004","input_cache_write":"0.000005","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000008","completion":"0.00003","input_cache_read":"0.0000008","input_cache_write":"0.00001"}]},"provider_name":"OpenAI","tag":"openai/priority","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.91450723740456,"uptime_last_5m":99.93370584335638,"uptime_last_1d":99.3024746088067,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-06,"_completion_per_m":2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":5e-06},{"name":"Azure | openai/gpt-5.6-sol-20260709","model_id":"openai/gpt-5.6-sol","model_name":"OpenAI: GPT-5.6 Sol","context_length":1050000,"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001","input_cache_write":"0.0000125"}]},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.92913832199547,"uptime_last_5m":100,"uptime_last_1d":99.93431532632887,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Amazon Bedrock | openai/gpt-5.6-sol-20260709","model_id":"openai/gpt-5.6-sol","model_name":"OpenAI: GPT-5.6 Sol","context_length":1050000,"pricing":{"prompt":"0.0000055","completion":"0.000033","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000011","completion":"0.0000495","input_cache_read":"0.0000011","input_cache_write":"0.00001375"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us-east-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":3.3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06},{"name":"Azure | openai/gpt-5.6-sol-20260709","model_id":"openai/gpt-5.6-sol","model_name":"OpenAI: GPT-5.6 Sol","context_length":1050000,"pricing":{"prompt":"0.0000055","completion":"0.000033","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000011","completion":"0.0000495","input_cache_read":"0.0000011","input_cache_write":"0.00001375"}]},"provider_name":"Azure","tag":"azure/eu","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":3.3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06},{"name":"Azure | openai/gpt-5.6-sol-20260709","model_id":"openai/gpt-5.6-sol","model_name":"OpenAI: GPT-5.6 Sol","context_length":1050000,"pricing":{"prompt":"0.0000055","completion":"0.000033","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000011","completion":"0.0000495","input_cache_read":"0.0000011","input_cache_write":"0.00001375"}]},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.45347074871174,"uptime_last_5m":100,"uptime_last_1d":94.81449013221774,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":3.3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.2e-06,"_priciest_blended_per_m":1.3749999999999999e-05,"_provider_spread_multiplier":6.249999999999999},{"id":"aion-labs/aion-3.0-mini","canonical_slug":"aion-labs/aion-3.0-mini-20260707","hugging_face_id":null,"name":"AionLabs: Aion-3.0-Mini","created":1783443096,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000007","completion":"0.0000014","input_cache_read":"0.00000018"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/aion-labs/aion-3.0-mini-20260707/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":7e-07,"_completion_per_m":1.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.8e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"AionLabs | aion-labs/aion-3.0-mini-20260707","model_id":"aion-labs/aion-3.0-mini","model_name":"AionLabs: Aion-3.0-Mini","context_length":131072,"pricing":{"prompt":"0.0000007","completion":"0.0000014","input_cache_read":"0.00000018","discount":0},"provider_name":"AionLabs","tag":"aion-labs","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-07,"_completion_per_m":1.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.8e-07,"_cached_write_per_m":null}],"_cheapest_provider":"AionLabs","_cheapest_blended_per_m":9.1e-07,"_priciest_blended_per_m":9.1e-07,"_provider_spread_multiplier":1.0},{"id":"tencent/hy3","canonical_slug":"tencent/hy3-20260706","hugging_face_id":"tencent/Hy3","name":"Tencent: Hy3","created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000132","completion":"0.000000528","input_cache_read":"0.000000033","overrides":[{"utc_start":0,"utc_end":1600,"prompt":"0.000000132","completion":"0.000000528","input_cache_read":"0.000000033"},{"utc_start":1600,"utc_end":0,"prompt":"0.0000000825","completion":"0.00000033","input_cache_read":"0.000000020625"}]},"top_provider":{"context_length":262144,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy3-20260706/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1220,"win_rate":43.7,"rank":42},{"arena":"models","category":"codecategories","elo":1201,"win_rate":41.1,"rank":53},{"arena":"models","category":"dataviz","elo":1147,"win_rate":36.1,"rank":75},{"arena":"models","category":"gamedev","elo":1173,"win_rate":38.6,"rank":62},{"arena":"models","category":"uicomponent","elo":1189,"win_rate":40.2,"rank":60},{"arena":"models","category":"website","elo":1202,"win_rate":41.3,"rank":58}]},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"_prompt_per_m":1.32e-07,"_completion_per_m":5.28e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | tencent/hy3-20260706","model_id":"tencent/hy3","model_name":"Tencent: Hy3","context_length":262144,"pricing":{"prompt":"0.000000126","completion":"0.000000522","input_cache_read":"0.0000000315","discount":0.1},"provider_name":"GMICloud","tag":"gmicloud/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.4006116207951,"uptime_last_5m":96.7741935483871,"uptime_last_1d":96.79798249971341,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.26e-07,"_completion_per_m":5.22e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.15e-08,"_cached_write_per_m":null},{"name":"Baidu | tencent/hy3-20260706","model_id":"tencent/hy3","model_name":"Tencent: Hy3","context_length":262144,"pricing":{"prompt":"0.000000132","completion":"0.000000528","input_cache_read":"0.000000033","discount":0},"provider_name":"Baidu","tag":"baidu/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9830170735021,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-07,"_completion_per_m":5.28e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-08,"_cached_write_per_m":null},{"name":"Tencent | tencent/hy3-20260706","model_id":"tencent/hy3","model_name":"Tencent: Hy3","context_length":262144,"pricing":{"prompt":"0.000000132","completion":"0.000000528","input_cache_read":"0.000000033","discount":0,"overrides":[{"utc_start":0,"utc_end":1600,"prompt":"0.000000132","completion":"0.000000528","input_cache_read":"0.000000033"},{"utc_start":1600,"utc_end":0,"prompt":"0.0000000825","completion":"0.00000033","input_cache_read":"0.000000020625"}]},"provider_name":"Tencent","tag":"tencent/fp8","quantization":"fp8","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","stop","max_completion_tokens","max_tokens","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":99.83941270933701,"uptime_last_5m":100,"uptime_last_1d":99.71830741385372,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.32e-07,"_completion_per_m":5.28e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-08,"_cached_write_per_m":null},{"name":"DeepInfra | tencent/hy3-20260706","model_id":"tencent/hy3","model_name":"Tencent: Hy3","context_length":262144,"pricing":{"prompt":"0.00000014","completion":"0.00000058","input_cache_read":"0.000000035","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","structured_outputs","tools","tool_choice","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":90.27777777777779,"uptime_last_5m":null,"uptime_last_1d":95.45902509286634,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":5.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-08,"_cached_write_per_m":null},{"name":"Novita | tencent/hy3-20260706","model_id":"tencent/hy3","model_name":"Tencent: Hy3","context_length":262144,"pricing":{"prompt":"0.00000014","completion":"0.00000058","input_cache_read":"0.000000035","discount":0},"provider_name":"Novita","tag":"novita","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.33920704845815,"uptime_last_5m":100,"uptime_last_1d":99.34053220208253,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":5.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-08,"_cached_write_per_m":null},{"name":"Phala | tencent/hy3-20260706","model_id":"tencent/hy3","model_name":"Tencent: Hy3","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.00000064","input_cache_read":"0.00000004","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.01960784313727,"uptime_last_5m":100,"uptime_last_1d":99.4774975616553,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"AtlasCloud | tencent/hy3-20260706","model_id":"tencent/hy3","model_name":"Tencent: Hy3","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.0000008","input_cache_read":"0.00000005","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99416841614183,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":2.4479999999999997e-07,"_priciest_blended_per_m":3.7999999999999996e-07,"_provider_spread_multiplier":1.5522875816993464},{"id":"poolside/laguna-xs-2.1:free","canonical_slug":"poolside/laguna-xs-2.1-20260625","hugging_face_id":"poolside/Laguna-XS-2.1","name":"Poolside: Laguna XS 2.1 (free)","created":1783002429,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Poolside | poolside/laguna-xs-2.1-20260625:free","model_id":"poolside/laguna-xs-2.1:free","model_name":"Poolside: Laguna XS 2.1","context_length":262144,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Poolside","tag":"poolside/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.91527619261012,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Poolside","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"aion-labs/aion-3.0","canonical_slug":"aion-labs/aion-3.0-20260707","hugging_face_id":null,"name":"AionLabs: Aion-3.0","created":1783443095,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000006","input_cache_read":"0.00000075"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/aion-labs/aion-3.0-20260707/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":3e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"AionLabs | aion-labs/aion-3.0-20260707","model_id":"aion-labs/aion-3.0","model_name":"AionLabs: Aion-3.0","context_length":131072,"pricing":{"prompt":"0.000003","completion":"0.000006","input_cache_read":"0.00000075","discount":0},"provider_name":"AionLabs","tag":"aion-labs","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"AionLabs","_cheapest_blended_per_m":3.9e-06,"_priciest_blended_per_m":3.9e-06,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-sonnet-5:batch","canonical_slug":"anthropic/claude-sonnet-5-20260630","hugging_face_id":null,"name":"Anthropic: Claude Sonnet 5 (batch)","created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1225,"win_rate":51.9,"rank":8},{"arena":"agents","category":"androidnative","elo":1249,"win_rate":55.8,"rank":9},{"arena":"agents","category":"fullstack","elo":1269,"win_rate":56.3,"rank":9},{"arena":"agents","category":"godotgamedev","elo":1268,"win_rate":60.4,"rank":4},{"arena":"agents","category":"htmlslides","elo":1233,"win_rate":54,"rank":4},{"arena":"agents","category":"mobileapps","elo":1227,"win_rate":51,"rank":13},{"arena":"agents","category":"python-pptxslides","elo":1249,"win_rate":52.6,"rank":7},{"arena":"agents","category":"webapps","elo":1275,"win_rate":56,"rank":5},{"arena":"models","category":"3d","elo":1301,"win_rate":55.2,"rank":15},{"arena":"models","category":"asciiart","elo":1236,"win_rate":52.8,"rank":17},{"arena":"models","category":"codecategories","elo":1300,"win_rate":54.1,"rank":16},{"arena":"models","category":"dataviz","elo":1261,"win_rate":52.6,"rank":24},{"arena":"models","category":"gamedev","elo":1329,"win_rate":55.1,"rank":9},{"arena":"models","category":"svg","elo":1229,"win_rate":52.5,"rank":20},{"arena":"models","category":"uicomponent","elo":1305,"win_rate":55.1,"rank":14},{"arena":"models","category":"website","elo":1297,"win_rate":54.1,"rank":14}],"artificial_analysis":{"intelligence_index":55.3,"coding_index":71.5,"agentic_index":49.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-sonnet-5-20260630:batch","model_id":"anthropic/claude-sonnet-5:batch","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":2.2e-06,"_priciest_blended_per_m":2.2e-06,"_provider_spread_multiplier":1.0},{"id":"poolside/laguna-xs-2.1","canonical_slug":"poolside/laguna-xs-2.1-20260625","hugging_face_id":"poolside/Laguna-XS-2.1","name":"Poolside: Laguna XS 2.1","created":1783002429,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000006","completion":"0.00000012","input_cache_read":"0.00000003"},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":6e-08,"_completion_per_m":1.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Poolside | poolside/laguna-xs-2.1-20260625","model_id":"poolside/laguna-xs-2.1","model_name":"Poolside: Laguna XS 2.1","context_length":262144,"pricing":{"prompt":"0.00000006","completion":"0.00000012","input_cache_read":"0.00000003","discount":0.4},"provider_name":"Poolside","tag":"poolside/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-08,"_completion_per_m":1.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Poolside","_cheapest_blended_per_m":7.799999999999998e-08,"_priciest_blended_per_m":7.799999999999998e-08,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-sonnet-5","canonical_slug":"anthropic/claude-sonnet-5-20260630","hugging_face_id":null,"name":"Anthropic: Claude Sonnet 5","created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1225,"win_rate":51.9,"rank":8},{"arena":"agents","category":"androidnative","elo":1249,"win_rate":55.8,"rank":9},{"arena":"agents","category":"fullstack","elo":1269,"win_rate":56.3,"rank":9},{"arena":"agents","category":"godotgamedev","elo":1268,"win_rate":60.4,"rank":4},{"arena":"agents","category":"htmlslides","elo":1233,"win_rate":54,"rank":4},{"arena":"agents","category":"mobileapps","elo":1227,"win_rate":51,"rank":13},{"arena":"agents","category":"python-pptxslides","elo":1249,"win_rate":52.6,"rank":7},{"arena":"agents","category":"webapps","elo":1275,"win_rate":56,"rank":5},{"arena":"models","category":"3d","elo":1301,"win_rate":55.2,"rank":15},{"arena":"models","category":"asciiart","elo":1236,"win_rate":52.8,"rank":17},{"arena":"models","category":"codecategories","elo":1300,"win_rate":54.1,"rank":16},{"arena":"models","category":"dataviz","elo":1261,"win_rate":52.6,"rank":24},{"arena":"models","category":"gamedev","elo":1329,"win_rate":55.1,"rank":9},{"arena":"models","category":"svg","elo":1229,"win_rate":52.5,"rank":20},{"arena":"models","category":"uicomponent","elo":1305,"win_rate":55.1,"rank":14},{"arena":"models","category":"website","elo":1297,"win_rate":54.1,"rank":14}],"artificial_analysis":{"intelligence_index":55.3,"coding_index":71.5,"agentic_index":49.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-sonnet-5-20260630","model_id":"anthropic/claude-sonnet-5","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9720635319229,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"Claude Platform on AWS | anthropic/claude-sonnet-5-20260630","model_id":"anthropic/claude-sonnet-5","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","discount":0},"provider_name":"Claude Platform on AWS","tag":"claude-on-aws","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.99079638850284,"uptime_last_5m":99.99488019660046,"uptime_last_1d":99.93780904077512,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"Azure | anthropic/claude-sonnet-5-20260630","model_id":"anthropic/claude-sonnet-5","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","discount":0},"provider_name":"Azure","tag":"azure/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.85652797704448,"uptime_last_5m":null,"uptime_last_1d":99.53210962003189,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"Google | anthropic/claude-sonnet-5-20260630","model_id":"anthropic/claude-sonnet-5","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tools","tool_choice","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9322018909777,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"Azure | anthropic/claude-sonnet-5-20260630","model_id":"anthropic/claude-sonnet-5","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","discount":0},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.976667133324,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"Amazon Bedrock | anthropic/claude-sonnet-5-20260630","model_id":"anthropic/claude-sonnet-5","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.9926756024317,"uptime_last_5m":100,"uptime_last_1d":99.97128041642402,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06},{"name":"Amazon Bedrock | anthropic/claude-sonnet-5-20260630","model_id":"anthropic/claude-sonnet-5","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.0000022","completion":"0.000011","web_search":"0.01","input_cache_read":"0.00000022","input_cache_write":"0.00000275","input_cache_write_1h":"0.0000044","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us-east-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":1.1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":2.75e-06},{"name":"Google | anthropic/claude-sonnet-5-20260630","model_id":"anthropic/claude-sonnet-5","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.0000022","completion":"0.000011","web_search":"0.01","input_cache_read":"0.00000022","input_cache_write":"0.00000275","input_cache_write_1h":"0.0000044","discount":0},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":1.1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":2.75e-06},{"name":"Google | anthropic/claude-sonnet-5-20260630","model_id":"anthropic/claude-sonnet-5","model_name":"Anthropic: Claude Sonnet 5","context_length":1000000,"pricing":{"prompt":"0.0000022","completion":"0.000011","web_search":"0.01","input_cache_read":"0.00000022","input_cache_write":"0.00000275","input_cache_write_1h":"0.0000044","discount":0},"provider_name":"Google","tag":"google-vertex/europe","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.94063324538259,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":1.1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":2.75e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":4.4e-06,"_priciest_blended_per_m":4.839999999999999e-06,"_provider_spread_multiplier":1.0999999999999999},{"id":"sakana/fugu-ultra","canonical_slug":"sakana/fugu-ultra-20260615","hugging_face_id":null,"name":"Sakana: Fugu Ultra","created":1782276303,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/sakana/fugu-ultra-20260615/endpoints"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"xhigh"},"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Sakana AI | sakana/fugu-ultra-20260615","model_id":"sakana/fugu-ultra","model_name":"Sakana: Fugu Ultra","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001"}]},"provider_name":"Sakana AI","tag":"sakana","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","structured_outputs","web_search_options","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Sakana AI","_cheapest_blended_per_m":1.25e-05,"_priciest_blended_per_m":1.25e-05,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3-pro-image","canonical_slug":"google/gemini-3-pro-image-20260528","hugging_face_id":null,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","created":1781754054,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","context_length":131072,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","image_output":"0.00012","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3-pro-image-20260528/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07,"_endpoints":[{"name":"Google | google/gemini-3-pro-image-20260528","model_id":"google/gemini-3-pro-image","model_name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","context_length":65536,"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","image_output":"0.00012","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.89271025809143,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07},{"name":"Google AI Studio | google/gemini-3-pro-image-20260528","model_id":"google/gemini-3-pro-image","model_name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","context_length":131072,"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","image_output":"0.00012","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/global","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.18652226233453,"uptime_last_5m":96.0352422907489,"uptime_last_1d":98.98390505608845,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07}],"_cheapest_provider":"Google","_cheapest_blended_per_m":4.9999999999999996e-06,"_priciest_blended_per_m":4.9999999999999996e-06,"_provider_spread_multiplier":1.0},{"id":"cohere/north-mini-code:free","canonical_slug":"cohere/north-mini-code-20260617","hugging_face_id":"CohereLabs/North-Mini-Code-1.0","name":"Cohere: North Mini Code (free)","created":1781723748,"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":256000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/cohere/north-mini-code-20260617/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":20.2,"coding_index":36.5,"agentic_index":3.1}},"reasoning":{"mandatory":false},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Cohere | cohere/north-mini-code-20260617:free","model_id":"cohere/north-mini-code:free","model_name":"Cohere: North Mini Code","context_length":256000,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Cohere","tag":"cohere","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.7806472439674,"uptime_last_5m":97.92147806004618,"uptime_last_1d":97.65563909521559,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Cohere","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"google/gemini-3.1-flash-image","canonical_slug":"google/gemini-3.1-flash-image-20260528","hugging_face_id":null,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","created":1781754065,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","context_length":131072,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000003","image_output":"0.00006","web_search":"0.014"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-image-20260528/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal"],"default_effort":"minimal"},"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | google/gemini-3.1-flash-image-20260528","model_id":"google/gemini-3.1-flash-image","model_name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","context_length":131072,"pricing":{"prompt":"0.0000005","completion":"0.000003","image_output":"0.00006","web_search":"0.014","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.73591549295774,"uptime_last_5m":99.78947368421053,"uptime_last_1d":99.60793056527187,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google AI Studio | google/gemini-3.1-flash-image-20260528","model_id":"google/gemini-3.1-flash-image","model_name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","context_length":65536,"pricing":{"prompt":"0.0000005","completion":"0.000003","image_output":"0.00006","web_search":"0.014","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":58982,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.87271019257867,"uptime_last_5m":99.52606635071089,"uptime_last_1d":99.65648917247344,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Google","_cheapest_blended_per_m":1.2499999999999999e-06,"_priciest_blended_per_m":1.2499999999999999e-06,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3.1-flash-lite-image","canonical_slug":"google/gemini-3.1-flash-lite-image-20260630","hugging_face_id":null,"name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","created":1782837225,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image_output":"0.00003","web_search":"0.014"},"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-01-01","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-lite-image-20260630/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal"],"default_effort":"minimal"},"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Google AI Studio | google/gemini-3.1-flash-lite-image-20260630","model_id":"google/gemini-3.1-flash-lite-image","model_name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","context_length":65536,"pricing":{"prompt":"0.00000025","completion":"0.0000015","image_output":"0.00003","web_search":"0.014","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":58982,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.87944544906571,"uptime_last_5m":100,"uptime_last_1d":99.73059719769525,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google | google/gemini-3.1-flash-lite-image-20260630","model_id":"google/gemini-3.1-flash-lite-image","model_name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","context_length":65536,"pricing":{"prompt":"0.00000025","completion":"0.0000015","image_output":"0.00003","web_search":"0.014","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":58982,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8073217726397,"uptime_last_5m":100,"uptime_last_1d":99.89592390588359,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":6.249999999999999e-07,"_priciest_blended_per_m":6.249999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"z-ai/glm-5.2:free","canonical_slug":"z-ai/glm-5.2-20260616","hugging_face_id":"zai-org/GLM-5.2","name":"Z.ai: GLM 5.2 (free)","created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":256000,"max_completion_tokens":230400,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.2-20260616/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1207,"win_rate":49.1,"rank":9},{"arena":"agents","category":"androidnative","elo":1200,"win_rate":54.8,"rank":18},{"arena":"agents","category":"fullstack","elo":1262,"win_rate":61.4,"rank":10},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":40.1,"rank":17},{"arena":"agents","category":"htmlslides","elo":1191,"win_rate":49.8,"rank":10},{"arena":"agents","category":"mobileapps","elo":1205,"win_rate":52,"rank":16},{"arena":"agents","category":"python-pptxslides","elo":1218,"win_rate":49.1,"rank":13},{"arena":"agents","category":"webapps","elo":1251,"win_rate":56.5,"rank":11},{"arena":"models","category":"3d","elo":1345,"win_rate":56.9,"rank":7},{"arena":"models","category":"asciiart","elo":1246,"win_rate":52.1,"rank":14},{"arena":"models","category":"codecategories","elo":1329,"win_rate":56.3,"rank":5},{"arena":"models","category":"dataviz","elo":1323,"win_rate":54.5,"rank":7},{"arena":"models","category":"gamedev","elo":1322,"win_rate":54.1,"rank":11},{"arena":"models","category":"svg","elo":1255,"win_rate":54.5,"rank":15},{"arena":"models","category":"uicomponent","elo":1323,"win_rate":57.2,"rank":9},{"arena":"models","category":"website","elo":1323,"win_rate":56.9,"rank":5}],"artificial_analysis":{"intelligence_index":52.6,"coding_index":68.8,"agentic_index":45.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high"],"default_effort":"high"},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Decart | z-ai/glm-5.2-20260616:free","model_id":"z-ai/glm-5.2:free","model_name":"Z.ai: GLM 5.2","context_length":256000,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Decart","tag":"decart/fp4","quantization":"fp4","max_completion_tokens":230400,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.77039251004533,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Decart","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"z-ai/glm-5.2","canonical_slug":"z-ai/glm-5.2-20260616","hugging_face_id":"zai-org/GLM-5.2","name":"Z.ai: GLM 5.2","created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000119","completion":"0.00000374","input_cache_read":"0.000000221"},"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.2-20260616/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1207,"win_rate":49.1,"rank":9},{"arena":"agents","category":"androidnative","elo":1200,"win_rate":54.8,"rank":18},{"arena":"agents","category":"fullstack","elo":1262,"win_rate":61.4,"rank":10},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":40.1,"rank":17},{"arena":"agents","category":"htmlslides","elo":1191,"win_rate":49.8,"rank":10},{"arena":"agents","category":"mobileapps","elo":1205,"win_rate":52,"rank":16},{"arena":"agents","category":"python-pptxslides","elo":1218,"win_rate":49.1,"rank":13},{"arena":"agents","category":"webapps","elo":1251,"win_rate":56.5,"rank":11},{"arena":"models","category":"3d","elo":1345,"win_rate":56.9,"rank":7},{"arena":"models","category":"asciiart","elo":1246,"win_rate":52.1,"rank":14},{"arena":"models","category":"codecategories","elo":1329,"win_rate":56.3,"rank":5},{"arena":"models","category":"dataviz","elo":1323,"win_rate":54.5,"rank":7},{"arena":"models","category":"gamedev","elo":1322,"win_rate":54.1,"rank":11},{"arena":"models","category":"svg","elo":1255,"win_rate":54.5,"rank":15},{"arena":"models","category":"uicomponent","elo":1323,"win_rate":57.2,"rank":9},{"arena":"models","category":"website","elo":1323,"win_rate":56.9,"rank":5}],"artificial_analysis":{"intelligence_index":52.6,"coding_index":68.8,"agentic_index":45.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high"],"default_effort":"high"},"_prompt_per_m":1.19e-06,"_completion_per_m":3.74e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.21e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000004875","completion":"0.00000156","input_cache_read":"0.000000091","discount":0.35},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":163840,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.43181818181817,"uptime_last_5m":99.82998979938796,"uptime_last_1d":99.51573141524227,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.875e-07,"_completion_per_m":1.56e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9.1e-08,"_cached_write_per_m":null},{"name":"Sail Research | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000005","completion":"0.00000315","input_cache_read":"0.000000115","discount":0},"provider_name":"Sail Research","tag":"sail-research/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","tools","temperature","top_p","top_k","frequency_penalty","presence_penalty","stop","seed","max_tokens","logprobs","top_logprobs","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.95588883987648,"uptime_last_5m":100,"uptime_last_1d":99.9546012993775,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":3.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.15e-07,"_cached_write_per_m":null},{"name":"Ambient | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":202752,"pricing":{"prompt":"0.0000006","completion":"0.000002","input_cache_read":"0.00000015","discount":0},"provider_name":"Ambient","tag":"ambient/fp8","quantization":"fp8","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","top_p","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.63099630996311,"uptime_last_5m":100,"uptime_last_1d":97.79639325189063,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"Decart | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.000000684","completion":"0.00000228","input_cache_read":"0.000000114","discount":0.43},"provider_name":"Decart","tag":"decart/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.83766233766234,"uptime_last_5m":100,"uptime_last_1d":98.78802378437676,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.84e-07,"_completion_per_m":2.28e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.14e-07,"_cached_write_per_m":null},{"name":"Makora | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":980000,"pricing":{"prompt":"0.00000072","completion":"0.00000238","input_cache_read":"0.00000012","discount":0},"provider_name":"Makora","tag":"makora/fp4","quantization":"fp4","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":97.8790259230165,"uptime_last_5m":100,"uptime_last_1d":97.98947071950084,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.2e-07,"_completion_per_m":2.38e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null},{"name":"StreamLake | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1024000,"pricing":{"prompt":"0.000000735","completion":"0.00000231","input_cache_read":"0.0000001365","discount":0.475},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tool_choice","tools","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.90302769098157,"uptime_last_5m":99.89356040447046,"uptime_last_1d":99.86495887383884,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.35e-07,"_completion_per_m":2.31e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.365e-07,"_cached_write_per_m":null},{"name":"Novita | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.000000742","completion":"0.000002332","input_cache_read":"0.0000001378","discount":0.47},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.30784442979565,"uptime_last_5m":100,"uptime_last_1d":99.78508211615711,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.42e-07,"_completion_per_m":2.332e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.378e-07,"_cached_write_per_m":null},{"name":"Inceptron | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000075","completion":"0.0000024","input_cache_read":"0.00000017","discount":0},"provider_name":"Inceptron","tag":"inceptron/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed","response_format","logprobs","top_logprobs","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":86.48383937316356,"uptime_last_5m":100,"uptime_last_1d":99.19687908356464,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.7e-07,"_cached_write_per_m":null},{"name":"CoreWeave | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000076","completion":"0.00000242","input_cache_read":"0.00000014","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","tools","tool_choice","logprobs","top_logprobs","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.52361646057166,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.6e-07,"_completion_per_m":2.42e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"AkashML | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000077","completion":"0.00000242","input_cache_read":"0.000000143","discount":0.45},"provider_name":"AkashML","tag":"akashml/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","max_tokens","tools","logprobs","top_logprobs","response_format","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":99.64788732394366,"uptime_last_5m":100,"uptime_last_1d":98.71020619446122,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.7e-07,"_completion_per_m":2.42e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.43e-07,"_cached_write_per_m":null},{"name":"Morph | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000008415","completion":"0.0000031365","input_cache_read":"0.0000001683","discount":0},"provider_name":"Morph","tag":"morph/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":97.33096085409252,"uptime_last_5m":98.73417721518987,"uptime_last_1d":98.53287403038338,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.415e-07,"_completion_per_m":3.1365e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.683e-07,"_cached_write_per_m":null},{"name":"Makora | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000094","completion":"0.0000028","input_cache_read":"0.00000018","discount":0},"provider_name":"Makora","tag":"makora/fp8","quantization":"fp8","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","tools","logit_bias","min_p","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.86910994764398,"uptime_last_5m":100,"uptime_last_1d":98.44615132367223,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.4e-07,"_completion_per_m":2.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.8e-07,"_cached_write_per_m":null},{"name":"Alibaba | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.000000966","completion":"0.000003036","input_cache_read":"0.0000001932","discount":0},"provider_name":"Alibaba","tag":"alibaba/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":1048576,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.9515503875969,"uptime_last_5m":100,"uptime_last_1d":99.96457167150854,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.66e-07,"_completion_per_m":3.036e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.932e-07,"_cached_write_per_m":null},{"name":"GMICloud | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000105","completion":"0.0000033","input_cache_read":"0.000000195","discount":0.25},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.80323968152284,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.05e-06,"_completion_per_m":3.3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.95e-07,"_cached_write_per_m":null},{"name":"Reka | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":262144,"pricing":{"prompt":"0.0000011","completion":"0.00000375","input_cache_read":"0.0000002","discount":0},"provider_name":"Reka","tag":"reka/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":98.89964386813989,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-06,"_completion_per_m":3.75e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000119","completion":"0.00000374","input_cache_read":"0.000000221","discount":0.15},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.96380745566414,"uptime_last_5m":100,"uptime_last_1d":99.99341880116881,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.19e-06,"_completion_per_m":3.74e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.21e-07,"_cached_write_per_m":null},{"name":"Phala | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000126","completion":"0.000003","input_cache_read":"0.00000022","discount":0},"provider_name":"Phala","tag":"phala/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.82238010657194,"uptime_last_5m":100,"uptime_last_1d":99.84892930478146,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.26e-06,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":null},{"name":"AtlasCloud | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000126","completion":"0.00000396","input_cache_read":"0.000000234","discount":0.1},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.99043245311901,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.26e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.34e-07,"_cached_write_per_m":null},{"name":"Baidu | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Baidu","tag":"baidu/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96455622206282,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"BaseTen | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000014","discount":0},"provider_name":"BaseTen","tag":"baseten/fp8","quantization":"fp8","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":95.18436228374566,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"Mistral | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000014","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98835177635411,"uptime_last_5m":100,"uptime_last_1d":99.43149422268472,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"Mistral | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000014","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.32383456124977,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"Fireworks | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000014","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.87363100252739,"uptime_last_5m":100,"uptime_last_1d":99.66648857804329,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"Cloudflare | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":262144,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","tools","structured_outputs","response_format","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96304508499631,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":262144,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000021","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","tool_choice","tools","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8540944738282,"uptime_last_5m":99.9680817108203,"uptime_last_1d":99.44479275356086,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.1e-07,"_cached_write_per_m":null},{"name":"Z.AI | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.68433294567204,"uptime_last_5m":99.63669391462307,"uptime_last_1d":99.81427943226579,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Parasail | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":262144,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Parasail","tag":"parasail/fp4","quantization":"fp4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":99.90141307919816,"uptime_last_5m":100,"uptime_last_1d":99.87995530643717,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Together | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":512000,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":460800,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":98.21698675344915,"uptime_last_5m":98.57600569597722,"uptime_last_1d":97.77664885918941,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Crusoe | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Crusoe","tag":"crusoe/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.29335457441967,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Venice | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1000000,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.89701338825952,"uptime_last_5m":100,"uptime_last_1d":99.23507102911873,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Friendli | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Friendli","tag":"friendli","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":99.75062344139651,"uptime_last_5m":99.69834087481146,"uptime_last_1d":99.76566936664973,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Mistral | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000154","completion":"0.00000484","input_cache_read":"0.000000154","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.54e-06,"_completion_per_m":4.84e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.54e-07,"_cached_write_per_m":null},{"name":"BaseTen | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000021","completion":"0.0000066","input_cache_read":"0.00000021","discount":0},"provider_name":"BaseTen","tag":"baseten/fast","quantization":"fp8","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":89.1377723227984,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-06,"_completion_per_m":6.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.1e-07,"_cached_write_per_m":null},{"name":"Cloudflare | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":262144,"pricing":{"prompt":"0.0000021","completion":"0.0000066","input_cache_read":"0.00000021","discount":0},"provider_name":"Cloudflare","tag":"cloudflare/fast","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99434900542495,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-06,"_completion_per_m":6.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.1e-07,"_cached_write_per_m":null},{"name":"Fireworks | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000021","completion":"0.0000066","input_cache_read":"0.00000021","discount":0},"provider_name":"Fireworks","tag":"fireworks/fast-us","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.86541049798116,"uptime_last_5m":100,"uptime_last_1d":99.20942829953884,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-06,"_completion_per_m":6.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.1e-07,"_cached_write_per_m":null},{"name":"Fireworks | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.0000021","completion":"0.0000066","input_cache_read":"0.00000021","discount":0},"provider_name":"Fireworks","tag":"fireworks/fast","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":98.96585957751917,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-06,"_completion_per_m":6.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.1e-07,"_cached_write_per_m":null},{"name":"Alibaba | z-ai/glm-5.2-20260616","model_id":"z-ai/glm-5.2","model_name":"Z.ai: GLM 5.2","context_length":1048576,"pricing":{"prompt":"0.00000231","completion":"0.00000726","input_cache_read":"0.000000462","discount":0},"provider_name":"Alibaba","tag":"alibaba/fast","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":1048576,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.98343731021919,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.31e-06,"_completion_per_m":7.26e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.62e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":8.092499999999999e-07,"_priciest_blended_per_m":3.7949999999999997e-06,"_provider_spread_multiplier":4.68952734012975},{"id":"openrouter/fusion","canonical_slug":"openrouter/fusion","hugging_face_id":null,"name":"OpenRouter: Fusion","created":1781371647,"description":"Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openrouter/fusion/endpoints"},"_prompt_per_m":-1.0,"_completion_per_m":-1.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":-1.0,"_priciest_blended_per_m":-1.0,"_provider_spread_multiplier":null},{"id":"moonshotai/kimi-k2.7-code","canonical_slug":"moonshotai/kimi-k2.7-code-20260612","hugging_face_id":"moonshotai/Kimi-K2.7-Code","name":"MoonshotAI: Kimi K2.7 Code","created":1781266361,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000066","completion":"0.0000034","input_cache_read":"0.00000018"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2.7-code-20260612/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1131,"win_rate":43.2,"rank":21},{"arena":"agents","category":"androidnative","elo":1157,"win_rate":46.1,"rank":25},{"arena":"agents","category":"fullstack","elo":1198,"win_rate":52.4,"rank":20},{"arena":"agents","category":"godotgamedev","elo":1183,"win_rate":49.3,"rank":12},{"arena":"agents","category":"htmlslides","elo":1216,"win_rate":53.9,"rank":7},{"arena":"agents","category":"mobileapps","elo":1192,"win_rate":49.4,"rank":23},{"arena":"agents","category":"python-pptxslides","elo":1168,"win_rate":44.4,"rank":17},{"arena":"agents","category":"webapps","elo":1205,"win_rate":47.6,"rank":22},{"arena":"models","category":"3d","elo":1286,"win_rate":52.1,"rank":23},{"arena":"models","category":"asciiart","elo":1240,"win_rate":52.3,"rank":16},{"arena":"models","category":"codecategories","elo":1282,"win_rate":52,"rank":25},{"arena":"models","category":"dataviz","elo":1242,"win_rate":49.9,"rank":36},{"arena":"models","category":"gamedev","elo":1252,"win_rate":49.6,"rank":32},{"arena":"models","category":"svg","elo":1219,"win_rate":48.3,"rank":26},{"arena":"models","category":"uicomponent","elo":1291,"win_rate":53.3,"rank":22},{"arena":"models","category":"website","elo":1290,"win_rate":53.5,"rank":19}],"artificial_analysis":{"intelligence_index":43,"coding_index":60.8,"agentic_index":30.3}},"reasoning":{"mandatory":true,"default_enabled":true},"_prompt_per_m":6.6e-07,"_completion_per_m":3.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.8e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Inceptron | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000066","completion":"0.0000034","input_cache_read":"0.00000018","discount":0},"provider_name":"Inceptron","tag":"inceptron/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.76149602274961,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.6e-07,"_completion_per_m":3.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.8e-07,"_cached_write_per_m":null},{"name":"DeepInfra | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000068","completion":"0.0000034","input_cache_read":"0.000000136","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.78596908442331,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.8e-07,"_completion_per_m":3.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.36e-07,"_cached_write_per_m":null},{"name":"Ambient | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000069","completion":"0.00000349","input_cache_read":"0.00000014","discount":0},"provider_name":"Ambient","tag":"ambient","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","frequency_penalty","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.17355371900827,"uptime_last_5m":97.82608695652173,"uptime_last_1d":97.87720635665279,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.9e-07,"_completion_per_m":3.49e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"CoreWeave | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000071","completion":"0.0000035","input_cache_read":"0.00000015","discount":0},"provider_name":"CoreWeave","tag":"coreweave/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.75247524752476,"uptime_last_5m":99.625468164794,"uptime_last_1d":99.79705218295746,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.1e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"Venice | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":256000,"pricing":{"prompt":"0.00000075","completion":"0.0000035","input_cache_read":"0.00000016","discount":0},"provider_name":"Venice","tag":"venice/int4","quantization":"int4","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","response_format","structured_outputs","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":100,"uptime_last_1d":97.04521181915273,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"Parasail | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000076","completion":"0.0000035","input_cache_read":"0.00000016","discount":0},"provider_name":"Parasail","tag":"parasail/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":89.44429310814492,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.6e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"ModelRun | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000085","completion":"0.00000375","input_cache_read":"0.00000016","discount":0},"provider_name":"ModelRun","tag":"modelrun/fp4","quantization":"fp4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","presence_penalty","repetition_penalty","frequency_penalty","top_p","top_k","stop","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.73958333333334,"uptime_last_5m":100,"uptime_last_1d":99.47446703024293,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.5e-07,"_completion_per_m":3.75e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000085916","completion":"0.0000038","input_cache_read":"0.00000017993","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.84270958947204,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.5916e-07,"_completion_per_m":3.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.7993e-07,"_cached_write_per_m":null},{"name":"Novita | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.000000912","completion":"0.00000384","input_cache_read":"0.0000001824","discount":0.04},"provider_name":"Novita","tag":"novita/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.14893617021276,"uptime_last_5m":null,"uptime_last_1d":99.91395718718222,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.12e-07,"_completion_per_m":3.84e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.824e-07,"_cached_write_per_m":null},{"name":"GMICloud | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000019","discount":0},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":85.2670349907919,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.9e-07,"_cached_write_per_m":null},{"name":"Cloudflare | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000019","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.91575400168492,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.9e-07,"_cached_write_per_m":null},{"name":"Moonshot AI | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000019","discount":0},"provider_name":"Moonshot AI","tag":"moonshotai/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","frequency_penalty","presence_penalty","structured_outputs","response_format","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.92648444863336,"uptime_last_5m":93.79310344827586,"uptime_last_1d":99.78166683723944,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.9e-07,"_cached_write_per_m":null},{"name":"Together | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000019","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":92.60975071696448,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.9e-07,"_cached_write_per_m":null},{"name":"Alibaba | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000019","discount":0},"provider_name":"Alibaba","tag":"alibaba/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":229376,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","structured_outputs","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.9e-07,"_cached_write_per_m":null},{"name":"Fireworks | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.0000019","completion":"0.000008","input_cache_read":"0.00000038","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":97.37201365187713,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.9e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.8e-07,"_cached_write_per_m":null},{"name":"Moonshot AI | moonshotai/kimi-k2.7-code-20260612","model_id":"moonshotai/kimi-k2.7-code","model_name":"MoonshotAI: Kimi K2.7 Code","context_length":262144,"pricing":{"prompt":"0.0000019","completion":"0.000008","input_cache_read":"0.00000038","discount":0},"provider_name":"Moonshot AI","tag":"moonshotai/highspeed","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","frequency_penalty","presence_penalty","tools","response_format","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.40476190476191,"uptime_last_5m":100,"uptime_last_1d":99.88963995033798,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.9e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.8e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Inceptron","_cheapest_blended_per_m":1.482e-06,"_priciest_blended_per_m":3.73e-06,"_provider_spread_multiplier":2.5168690958164643},{"id":"~anthropic/claude-fable-latest","canonical_slug":"~anthropic/claude-fable-latest","alias_target":{"name":"Anthropic: Claude Fable 5","slug":"anthropic/claude-fable-5"},"hugging_face_id":null,"name":"Anthropic: Claude Fable Latest","created":1781029944,"description":"This model always redirects to the latest model in the Claude Fable family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~anthropic/claude-fable-latest/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":2.2e-05,"_priciest_blended_per_m":2.2e-05,"_provider_spread_multiplier":null},{"id":"nex-agi/nex-n2-pro","canonical_slug":"nex-agi/nex-n2-pro","hugging_face_id":"nex-agi/Nex-N2-Pro","name":"Nex AGI: Nex-N2-Pro","created":1780937140,"description":"Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000001","input_cache_read":"0.000000025"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.7,"top_p":0.95,"top_k":40,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nex-agi/nex-n2-pro/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1295,"win_rate":53.6,"rank":19},{"arena":"models","category":"asciiart","elo":1129,"win_rate":38.2,"rank":52},{"arena":"models","category":"codecategories","elo":1256,"win_rate":48.3,"rank":36},{"arena":"models","category":"dataviz","elo":1248,"win_rate":48.9,"rank":33},{"arena":"models","category":"gamedev","elo":1258,"win_rate":49.1,"rank":30},{"arena":"models","category":"svg","elo":1240,"win_rate":51.4,"rank":17},{"arena":"models","category":"uicomponent","elo":1245,"win_rate":47.2,"rank":38},{"arena":"models","category":"website","elo":1240,"win_rate":46,"rank":41}],"artificial_analysis":{"intelligence_index":41.7,"coding_index":59.1,"agentic_index":31.2}},"reasoning":{"mandatory":false},"_prompt_per_m":2.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Nex AGI | nex-agi/nex-n2-pro","model_id":"nex-agi/nex-n2-pro","model_name":"Nex AGI: Nex-N2-Pro","context_length":262144,"pricing":{"prompt":"0.00000025","completion":"0.000001","input_cache_read":"0.000000025","discount":0},"provider_name":"Nex AGI","tag":"nex-agi/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","top_p","top_k","temperature","max_tokens","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.68503937007874,"uptime_last_5m":null,"uptime_last_1d":99.50865699578848,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | nex-agi/nex-n2-pro","model_id":"nex-agi/nex-n2-pro","model_name":"Nex AGI: Nex-N2-Pro","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.0000025","input_cache_read":"0.00000025","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow","quantization":"unknown","max_completion_tokens":256000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.00990099009901,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Nex AGI","_cheapest_blended_per_m":4.75e-07,"_priciest_blended_per_m":1.1e-06,"_provider_spread_multiplier":2.3157894736842106},{"id":"nvidia/nemotron-3.5-content-safety:free","canonical_slug":"nvidia/nemotron-3.5-content-safety-20260604","hugging_face_id":"nvidia/Nemotron-3.5-Content-Safety","name":"NVIDIA: Nemotron 3.5 Content Safety (free)","created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-content-safety-20260604/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Nvidia | nvidia/nemotron-3.5-content-safety-20260604:free","model_id":"nvidia/nemotron-3.5-content-safety:free","model_name":"NVIDIA: Nemotron 3.5 Content Safety","context_length":128000,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Nvidia","tag":"nvidia","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.52555137170522,"uptime_last_5m":97.01492537313433,"uptime_last_1d":97.54335394486029,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Nvidia","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"nex-agi/nex-n2-mini","canonical_slug":"nex-agi/nex-n2-mini","hugging_face_id":"nex-agi/Nex-N2-Mini","name":"Nex AGI: Nex-N2-Mini","created":1782312964,"description":"Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.000000025","completion":"0.0000001","input_cache_read":"0.0000000025"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.7,"top_p":0.95,"top_k":40,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nex-agi/nex-n2-mini/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":2.5e-08,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-09,"_cached_write_per_m":null,"_endpoints":[{"name":"Nex AGI | nex-agi/nex-n2-mini","model_id":"nex-agi/nex-n2-mini","model_name":"Nex AGI: Nex-N2-Mini","context_length":262144,"pricing":{"prompt":"0.000000025","completion":"0.0000001","input_cache_read":"0.0000000025","discount":0},"provider_name":"Nex AGI","tag":"nex-agi","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","top_p","top_k","temperature","max_tokens","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98334166250208,"uptime_last_5m":100,"uptime_last_1d":99.99493590300084,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-08,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-09,"_cached_write_per_m":null}],"_cheapest_provider":"Nex AGI","_cheapest_blended_per_m":4.7499999999999995e-08,"_priciest_blended_per_m":4.7499999999999995e-08,"_provider_spread_multiplier":1.0},{"id":"nvidia/nemotron-3-ultra-550b-a55b","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA: Nemotron 3 Ultra","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000022","input_cache_read":"0.0000001"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1177,"win_rate":41.2,"rank":57},{"arena":"models","category":"asciiart","elo":1097,"win_rate":36.2,"rank":55},{"arena":"models","category":"codecategories","elo":1159,"win_rate":36.3,"rank":75},{"arena":"models","category":"dataviz","elo":1158,"win_rate":38.2,"rank":69},{"arena":"models","category":"gamedev","elo":1160,"win_rate":37,"rank":68},{"arena":"models","category":"svg","elo":1119,"win_rate":36.7,"rank":54},{"arena":"models","category":"uicomponent","elo":1162,"win_rate":37.5,"rank":69},{"arena":"models","category":"website","elo":1146,"win_rate":34.2,"rank":80}],"artificial_analysis":{"intelligence_index":38.3,"coding_index":49.3,"agentic_index":27.5}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["high","medium"],"default_effort":"high"},"_prompt_per_m":5e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | nvidia/nemotron-3-ultra-550b-a55b-20260604","model_id":"nvidia/nemotron-3-ultra-550b-a55b","model_name":"NVIDIA: Nemotron 3 Ultra","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.0000022","input_cache_read":"0.0000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.93263725159987,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"BaseTen | nvidia/nemotron-3-ultra-550b-a55b-20260604","model_id":"nvidia/nemotron-3-ultra-550b-a55b","model_name":"NVIDIA: Nemotron 3 Ultra","context_length":202800,"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.00000012","discount":0},"provider_name":"BaseTen","tag":"baseten/fp4","quantization":"fp4","max_completion_tokens":182520,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.30984712961457,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null},{"name":"Venice | nvidia/nemotron-3-ultra-550b-a55b-20260604","model_id":"nvidia/nemotron-3-ultra-550b-a55b","model_name":"NVIDIA: Nemotron 3 Ultra","context_length":256000,"pricing":{"prompt":"0.000000625","completion":"0.000003125","input_cache_read":"0.0000001875","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.72527472527473,"uptime_last_5m":100,"uptime_last_1d":93.27939740549589,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.25e-07,"_completion_per_m":3.125e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.875e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.01e-06,"_priciest_blended_per_m":1.375e-06,"_provider_spread_multiplier":1.3613861386138613},{"id":"nvidia/nemotron-3-ultra-550b-a55b:batch","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA: Nemotron 3 Ultra (batch)","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","context_length":512288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000036","input_cache_read":"0.0000002"},"top_provider":{"context_length":512288,"max_completion_tokens":461059,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1177,"win_rate":41.2,"rank":57},{"arena":"models","category":"asciiart","elo":1097,"win_rate":36.2,"rank":55},{"arena":"models","category":"codecategories","elo":1159,"win_rate":36.3,"rank":75},{"arena":"models","category":"dataviz","elo":1158,"win_rate":38.2,"rank":69},{"arena":"models","category":"gamedev","elo":1160,"win_rate":37,"rank":68},{"arena":"models","category":"svg","elo":1119,"win_rate":36.7,"rank":54},{"arena":"models","category":"uicomponent","elo":1162,"win_rate":37.5,"rank":69},{"arena":"models","category":"website","elo":1146,"win_rate":34.2,"rank":80}],"artificial_analysis":{"intelligence_index":38.3,"coding_index":49.3,"agentic_index":27.5}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["high","medium"],"default_effort":"high"},"_prompt_per_m":6e-07,"_completion_per_m":3.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Together | nvidia/nemotron-3-ultra-550b-a55b-20260604:batch","model_id":"nvidia/nemotron-3-ultra-550b-a55b:batch","model_name":"NVIDIA: Nemotron 3 Ultra","context_length":512288,"pricing":{"prompt":"0.0000006","completion":"0.0000036","input_cache_read":"0.0000002","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":461059,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tool_choice","tools","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":3.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Together","_cheapest_blended_per_m":1.4999999999999998e-06,"_priciest_blended_per_m":1.4999999999999998e-06,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-fable-5","canonical_slug":"anthropic/claude-5-fable-20260609","hugging_face_id":null,"name":"Anthropic: Claude Fable 5","created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-5-fable-20260609/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1281,"win_rate":61.3,"rank":1},{"arena":"agents","category":"agentichtmlslides","elo":1254,"win_rate":59.4,"rank":1},{"arena":"agents","category":"agenticslides(html)","elo":1252,"win_rate":59.5,"rank":1},{"arena":"agents","category":"androidnative","elo":1304,"win_rate":65.4,"rank":2},{"arena":"agents","category":"fullstack","elo":1290,"win_rate":61.3,"rank":5},{"arena":"agents","category":"godotgamedev","elo":1344,"win_rate":70.2,"rank":1},{"arena":"agents","category":"htmlslides","elo":1271,"win_rate":60.5,"rank":1},{"arena":"agents","category":"mobileapps","elo":1249,"win_rate":55.7,"rank":8},{"arena":"agents","category":"python-pptxslides","elo":1314,"win_rate":62.2,"rank":2},{"arena":"agents","category":"webapps","elo":1289,"win_rate":59.1,"rank":3},{"arena":"models","category":"3d","elo":1363,"win_rate":62.5,"rank":4},{"arena":"models","category":"asciiart","elo":1370,"win_rate":70.9,"rank":2},{"arena":"models","category":"codecategories","elo":1337,"win_rate":59,"rank":4},{"arena":"models","category":"dataviz","elo":1332,"win_rate":58.3,"rank":6},{"arena":"models","category":"gamedev","elo":1383,"win_rate":63.5,"rank":2},{"arena":"models","category":"svg","elo":1340,"win_rate":64.6,"rank":3},{"arena":"models","category":"uicomponent","elo":1342,"win_rate":58.5,"rank":5},{"arena":"models","category":"website","elo":1319,"win_rate":57.7,"rank":8}],"artificial_analysis":{"intelligence_index":62.1,"coding_index":76.5,"agentic_index":56.6}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05,"_endpoints":[{"name":"Amazon Bedrock | anthropic/claude-5-fable-20260609","model_id":"anthropic/claude-fable-5","model_name":"Anthropic: Claude Fable 5","context_length":1000000,"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05},{"name":"Azure | anthropic/claude-5-fable-20260609","model_id":"anthropic/claude-fable-5","model_name":"Anthropic: Claude Fable 5","context_length":1000000,"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":98.23062843197071,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05},{"name":"Claude Platform on AWS | anthropic/claude-5-fable-20260609","model_id":"anthropic/claude-fable-5","model_name":"Anthropic: Claude Fable 5","context_length":1000000,"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","discount":0},"provider_name":"Claude Platform on AWS","tag":"claude-on-aws","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.94654312188167,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05},{"name":"Google | anthropic/claude-5-fable-20260609","model_id":"anthropic/claude-fable-5","model_name":"Anthropic: Claude Fable 5","context_length":1000000,"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.9626796044038,"uptime_last_5m":99.88151658767772,"uptime_last_1d":99.98566176094059,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05},{"name":"Anthropic | anthropic/claude-5-fable-20260609","model_id":"anthropic/claude-fable-5","model_name":"Anthropic: Claude Fable 5","context_length":1000000,"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.69884776536313,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05},{"name":"Google | anthropic/claude-5-fable-20260609","model_id":"anthropic/claude-fable-5","model_name":"Anthropic: Claude Fable 5","context_length":1000000,"pricing":{"prompt":"0.000011","completion":"0.000055","web_search":"0.01","input_cache_read":"0.0000011","input_cache_write":"0.00001375","input_cache_write_1h":"0.000022","discount":0},"provider_name":"Google","tag":"google-vertex/europe","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-05,"_completion_per_m":5.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-06,"_cached_write_per_m":1.375e-05}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":2.2e-05,"_priciest_blended_per_m":2.42e-05,"_provider_spread_multiplier":1.0999999999999999},{"id":"anthropic/claude-fable-5:batch","canonical_slug":"anthropic/claude-5-fable-20260609","hugging_face_id":null,"name":"Anthropic: Claude Fable 5 (batch)","created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-5-fable-20260609/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1281,"win_rate":61.3,"rank":1},{"arena":"agents","category":"agentichtmlslides","elo":1254,"win_rate":59.4,"rank":1},{"arena":"agents","category":"agenticslides(html)","elo":1252,"win_rate":59.5,"rank":1},{"arena":"agents","category":"androidnative","elo":1304,"win_rate":65.4,"rank":2},{"arena":"agents","category":"fullstack","elo":1290,"win_rate":61.3,"rank":5},{"arena":"agents","category":"godotgamedev","elo":1344,"win_rate":70.2,"rank":1},{"arena":"agents","category":"htmlslides","elo":1271,"win_rate":60.5,"rank":1},{"arena":"agents","category":"mobileapps","elo":1249,"win_rate":55.7,"rank":8},{"arena":"agents","category":"python-pptxslides","elo":1314,"win_rate":62.2,"rank":2},{"arena":"agents","category":"webapps","elo":1289,"win_rate":59.1,"rank":3},{"arena":"models","category":"3d","elo":1363,"win_rate":62.5,"rank":4},{"arena":"models","category":"asciiart","elo":1370,"win_rate":70.9,"rank":2},{"arena":"models","category":"codecategories","elo":1337,"win_rate":59,"rank":4},{"arena":"models","category":"dataviz","elo":1332,"win_rate":58.3,"rank":6},{"arena":"models","category":"gamedev","elo":1383,"win_rate":63.5,"rank":2},{"arena":"models","category":"svg","elo":1340,"win_rate":64.6,"rank":3},{"arena":"models","category":"uicomponent","elo":1342,"win_rate":58.5,"rank":5},{"arena":"models","category":"website","elo":1319,"win_rate":57.7,"rank":8}],"artificial_analysis":{"intelligence_index":62.1,"coding_index":76.5,"agentic_index":56.6}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-5-fable-20260609:batch","model_id":"anthropic/claude-fable-5:batch","model_name":"Anthropic: Claude Fable 5","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":1.1e-05,"_priciest_blended_per_m":1.1e-05,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.7-plus","canonical_slug":"qwen/qwen3.7-plus-20260602","hugging_face_id":null,"name":"Qwen: Qwen3.7 Plus","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000032","completion":"0.00000128","input_cache_read":"0.000000064","input_cache_write":"0.0000004","overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000096","completion":"0.00000384","input_cache_read":"0.000000192","input_cache_write":"0.0000012"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1283,"win_rate":49.5,"rank":24},{"arena":"models","category":"asciiart","elo":1178,"win_rate":44.9,"rank":32},{"arena":"models","category":"codecategories","elo":1288,"win_rate":50.7,"rank":21},{"arena":"models","category":"dataviz","elo":1289,"win_rate":53.3,"rank":16},{"arena":"models","category":"gamedev","elo":1294,"win_rate":51.1,"rank":21},{"arena":"models","category":"svg","elo":1259,"win_rate":53.1,"rank":13},{"arena":"models","category":"uicomponent","elo":1274,"win_rate":49.1,"rank":28},{"arena":"models","category":"website","elo":1289,"win_rate":51.5,"rank":20}],"artificial_analysis":{"intelligence_index":39.4,"coding_index":55.9,"agentic_index":20.7}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":3.2e-07,"_completion_per_m":1.28e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6.4e-08,"_cached_write_per_m":4e-07,"_endpoints":[{"name":"Alibaba | qwen/qwen3.7-plus-20260602","model_id":"qwen/qwen3.7-plus","model_name":"Qwen: Qwen3.7 Plus","context_length":1000000,"pricing":{"prompt":"0.00000032","completion":"0.00000128","input_cache_read":"0.000000064","input_cache_write":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000096","completion":"0.00000384","input_cache_read":"0.000000192","input_cache_write":"0.0000012"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","logprobs","top_logprobs","tools","tool_choice","structured_outputs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97219403874557,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.2e-07,"_completion_per_m":1.28e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6.4e-08,"_cached_write_per_m":4e-07}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":6.079999999999999e-07,"_priciest_blended_per_m":6.079999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"minimax/minimax-m3:batch","canonical_slug":"minimax/minimax-m3-20260531","hugging_face_id":"MiniMaxAI/Minimax-M3","name":"MiniMax: MiniMax M3 (batch)","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","context_length":524288,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006"},"top_provider":{"context_length":524288,"max_completion_tokens":471859,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m3-20260531/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1158,"win_rate":44.4,"rank":19},{"arena":"agents","category":"androidnative","elo":1177,"win_rate":46.6,"rank":22},{"arena":"agents","category":"fullstack","elo":1225,"win_rate":50,"rank":16},{"arena":"agents","category":"htmlslides","elo":1185,"win_rate":45.3,"rank":12},{"arena":"agents","category":"mobileapps","elo":1202,"win_rate":47.6,"rank":18},{"arena":"agents","category":"python-pptxslides","elo":1241,"win_rate":49.5,"rank":10},{"arena":"agents","category":"webapps","elo":1231,"win_rate":49,"rank":18},{"arena":"models","category":"3d","elo":1256,"win_rate":52.6,"rank":31},{"arena":"models","category":"asciiart","elo":1187,"win_rate":47.6,"rank":27},{"arena":"models","category":"codecategories","elo":1275,"win_rate":52.8,"rank":26},{"arena":"models","category":"dataviz","elo":1254,"win_rate":51.8,"rank":29},{"arena":"models","category":"gamedev","elo":1247,"win_rate":47.9,"rank":34},{"arena":"models","category":"svg","elo":1211,"win_rate":49.2,"rank":28},{"arena":"models","category":"uicomponent","elo":1275,"win_rate":53,"rank":27},{"arena":"models","category":"website","elo":1279,"win_rate":53.3,"rank":25}],"artificial_analysis":{"intelligence_index":45.4,"coding_index":58.6,"agentic_index":36.1}},"reasoning":{"mandatory":false},"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Together | minimax/minimax-m3-20260531:batch","model_id":"minimax/minimax-m3:batch","model_name":"MiniMax: MiniMax M3","context_length":524288,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":471859,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Together","_cheapest_blended_per_m":5.699999999999999e-07,"_priciest_blended_per_m":5.699999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA: Nemotron 3 Ultra (free)","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1177,"win_rate":41.2,"rank":57},{"arena":"models","category":"asciiart","elo":1097,"win_rate":36.2,"rank":55},{"arena":"models","category":"codecategories","elo":1159,"win_rate":36.3,"rank":75},{"arena":"models","category":"dataviz","elo":1158,"win_rate":38.2,"rank":69},{"arena":"models","category":"gamedev","elo":1160,"win_rate":37,"rank":68},{"arena":"models","category":"svg","elo":1119,"win_rate":36.7,"rank":54},{"arena":"models","category":"uicomponent","elo":1162,"win_rate":37.5,"rank":69},{"arena":"models","category":"website","elo":1146,"win_rate":34.2,"rank":80}],"artificial_analysis":{"intelligence_index":38.3,"coding_index":49.3,"agentic_index":27.5}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["high","medium"],"default_effort":"high"},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Nvidia | nvidia/nemotron-3-ultra-550b-a55b-20260604:free","model_id":"nvidia/nemotron-3-ultra-550b-a55b:free","model_name":"NVIDIA: Nemotron 3 Ultra","context_length":1000000,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Nvidia","tag":"nvidia","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.04012009324548,"uptime_last_5m":99.11377930245855,"uptime_last_1d":99.00648599971026,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Nvidia","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"stepfun/step-3.7-flash","canonical_slug":"stepfun/step-3.7-flash-20260528","hugging_face_id":"stepfun-ai/Step-3.7-Flash","name":"StepFun: Step 3.7 Flash","created":1779985069,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.00000115","input_cache_read":"0.00000004"},"top_provider":{"context_length":256000,"max_completion_tokens":230400,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/stepfun/step-3.7-flash-20260528/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1169,"win_rate":41.9,"rank":60},{"arena":"models","category":"asciiart","elo":1179,"win_rate":45.3,"rank":30},{"arena":"models","category":"codecategories","elo":1203,"win_rate":44,"rank":51},{"arena":"models","category":"dataviz","elo":1193,"win_rate":44.3,"rank":54},{"arena":"models","category":"gamedev","elo":1190,"win_rate":40.8,"rank":55},{"arena":"models","category":"svg","elo":1112,"win_rate":38.1,"rank":56},{"arena":"models","category":"uicomponent","elo":1201,"win_rate":43.5,"rank":51},{"arena":"models","category":"website","elo":1213,"win_rate":45.3,"rank":49}],"artificial_analysis":{"intelligence_index":30.9,"coding_index":39.6,"agentic_index":21.7}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":2e-07,"_completion_per_m":1.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"StepFun | stepfun/step-3.7-flash-20260528","model_id":"stepfun/step-3.7-flash","model_name":"StepFun: Step 3.7 Flash","context_length":256000,"pricing":{"prompt":"0.0000002","completion":"0.00000115","input_cache_read":"0.00000004","discount":0},"provider_name":"StepFun","tag":"stepfun/fp8","quantization":"fp8","max_completion_tokens":230400,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","top_p","stop","frequency_penalty","logprobs","top_logprobs","response_format","structured_outputs","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.25093632958801,"uptime_last_5m":98.50746268656717,"uptime_last_1d":98.95134739665895,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"DeepInfra | stepfun/step-3.7-flash-20260528","model_id":"stepfun/step-3.7-flash","model_name":"StepFun: Step 3.7 Flash","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.00000115","input_cache_read":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.92422192151557,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Novita | stepfun/step-3.7-flash-20260528","model_id":"stepfun/step-3.7-flash","model_name":"StepFun: Step 3.7 Flash","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.00000115","input_cache_read":"0.00000004","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":256000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.45652173913044,"uptime_last_5m":100,"uptime_last_1d":97.55163888667357,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null}],"_cheapest_provider":"StepFun","_cheapest_blended_per_m":4.85e-07,"_priciest_blended_per_m":4.85e-07,"_provider_spread_multiplier":1.0},{"id":"minimax/minimax-m3","canonical_slug":"minimax/minimax-m3-20260531","hugging_face_id":"MiniMaxAI/Minimax-M3","name":"MiniMax: MiniMax M3","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006"},"top_provider":{"context_length":524288,"max_completion_tokens":512000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m3-20260531/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1158,"win_rate":44.4,"rank":19},{"arena":"agents","category":"androidnative","elo":1177,"win_rate":46.6,"rank":22},{"arena":"agents","category":"fullstack","elo":1225,"win_rate":50,"rank":16},{"arena":"agents","category":"htmlslides","elo":1185,"win_rate":45.3,"rank":12},{"arena":"agents","category":"mobileapps","elo":1202,"win_rate":47.6,"rank":18},{"arena":"agents","category":"python-pptxslides","elo":1241,"win_rate":49.5,"rank":10},{"arena":"agents","category":"webapps","elo":1231,"win_rate":49,"rank":18},{"arena":"models","category":"3d","elo":1256,"win_rate":52.6,"rank":31},{"arena":"models","category":"asciiart","elo":1187,"win_rate":47.6,"rank":27},{"arena":"models","category":"codecategories","elo":1275,"win_rate":52.8,"rank":26},{"arena":"models","category":"dataviz","elo":1254,"win_rate":51.8,"rank":29},{"arena":"models","category":"gamedev","elo":1247,"win_rate":47.9,"rank":34},{"arena":"models","category":"svg","elo":1211,"win_rate":49.2,"rank":28},{"arena":"models","category":"uicomponent","elo":1275,"win_rate":53,"rank":27},{"arena":"models","category":"website","elo":1279,"win_rate":53.3,"rank":25}],"artificial_analysis":{"intelligence_index":45.4,"coding_index":58.6,"agentic_index":36.1}},"reasoning":{"mandatory":false},"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"CoreWeave | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":262144,"pricing":{"prompt":"0.00000023","completion":"0.00000096","input_cache_read":"0.00000005","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp4","quantization":"fp4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.86141960405601,"uptime_last_5m":92.7710843373494,"uptime_last_1d":98.35861244220615,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.3e-07,"_completion_per_m":9.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"DeepInfra | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":524288,"pricing":{"prompt":"0.00000028","completion":"0.0000011","input_cache_read":"0.000000056","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":512000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-2,"uptime_last_30m":92.72924579489961,"uptime_last_5m":90.2439024390244,"uptime_last_1d":96.06531285920599,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.8e-07,"_completion_per_m":1.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.6e-08,"_cached_write_per_m":null},{"name":"AtlasCloud | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":524300,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":524288,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.60591133004925,"uptime_last_5m":99.24812030075188,"uptime_last_1d":99.77788589681214,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Parasail | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":524288,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.17624148003895,"uptime_last_5m":99.38271604938271,"uptime_last_1d":98.35651343030045,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Novita | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":1000000,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.72101828326608,"uptime_last_5m":99.76435935198822,"uptime_last_1d":99.74235562826502,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"StreamLake | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":1000000,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0.5},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":512000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.8756148981026,"uptime_last_5m":98.70550161812298,"uptime_last_1d":99.43919623392627,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Venice | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":524288,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.8778708599872,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Minimax | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":524288,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"Minimax","tag":"minimax/fp8","quantization":"fp8","max_completion_tokens":512000,"max_prompt_tokens":524288,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.64633068081345,"uptime_last_5m":99.64850615114236,"uptime_last_1d":99.61287702962713,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"SambaNova | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":1048576,"pricing":{"prompt":"0.0000006","completion":"0.0000024","discount":0},"provider_name":"SambaNova","tag":"sambanova","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.23954372623575,"uptime_last_5m":95.34883720930233,"uptime_last_1d":99.47888262740108,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"GMICloud | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":1048576,"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.00000012","discount":0},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.7943925233645,"uptime_last_5m":null,"uptime_last_1d":96.05600609967422,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null},{"name":"ModelRun | minimax/minimax-m3-20260531","model_id":"minimax/minimax-m3","model_name":"MiniMax: MiniMax M3","context_length":1048576,"pricing":{"prompt":"0.00000075","completion":"0.000003","input_cache_read":"0.00000015","discount":0},"provider_name":"ModelRun","tag":"modelrun/fp4","quantization":"fp4","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","presence_penalty","repetition_penalty","frequency_penalty","top_p","top_k","stop","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.94047619047619,"uptime_last_5m":100,"uptime_last_1d":99.66137484388479,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"CoreWeave","_cheapest_blended_per_m":4.4899999999999996e-07,"_priciest_blended_per_m":1.425e-06,"_provider_spread_multiplier":3.173719376391982},{"id":"minimax/minimax-m3:free","canonical_slug":"minimax/minimax-m3-20260531","hugging_face_id":"MiniMaxAI/Minimax-M3","name":"MiniMax: MiniMax M3 (free)","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m3-20260531/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1158,"win_rate":44.4,"rank":19},{"arena":"agents","category":"androidnative","elo":1177,"win_rate":46.6,"rank":22},{"arena":"agents","category":"fullstack","elo":1225,"win_rate":50,"rank":16},{"arena":"agents","category":"htmlslides","elo":1185,"win_rate":45.3,"rank":12},{"arena":"agents","category":"mobileapps","elo":1202,"win_rate":47.6,"rank":18},{"arena":"agents","category":"python-pptxslides","elo":1241,"win_rate":49.5,"rank":10},{"arena":"agents","category":"webapps","elo":1231,"win_rate":49,"rank":18},{"arena":"models","category":"3d","elo":1256,"win_rate":52.6,"rank":31},{"arena":"models","category":"asciiart","elo":1187,"win_rate":47.6,"rank":27},{"arena":"models","category":"codecategories","elo":1275,"win_rate":52.8,"rank":26},{"arena":"models","category":"dataviz","elo":1254,"win_rate":51.8,"rank":29},{"arena":"models","category":"gamedev","elo":1247,"win_rate":47.9,"rank":34},{"arena":"models","category":"svg","elo":1211,"win_rate":49.2,"rank":28},{"arena":"models","category":"uicomponent","elo":1275,"win_rate":53,"rank":27},{"arena":"models","category":"website","elo":1279,"win_rate":53.3,"rank":25}],"artificial_analysis":{"intelligence_index":45.4,"coding_index":58.6,"agentic_index":36.1}},"reasoning":{"mandatory":false},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | minimax/minimax-m3-20260531:free","model_id":"minimax/minimax-m3:free","model_name":"MiniMax: MiniMax M3","context_length":1048576,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.686258254481,"uptime_last_5m":99.487296864271,"uptime_last_1d":99.68814081613758,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"anthropic/claude-opus-4.8","canonical_slug":"anthropic/claude-4.8-opus-20260528","hugging_face_id":null,"name":"Anthropic: Claude Opus 4.8","created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1238,"win_rate":55.5,"rank":5},{"arena":"agents","category":"agentichtmlslides","elo":1227,"win_rate":55.6,"rank":4},{"arena":"agents","category":"agenticslides","elo":1294,"win_rate":64.8,"rank":2},{"arena":"agents","category":"agenticslides(html)","elo":1230,"win_rate":56,"rank":4},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":2},{"arena":"agents","category":"androidnative","elo":1251,"win_rate":58.2,"rank":7},{"arena":"agents","category":"fullstack","elo":1271,"win_rate":59.1,"rank":7},{"arena":"agents","category":"godotgamedev","elo":1253,"win_rate":58.9,"rank":5},{"arena":"agents","category":"htmlslides","elo":1234,"win_rate":58.1,"rank":3},{"arena":"agents","category":"mobileapps","elo":1236,"win_rate":54.3,"rank":11},{"arena":"agents","category":"pptxslides","elo":1306,"win_rate":67.9,"rank":2},{"arena":"agents","category":"python-pptxslides","elo":1298,"win_rate":65.9,"rank":3},{"arena":"agents","category":"webapps","elo":1255,"win_rate":53.1,"rank":10},{"arena":"models","category":"3d","elo":1266,"win_rate":53.5,"rank":28},{"arena":"models","category":"asciiart","elo":1299,"win_rate":63,"rank":6},{"arena":"models","category":"codecategories","elo":1273,"win_rate":53.8,"rank":27},{"arena":"models","category":"dataviz","elo":1259,"win_rate":54.2,"rank":25},{"arena":"models","category":"gamedev","elo":1290,"win_rate":54.7,"rank":23},{"arena":"models","category":"svg","elo":1221,"win_rate":52.9,"rank":23},{"arena":"models","category":"uicomponent","elo":1281,"win_rate":54.9,"rank":25},{"arena":"models","category":"website","elo":1272,"win_rate":54,"rank":27}],"artificial_analysis":{"intelligence_index":57.3,"coding_index":74.3,"agentic_index":49.4}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06,"_endpoints":[{"name":"Google | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98165168220714,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Azure | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.12536443148689,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Amazon Bedrock | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.83792544570503,"uptime_last_5m":100,"uptime_last_1d":99.88912057723496,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Azure | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Azure","tag":"azure/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Anthropic | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.49832775919732,"uptime_last_5m":100,"uptime_last_1d":99.52809092731675,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Claude Platform on AWS | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Claude Platform on AWS","tag":"claude-on-aws","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.99353504008275,"uptime_last_5m":100,"uptime_last_1d":99.9858181412986,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Amazon Bedrock | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06},{"name":"Amazon Bedrock | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06},{"name":"Google | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Google","tag":"google-vertex/europe","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06},{"name":"Google | anthropic/claude-4.8-opus-20260528","model_id":"anthropic/claude-opus-4.8","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06}],"_cheapest_provider":"Google","_cheapest_blended_per_m":1.1e-05,"_priciest_blended_per_m":1.21e-05,"_provider_spread_multiplier":1.0999999999999999},{"id":"anthropic/claude-opus-4.8:batch","canonical_slug":"anthropic/claude-4.8-opus-20260528","hugging_face_id":null,"name":"Anthropic: Claude Opus 4.8 (batch)","created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1238,"win_rate":55.5,"rank":5},{"arena":"agents","category":"agentichtmlslides","elo":1227,"win_rate":55.6,"rank":4},{"arena":"agents","category":"agenticslides","elo":1294,"win_rate":64.8,"rank":2},{"arena":"agents","category":"agenticslides(html)","elo":1230,"win_rate":56,"rank":4},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":2},{"arena":"agents","category":"androidnative","elo":1251,"win_rate":58.2,"rank":7},{"arena":"agents","category":"fullstack","elo":1271,"win_rate":59.1,"rank":7},{"arena":"agents","category":"godotgamedev","elo":1253,"win_rate":58.9,"rank":5},{"arena":"agents","category":"htmlslides","elo":1234,"win_rate":58.1,"rank":3},{"arena":"agents","category":"mobileapps","elo":1236,"win_rate":54.3,"rank":11},{"arena":"agents","category":"pptxslides","elo":1306,"win_rate":67.9,"rank":2},{"arena":"agents","category":"python-pptxslides","elo":1298,"win_rate":65.9,"rank":3},{"arena":"agents","category":"webapps","elo":1255,"win_rate":53.1,"rank":10},{"arena":"models","category":"3d","elo":1266,"win_rate":53.5,"rank":28},{"arena":"models","category":"asciiart","elo":1299,"win_rate":63,"rank":6},{"arena":"models","category":"codecategories","elo":1273,"win_rate":53.8,"rank":27},{"arena":"models","category":"dataviz","elo":1259,"win_rate":54.2,"rank":25},{"arena":"models","category":"gamedev","elo":1290,"win_rate":54.7,"rank":23},{"arena":"models","category":"svg","elo":1221,"win_rate":52.9,"rank":23},{"arena":"models","category":"uicomponent","elo":1281,"win_rate":54.9,"rank":25},{"arena":"models","category":"website","elo":1272,"win_rate":54,"rank":27}],"artificial_analysis":{"intelligence_index":57.3,"coding_index":74.3,"agentic_index":49.4}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.8-opus-20260528:batch","model_id":"anthropic/claude-opus-4.8:batch","model_name":"Anthropic: Claude Opus 4.8","context_length":1000000,"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":5.5e-06,"_priciest_blended_per_m":5.5e-06,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-opus-4.8-fast","canonical_slug":"anthropic/claude-4.8-opus-fast-20260528","hugging_face_id":null,"name":"Anthropic: Claude Opus 4.8 (Fast)","created":1779913703,"description":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.8-opus-fast-20260528/endpoints"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.8-opus-fast-20260528","model_id":"anthropic/claude-opus-4.8-fast","model_name":"Anthropic: Claude Opus 4.8 (Fast)","context_length":1000000,"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-06,"_cached_write_per_m":1.25e-05}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":2.2e-05,"_priciest_blended_per_m":2.2e-05,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3.5-flash","canonical_slug":"google/gemini-3.5-flash-20260519","hugging_face_id":null,"name":"Google: Gemini 3.5 Flash","created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.000009","image":"0.0000015","audio":"0.000003","input_audio_cache":"0.0000003","web_search":"0.014","internal_reasoning":"0.000009","input_cache_read":"0.00000015","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-01","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.5-flash-20260519/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1180,"win_rate":55.5,"rank":13},{"arena":"agents","category":"agentichtmlslides","elo":1162,"win_rate":45.8,"rank":7},{"arena":"agents","category":"agenticslides","elo":1244,"win_rate":57.5,"rank":4},{"arena":"agents","category":"agenticslides(html)","elo":1162,"win_rate":45.7,"rank":7},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1242,"win_rate":57.8,"rank":3},{"arena":"agents","category":"androidnative","elo":1208,"win_rate":58,"rank":14},{"arena":"agents","category":"fullstack","elo":1224,"win_rate":57.9,"rank":17},{"arena":"agents","category":"godotgamedev","elo":1135,"win_rate":42.9,"rank":21},{"arena":"agents","category":"htmlslides","elo":1159,"win_rate":47,"rank":18},{"arena":"agents","category":"mobileapps","elo":1206,"win_rate":52.1,"rank":15},{"arena":"agents","category":"pptxslides","elo":1244,"win_rate":57.7,"rank":3},{"arena":"agents","category":"python-pptxslides","elo":1247,"win_rate":57.4,"rank":9},{"arena":"agents","category":"webapps","elo":1234,"win_rate":53.4,"rank":17},{"arena":"models","category":"3d","elo":1288,"win_rate":57.9,"rank":22},{"arena":"models","category":"asciiart","elo":1284,"win_rate":59.6,"rank":10},{"arena":"models","category":"codecategories","elo":1287,"win_rate":55.4,"rank":22},{"arena":"models","category":"dataviz","elo":1256,"win_rate":54.4,"rank":28},{"arena":"models","category":"gamedev","elo":1302,"win_rate":55,"rank":16},{"arena":"models","category":"svg","elo":1291,"win_rate":60.5,"rank":5},{"arena":"models","category":"uicomponent","elo":1300,"win_rate":56.3,"rank":16},{"arena":"models","category":"website","elo":1281,"win_rate":54.6,"rank":24}],"artificial_analysis":{"intelligence_index":52,"coding_index":70.1,"agentic_index":39.7}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":1.5e-06,"_completion_per_m":9e-06,"_image_per_m":1.5e-06,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":8.33333333333333e-08,"_endpoints":[{"name":"Google AI Studio | google/gemini-3.5-flash-20260519","model_id":"google/gemini-3.5-flash","model_name":"Google: Gemini 3.5 Flash","context_length":1048576,"pricing":{"prompt":"0.0000015","completion":"0.000009","image":"0.0000015","audio":"0.000003","input_audio_cache":"0.0000003","web_search":"0.014","internal_reasoning":"0.000009","input_cache_read":"0.00000015","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.80119284294234,"uptime_last_5m":99.96076892899175,"uptime_last_1d":99.37523011782032,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-06,"_completion_per_m":9e-06,"_image_per_m":1.5e-06,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-3.5-flash-20260519","model_id":"google/gemini-3.5-flash","model_name":"Google: Gemini 3.5 Flash","context_length":1048576,"pricing":{"prompt":"0.00000075","completion":"0.0000045","image":"0.00000075","audio":"0.0000015","input_audio_cache":"0.00000015","web_search":"0.014","internal_reasoning":"0.0000045","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.80119284294234,"uptime_last_5m":99.96076892899175,"uptime_last_1d":99.37523011782032,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":4.5e-06,"_image_per_m":7.5e-07,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-3.5-flash-20260519","model_id":"google/gemini-3.5-flash","model_name":"Google: Gemini 3.5 Flash","context_length":1048576,"pricing":{"prompt":"0.0000027","completion":"0.0000162","image":"0.0000027","audio":"0.0000054","input_audio_cache":"0.00000054","web_search":"0.014","internal_reasoning":"0.0000162","input_cache_read":"0.00000027","input_cache_write":"0.00000015","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.80119284294234,"uptime_last_5m":99.96076892899175,"uptime_last_1d":99.37523011782032,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-06,"_completion_per_m":1.62e-05,"_image_per_m":2.7e-06,"_request_per_m":null,"_cached_read_per_m":2.7e-07,"_cached_write_per_m":1.5e-07},{"name":"Google | google/gemini-3.5-flash-20260519","model_id":"google/gemini-3.5-flash","model_name":"Google: Gemini 3.5 Flash","context_length":1048576,"pricing":{"prompt":"0.0000015","completion":"0.000009","image":"0.0000015","audio":"0.000003","input_audio_cache":"0.0000003","web_search":"0.014","internal_reasoning":"0.000009","input_cache_read":"0.00000015","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.85032024505709,"uptime_last_5m":99.90101460034644,"uptime_last_1d":99.57064308265318,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-06,"_completion_per_m":9e-06,"_image_per_m":1.5e-06,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google | google/gemini-3.5-flash-20260519","model_id":"google/gemini-3.5-flash","model_name":"Google: Gemini 3.5 Flash","context_length":1048576,"pricing":{"prompt":"0.00000075","completion":"0.0000045","image":"0.00000075","audio":"0.0000015","input_audio_cache":"0.00000015","web_search":"0.014","internal_reasoning":"0.0000045","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.85032024505709,"uptime_last_5m":99.90101460034644,"uptime_last_1d":99.57064308265318,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":4.5e-06,"_image_per_m":7.5e-07,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google | google/gemini-3.5-flash-20260519","model_id":"google/gemini-3.5-flash","model_name":"Google: Gemini 3.5 Flash","context_length":1048576,"pricing":{"prompt":"0.0000027","completion":"0.0000162","image":"0.0000027","audio":"0.0000054","input_audio_cache":"0.00000054","web_search":"0.014","internal_reasoning":"0.0000162","input_cache_read":"0.00000027","input_cache_write":"0.00000015","discount":0},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.85032024505709,"uptime_last_5m":99.90101460034644,"uptime_last_1d":99.57064308265318,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-06,"_completion_per_m":1.62e-05,"_image_per_m":2.7e-06,"_request_per_m":null,"_cached_read_per_m":2.7e-07,"_cached_write_per_m":1.5e-07},{"name":"Google | google/gemini-3.5-flash-20260519","model_id":"google/gemini-3.5-flash","model_name":"Google: Gemini 3.5 Flash","context_length":1048576,"pricing":{"prompt":"0.00000165","completion":"0.0000099","image":"0.00000165","audio":"0.0000033","input_audio_cache":"0.00000033","web_search":"0.014","internal_reasoning":"0.0000099","input_cache_read":"0.000000165","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.65e-06,"_completion_per_m":9.9e-06,"_image_per_m":1.65e-06,"_request_per_m":null,"_cached_read_per_m":1.65e-07,"_cached_write_per_m":8.33333333333333e-08}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":1.8749999999999998e-06,"_priciest_blended_per_m":6.75e-06,"_provider_spread_multiplier":3.6},{"id":"qwen/qwen3.7-max","canonical_slug":"qwen/qwen3.7-max-20260520","hugging_face_id":null,"name":"Qwen: Qwen3.7 Max","created":1779376861,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000001475","completion":"0.000004425","input_cache_read":"0.000000295","input_cache_write":"0.00000184375"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.7-max-20260520/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1166,"win_rate":47.4,"rank":18},{"arena":"agents","category":"androidnative","elo":1178,"win_rate":48.5,"rank":21},{"arena":"agents","category":"fullstack","elo":1212,"win_rate":50.2,"rank":18},{"arena":"agents","category":"godotgamedev","elo":1224,"win_rate":55.4,"rank":8},{"arena":"agents","category":"htmlslides","elo":1173,"win_rate":43.6,"rank":14},{"arena":"agents","category":"mobileapps","elo":1197,"win_rate":47.5,"rank":21},{"arena":"agents","category":"python-pptxslides","elo":1220,"win_rate":47.7,"rank":12},{"arena":"agents","category":"webapps","elo":1240,"win_rate":50.6,"rank":14},{"arena":"models","category":"3d","elo":1314,"win_rate":56.5,"rank":12},{"arena":"models","category":"asciiart","elo":1241,"win_rate":53.5,"rank":15},{"arena":"models","category":"codecategories","elo":1301,"win_rate":55.8,"rank":15},{"arena":"models","category":"dataviz","elo":1298,"win_rate":54.6,"rank":14},{"arena":"models","category":"gamedev","elo":1308,"win_rate":56,"rank":14},{"arena":"models","category":"svg","elo":1259,"win_rate":58.8,"rank":12},{"arena":"models","category":"uicomponent","elo":1297,"win_rate":55,"rank":18},{"arena":"models","category":"website","elo":1293,"win_rate":55.7,"rank":16}],"artificial_analysis":{"intelligence_index":46.7,"coding_index":66,"agentic_index":30.9}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":1.475e-06,"_completion_per_m":4.425e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.95e-07,"_cached_write_per_m":1.84375e-06,"_endpoints":[{"name":"Alibaba | qwen/qwen3.7-max-20260520","model_id":"qwen/qwen3.7-max","model_name":"Qwen: Qwen3.7 Max","context_length":1000000,"pricing":{"prompt":"0.000001475","completion":"0.000004425","input_cache_read":"0.000000295","input_cache_write":"0.00000184375","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99765249031653,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.475e-06,"_completion_per_m":4.425e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.95e-07,"_cached_write_per_m":1.84375e-06}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":2.3600000000000003e-06,"_priciest_blended_per_m":2.3600000000000003e-06,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3.5-flash:batch","canonical_slug":"google/gemini-3.5-flash-20260519","hugging_face_id":null,"name":"Google: Gemini 3.5 Flash (batch)","created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.0000045","image":"0.00000075","audio":"0.0000015","input_audio_cache":"0.00000015","web_search":"0.014","internal_reasoning":"0.0000045","input_cache_read":"0.000000075"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-01","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.5-flash-20260519/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1180,"win_rate":55.5,"rank":13},{"arena":"agents","category":"agentichtmlslides","elo":1162,"win_rate":45.8,"rank":7},{"arena":"agents","category":"agenticslides","elo":1244,"win_rate":57.5,"rank":4},{"arena":"agents","category":"agenticslides(html)","elo":1162,"win_rate":45.7,"rank":7},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1242,"win_rate":57.8,"rank":3},{"arena":"agents","category":"androidnative","elo":1208,"win_rate":58,"rank":14},{"arena":"agents","category":"fullstack","elo":1224,"win_rate":57.9,"rank":17},{"arena":"agents","category":"godotgamedev","elo":1135,"win_rate":42.9,"rank":21},{"arena":"agents","category":"htmlslides","elo":1159,"win_rate":47,"rank":18},{"arena":"agents","category":"mobileapps","elo":1206,"win_rate":52.1,"rank":15},{"arena":"agents","category":"pptxslides","elo":1244,"win_rate":57.7,"rank":3},{"arena":"agents","category":"python-pptxslides","elo":1247,"win_rate":57.4,"rank":9},{"arena":"agents","category":"webapps","elo":1234,"win_rate":53.4,"rank":17},{"arena":"models","category":"3d","elo":1288,"win_rate":57.9,"rank":22},{"arena":"models","category":"asciiart","elo":1284,"win_rate":59.6,"rank":10},{"arena":"models","category":"codecategories","elo":1287,"win_rate":55.4,"rank":22},{"arena":"models","category":"dataviz","elo":1256,"win_rate":54.4,"rank":28},{"arena":"models","category":"gamedev","elo":1302,"win_rate":55,"rank":16},{"arena":"models","category":"svg","elo":1291,"win_rate":60.5,"rank":5},{"arena":"models","category":"uicomponent","elo":1300,"win_rate":56.3,"rank":16},{"arena":"models","category":"website","elo":1281,"win_rate":54.6,"rank":24}],"artificial_analysis":{"intelligence_index":52,"coding_index":70.1,"agentic_index":39.7}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":7.5e-07,"_completion_per_m":4.5e-06,"_image_per_m":7.5e-07,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | google/gemini-3.5-flash-20260519:batch","model_id":"google/gemini-3.5-flash:batch","model_name":"Google: Gemini 3.5 Flash","context_length":1048576,"pricing":{"prompt":"0.00000075","completion":"0.0000045","image":"0.00000075","audio":"0.0000015","input_audio_cache":"0.00000015","web_search":"0.014","internal_reasoning":"0.0000045","input_cache_read":"0.000000075","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":4.5e-06,"_image_per_m":7.5e-07,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Google","_cheapest_blended_per_m":1.8749999999999998e-06,"_priciest_blended_per_m":1.8749999999999998e-06,"_provider_spread_multiplier":1.0},{"id":"x-ai/grok-build-0.1","canonical_slug":"x-ai/grok-build-0.1-20260520","hugging_face_id":null,"name":"SpaceXAI: Grok Build 0.1","created":1779298123,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...","context_length":256000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000002","web_search":"0.005","input_cache_read":"0.0000002","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000002","completion":"0.000004","input_cache_read":"0.0000004"}]},"top_provider":{"context_length":256000,"max_completion_tokens":230400,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-build-0.1-20260520/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":40.7,"coding_index":51.5,"agentic_index":28.9}},"reasoning":{"mandatory":true},"_prompt_per_m":1e-06,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"xAI | x-ai/grok-build-0.1-20260520","model_id":"x-ai/grok-build-0.1","model_name":"SpaceXAI: Grok Build 0.1","context_length":256000,"pricing":{"prompt":"0.000001","completion":"0.000002","web_search":"0.005","input_cache_read":"0.0000002","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000002","completion":"0.000004","input_cache_read":"0.0000004"}]},"provider_name":"xAI","tag":"xai","quantization":"unknown","max_completion_tokens":230400,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-build-0.1-20260520","model_id":"x-ai/grok-build-0.1","model_name":"SpaceXAI: Grok Build 0.1","context_length":256000,"pricing":{"prompt":"0.000002","completion":"0.000004","web_search":"0.005","input_cache_read":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000008","input_cache_read":"0.0000008"}]},"provider_name":"xAI","tag":"xai/priority","quantization":"unknown","max_completion_tokens":230400,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-build-0.1-20260520","model_id":"x-ai/grok-build-0.1","model_name":"SpaceXAI: Grok Build 0.1","context_length":256000,"pricing":{"prompt":"0.000001","completion":"0.000002","web_search":"0.005","input_cache_read":"0.0000002","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000002","completion":"0.000004","input_cache_read":"0.0000004"}]},"provider_name":"xAI","tag":"xai/zdr","quantization":"unknown","max_completion_tokens":230400,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-build-0.1-20260520","model_id":"x-ai/grok-build-0.1","model_name":"SpaceXAI: Grok Build 0.1","context_length":256000,"pricing":{"prompt":"0.000002","completion":"0.000004","web_search":"0.005","input_cache_read":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000008","input_cache_read":"0.0000008"}]},"provider_name":"xAI","tag":"xai/zdr/priority","quantization":"unknown","max_completion_tokens":230400,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":null}],"_cheapest_provider":"xAI","_cheapest_blended_per_m":1.2999999999999998e-06,"_priciest_blended_per_m":2.5999999999999997e-06,"_provider_spread_multiplier":2.0},{"id":"anthropic/claude-opus-4.7-fast","canonical_slug":"anthropic/claude-4.7-opus-fast-20260512","hugging_face_id":null,"name":"Anthropic: Claude Opus 4.7 (Fast)","created":1778613011,"description":"Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.00003","completion":"0.00015","web_search":"0.01","input_cache_read":"0.000003","input_cache_write":"0.0000375","input_cache_write_1h":"0.00006"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.7-opus-fast-20260512/endpoints"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":3e-05,"_completion_per_m":0.00015,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-06,"_cached_write_per_m":3.75e-05,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.7-opus-fast-20260512","model_id":"anthropic/claude-opus-4.7-fast","model_name":"Anthropic: Claude Opus 4.7 (Fast)","context_length":1000000,"pricing":{"prompt":"0.00003","completion":"0.00015","web_search":"0.01","input_cache_read":"0.000003","input_cache_write":"0.0000375","input_cache_write_1h":"0.00006","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-05,"_completion_per_m":0.00015,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-06,"_cached_write_per_m":3.75e-05}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":6.599999999999999e-05,"_priciest_blended_per_m":6.599999999999999e-05,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3.1-flash-lite","canonical_slug":"google/gemini-3.1-flash-lite-20260507","hugging_face_id":null,"name":"Google: Gemini 3.1 Flash Lite","created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"},"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":2.5e-07,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":8.33333333333333e-08,"_endpoints":[{"name":"Google | google/gemini-3.1-flash-lite-20260507","model_id":"google/gemini-3.1-flash-lite","model_name":"Google: Gemini 3.1 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.63577941522828,"uptime_last_5m":99.64950931303825,"uptime_last_1d":99.27417456340828,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":2.5e-07,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google | google/gemini-3.1-flash-lite-20260507","model_id":"google/gemini-3.1-flash-lite","model_name":"Google: Gemini 3.1 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.000000125","completion":"0.00000075","image":"0.000000125","audio":"0.00000025","input_audio_cache":"0.000000025","web_search":"0.014","internal_reasoning":"0.00000075","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.63577941522828,"uptime_last_5m":99.64950931303825,"uptime_last_1d":99.27417456340828,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-07,"_completion_per_m":7.5e-07,"_image_per_m":1.25e-07,"_request_per_m":null,"_cached_read_per_m":1.25e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google | google/gemini-3.1-flash-lite-20260507","model_id":"google/gemini-3.1-flash-lite","model_name":"Google: Gemini 3.1 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000045","completion":"0.0000027","image":"0.00000045","audio":"0.0000009","input_audio_cache":"0.00000009","web_search":"0.014","internal_reasoning":"0.0000027","input_cache_read":"0.000000045","input_cache_write":"0.00000015","discount":0},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.63577941522828,"uptime_last_5m":99.64950931303825,"uptime_last_1d":99.27417456340828,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":2.7e-06,"_image_per_m":4.5e-07,"_request_per_m":null,"_cached_read_per_m":4.5e-08,"_cached_write_per_m":1.5e-07},{"name":"Google AI Studio | google/gemini-3.1-flash-lite-20260507","model_id":"google/gemini-3.1-flash-lite","model_name":"Google: Gemini 3.1 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.27569565183492,"uptime_last_5m":99.49758094529216,"uptime_last_1d":99.15489125814076,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":2.5e-07,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-3.1-flash-lite-20260507","model_id":"google/gemini-3.1-flash-lite","model_name":"Google: Gemini 3.1 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.000000125","completion":"0.00000075","image":"0.000000125","audio":"0.00000025","input_audio_cache":"0.000000025","web_search":"0.014","internal_reasoning":"0.00000075","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.27569565183492,"uptime_last_5m":99.49758094529216,"uptime_last_1d":99.15489125814076,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-07,"_completion_per_m":7.5e-07,"_image_per_m":1.25e-07,"_request_per_m":null,"_cached_read_per_m":1.25e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-3.1-flash-lite-20260507","model_id":"google/gemini-3.1-flash-lite","model_name":"Google: Gemini 3.1 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000045","completion":"0.0000027","image":"0.00000045","audio":"0.0000009","input_audio_cache":"0.00000009","web_search":"0.014","internal_reasoning":"0.0000027","input_cache_read":"0.000000045","input_cache_write":"0.00000015","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.27569565183492,"uptime_last_5m":99.49758094529216,"uptime_last_1d":99.15489125814076,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":2.7e-06,"_image_per_m":4.5e-07,"_request_per_m":null,"_cached_read_per_m":4.5e-08,"_cached_write_per_m":1.5e-07},{"name":"Google | google/gemini-3.1-flash-lite-20260507","model_id":"google/gemini-3.1-flash-lite","model_name":"Google: Gemini 3.1 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.000000275","completion":"0.00000165","image":"0.000000275","audio":"0.00000055","input_audio_cache":"0.000000055","web_search":"0.014","internal_reasoning":"0.00000165","input_cache_read":"0.0000000275","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/eu","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.75e-07,"_completion_per_m":1.65e-06,"_image_per_m":2.75e-07,"_request_per_m":null,"_cached_read_per_m":2.75e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google | google/gemini-3.1-flash-lite-20260507","model_id":"google/gemini-3.1-flash-lite","model_name":"Google: Gemini 3.1 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.000000275","completion":"0.00000165","image":"0.000000275","audio":"0.00000055","input_audio_cache":"0.000000055","web_search":"0.014","internal_reasoning":"0.00000165","input_cache_read":"0.0000000275","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.75e-07,"_completion_per_m":1.65e-06,"_image_per_m":2.75e-07,"_request_per_m":null,"_cached_read_per_m":2.75e-08,"_cached_write_per_m":8.33333333333333e-08}],"_cheapest_provider":"Google","_cheapest_blended_per_m":3.1249999999999997e-07,"_priciest_blended_per_m":1.1249999999999998e-06,"_provider_spread_multiplier":3.5999999999999996},{"id":"google/gemini-3.1-flash-lite:batch","canonical_slug":"google/gemini-3.1-flash-lite-20260507","hugging_face_id":null,"name":"Google: Gemini 3.1 Flash Lite (batch)","created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000000125","completion":"0.00000075","image":"0.000000125","audio":"0.00000025","input_audio_cache":"0.000000025","web_search":"0.014","internal_reasoning":"0.00000075","input_cache_read":"0.0000000125"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"},"_prompt_per_m":1.25e-07,"_completion_per_m":7.5e-07,"_image_per_m":1.25e-07,"_request_per_m":null,"_cached_read_per_m":1.25e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | google/gemini-3.1-flash-lite-20260507:batch","model_id":"google/gemini-3.1-flash-lite:batch","model_name":"Google: Gemini 3.1 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.000000125","completion":"0.00000075","image":"0.000000125","audio":"0.00000025","input_audio_cache":"0.000000025","web_search":"0.014","internal_reasoning":"0.00000075","input_cache_read":"0.0000000125","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-07,"_completion_per_m":7.5e-07,"_image_per_m":1.25e-07,"_request_per_m":null,"_cached_read_per_m":1.25e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Google","_cheapest_blended_per_m":3.1249999999999997e-07,"_priciest_blended_per_m":3.1249999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"x-ai/grok-4.3","canonical_slug":"x-ai/grok-4.3-20260430","hugging_face_id":null,"name":"SpaceXAI: Grok 4.3","created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.0000025","web_search":"0.005","input_cache_read":"0.0000002","overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":900000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-4.3-20260430/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1005,"win_rate":28.6,"rank":24},{"arena":"agents","category":"agentichtmlslides","elo":1066,"win_rate":31.8,"rank":10},{"arena":"agents","category":"agenticslides","elo":1072,"win_rate":31.9,"rank":10},{"arena":"agents","category":"agenticslides(html)","elo":1066,"win_rate":31.7,"rank":10},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1068,"win_rate":32.4,"rank":10},{"arena":"agents","category":"androidnative","elo":978,"win_rate":22.1,"rank":36},{"arena":"agents","category":"fullstack","elo":1029,"win_rate":28.9,"rank":38},{"arena":"agents","category":"godotgamedev","elo":1035,"win_rate":31.2,"rank":29},{"arena":"agents","category":"htmlslides","elo":1025,"win_rate":28.7,"rank":22},{"arena":"agents","category":"mobileapps","elo":1101,"win_rate":35.8,"rank":38},{"arena":"agents","category":"pptxslides","elo":1071,"win_rate":32.5,"rank":9},{"arena":"agents","category":"python-pptxslides","elo":1072,"win_rate":30.8,"rank":21},{"arena":"agents","category":"webapps","elo":1160,"win_rate":44.3,"rank":26},{"arena":"models","category":"3d","elo":1168,"win_rate":43.1,"rank":61},{"arena":"models","category":"asciiart","elo":1157,"win_rate":44.5,"rank":41},{"arena":"models","category":"codecategories","elo":1210,"win_rate":46,"rank":47},{"arena":"models","category":"dataviz","elo":1203,"win_rate":46.3,"rank":48},{"arena":"models","category":"gamedev","elo":1209,"win_rate":47.2,"rank":46},{"arena":"models","category":"svg","elo":1126,"win_rate":40.6,"rank":53},{"arena":"models","category":"uicomponent","elo":1218,"win_rate":46.7,"rank":44},{"arena":"models","category":"website","elo":1212,"win_rate":45.7,"rank":50}],"artificial_analysis":{"intelligence_index":37.9,"coding_index":42.2,"agentic_index":24.2}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"low"},"_prompt_per_m":1.25e-06,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"xAI | x-ai/grok-4.3-20260430","model_id":"x-ai/grok-4.3","model_name":"SpaceXAI: Grok 4.3","context_length":1000000,"pricing":{"prompt":"0.00000125","completion":"0.0000025","web_search":"0.005","input_cache_read":"0.0000002","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}]},"provider_name":"xAI","tag":"xai/zdr","quantization":"unknown","max_completion_tokens":900000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.86212734303358,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.3-20260430","model_id":"x-ai/grok-4.3","model_name":"SpaceXAI: Grok 4.3","context_length":1000000,"pricing":{"prompt":"0.0000025","completion":"0.000005","web_search":"0.005","input_cache_read":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000005","completion":"0.00001","input_cache_read":"0.0000008"}]},"provider_name":"xAI","tag":"xai/zdr/priority","quantization":"unknown","max_completion_tokens":900000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.86212734303358,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.3-20260430","model_id":"x-ai/grok-4.3","model_name":"SpaceXAI: Grok 4.3","context_length":1000000,"pricing":{"prompt":"0.00000125","completion":"0.0000025","web_search":"0.005","input_cache_read":"0.0000002","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}]},"provider_name":"xAI","tag":"xai","quantization":"unknown","max_completion_tokens":900000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.93280632411067,"uptime_last_5m":99.87917841320983,"uptime_last_1d":99.92003543045543,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.3-20260430","model_id":"x-ai/grok-4.3","model_name":"SpaceXAI: Grok 4.3","context_length":1000000,"pricing":{"prompt":"0.0000025","completion":"0.000005","web_search":"0.005","input_cache_read":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000005","completion":"0.00001","input_cache_read":"0.0000008"}]},"provider_name":"xAI","tag":"xai/priority","quantization":"unknown","max_completion_tokens":900000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.93280632411067,"uptime_last_5m":99.87917841320983,"uptime_last_1d":99.92003543045543,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":null}],"_cheapest_provider":"xAI","_cheapest_blended_per_m":1.6250000000000001e-06,"_priciest_blended_per_m":3.2500000000000002e-06,"_provider_spread_multiplier":2.0},{"id":"openai/gpt-chat-latest","canonical_slug":"openai/gpt-chat-latest-20260505","hugging_face_id":null,"name":"OpenAI: GPT Chat Latest","created":1778000212,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-chat-latest-20260505/endpoints"},"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-chat-latest-20260505","model_id":"openai/gpt-chat-latest","model_name":"OpenAI: GPT Chat Latest","context_length":400000,"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":1.25e-05,"_priciest_blended_per_m":1.25e-05,"_provider_spread_multiplier":1.0},{"id":"ibm-granite/granite-4.1-8b","canonical_slug":"ibm-granite/granite-4.1-8b-20260429","hugging_face_id":"ibm-granite/granite-4.1-8b","name":"IBM: Granite 4.1 8B","created":1777577071,"description":"Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.0000001","input_cache_read":"0.00000005"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/ibm-granite/granite-4.1-8b-20260429/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":9.5,"agentic_index":null}},"_prompt_per_m":5e-08,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"CoreWeave | ibm-granite/granite-4.1-8b-20260429","model_id":"ibm-granite/granite-4.1-8b","model_name":"IBM: Granite 4.1 8B","context_length":131072,"pricing":{"prompt":"0.00000005","completion":"0.0000001","input_cache_read":"0.00000005","discount":0},"provider_name":"CoreWeave","tag":"coreweave/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"CoreWeave","_cheapest_blended_per_m":6.499999999999999e-08,"_priciest_blended_per_m":6.499999999999999e-08,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-medium-3-5:batch","canonical_slug":"mistralai/mistral-medium-3.5-20260430","hugging_face_id":null,"name":"Mistral: Mistral Medium 3.5 (batch)","created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.00000375"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-medium-3.5-20260430/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":30.4,"coding_index":46.9,"agentic_index":19.2}},"reasoning":{"mandatory":false,"supported_efforts":["high","none"],"default_effort":"high"},"_prompt_per_m":7.5e-07,"_completion_per_m":3.75e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-medium-3.5-20260430:batch","model_id":"mistralai/mistral-medium-3-5:batch","model_name":"Mistral: Mistral Medium 3.5","context_length":262144,"pricing":{"prompt":"0.00000075","completion":"0.00000375","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":3.75e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":1.6499999999999999e-06,"_priciest_blended_per_m":1.6499999999999999e-06,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-medium-3-5","canonical_slug":"mistralai/mistral-medium-3.5-20260430","hugging_face_id":null,"name":"Mistral: Mistral Medium 3.5","created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.0000075"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-medium-3.5-20260430/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":30.4,"coding_index":46.9,"agentic_index":19.2}},"reasoning":{"mandatory":false,"supported_efforts":["high","none"],"default_effort":"high"},"_prompt_per_m":1.5e-06,"_completion_per_m":7.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-medium-3.5-20260430","model_id":"mistralai/mistral-medium-3-5","model_name":"Mistral: Mistral Medium 3.5","context_length":262144,"pricing":{"prompt":"0.0000015","completion":"0.0000075","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.28057553956835,"uptime_last_5m":98.51851851851852,"uptime_last_1d":97.94879923912183,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-06,"_completion_per_m":7.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-medium-3.5-20260430","model_id":"mistralai/mistral-medium-3-5","model_name":"Mistral: Mistral Medium 3.5","context_length":262144,"pricing":{"prompt":"0.0000015","completion":"0.0000075","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.24242424242425,"uptime_last_5m":null,"uptime_last_1d":97.99054373522459,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-06,"_completion_per_m":7.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-medium-3.5-20260430","model_id":"mistralai/mistral-medium-3-5","model_name":"Mistral: Mistral Medium 3.5","context_length":262144,"pricing":{"prompt":"0.00000165","completion":"0.00000825","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.65e-06,"_completion_per_m":8.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":3.2999999999999997e-06,"_priciest_blended_per_m":3.63e-06,"_provider_spread_multiplier":1.1},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","canonical_slug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","hugging_face_id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","name":"NVIDIA: Nemotron 3 Nano Omni (free)","created":1777393095,"description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...","context_length":256000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":13.8,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Nvidia | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428:free","model_id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","model_name":"NVIDIA: Nemotron 3 Nano Omni","context_length":256000,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Nvidia","tag":"nvidia","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p","tool_choice","tools"],"supports_tool_choice":{"none":false,"auto":false,"required":false,"function":false},"status":-2,"uptime_last_30m":85.11961722488039,"uptime_last_5m":86.40552995391705,"uptime_last_1d":81.06628114334035,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Nvidia","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"~anthropic/claude-haiku-latest","canonical_slug":"~anthropic/claude-haiku-latest","alias_target":{"name":"Anthropic: Claude Haiku 4.5","slug":"anthropic/claude-haiku-4.5"},"hugging_face_id":null,"name":"Anthropic Claude Haiku Latest","created":1777318492,"description":"This model always redirects to the latest model in the Anthropic Claude Haiku family.","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~anthropic/claude-haiku-latest/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":2.2e-06,"_priciest_blended_per_m":2.2e-06,"_provider_spread_multiplier":null},{"id":"~openai/gpt-mini-latest","canonical_slug":"~openai/gpt-mini-latest","alias_target":{"name":"OpenAI: GPT-5.4 Mini","slug":"openai/gpt-5.4-mini"},"hugging_face_id":null,"name":"OpenAI GPT Mini Latest","created":1777318471,"description":"This model always redirects to the latest model in the OpenAI GPT Mini family.","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.0000045","web_search":"0.01","input_cache_read":"0.000000075"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-08-31","expiration_date":null,"links":{"details":"/api/v1/models/~openai/gpt-mini-latest/endpoints"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":7.5e-07,"_completion_per_m":4.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":1.8749999999999998e-06,"_priciest_blended_per_m":1.8749999999999998e-06,"_provider_spread_multiplier":null},{"id":"~google/gemini-pro-latest","canonical_slug":"~google/gemini-pro-latest","alias_target":{"name":"Google: Gemini 3.1 Pro Preview","slug":"google/gemini-3.1-pro-preview"},"hugging_face_id":null,"name":"Google Gemini Pro Latest","created":1777318451,"description":"This model always redirects to the latest model in the Google Gemini Pro family.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000018","audio":"0.000004","input_audio_cache":"0.0000004","input_cache_read":"0.0000004"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~google/gemini-pro-latest/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":4.9999999999999996e-06,"_priciest_blended_per_m":4.9999999999999996e-06,"_provider_spread_multiplier":null},{"id":"~moonshotai/kimi-latest","canonical_slug":"~moonshotai/kimi-latest","alias_target":{"name":"MoonshotAI: Kimi K3","slug":"moonshotai/kimi-k3"},"hugging_face_id":null,"name":"MoonshotAI Kimi Latest","created":1777318428,"description":"This model always redirects to the latest model in the MoonshotAI Kimi family.","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.00000255","completion":"0.00001275","input_cache_read":"0.00000025599999"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~moonshotai/kimi-latest/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"_prompt_per_m":2.55e-06,"_completion_per_m":1.275e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5599999e-07,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":5.61e-06,"_priciest_blended_per_m":5.61e-06,"_provider_spread_multiplier":null},{"id":"~google/gemini-flash-latest","canonical_slug":"~google/gemini-flash-latest","alias_target":{"name":"Google: Gemini 3.7 Flash","slug":"google/gemini-3.7-flash"},"hugging_face_id":null,"name":"Google Gemini Flash Latest","created":1777318398,"description":"This model always redirects to the latest model in the Google Gemini Flash family.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","web_search":"0.014","internal_reasoning":"0.000001875","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~google/gemini-flash-latest/endpoints"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":3.75e-07,"_completion_per_m":1.875e-06,"_image_per_m":3.75e-07,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":2.08333333333333e-08,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":8.249999999999999e-07,"_priciest_blended_per_m":8.249999999999999e-07,"_provider_spread_multiplier":null},{"id":"~anthropic/claude-sonnet-latest","canonical_slug":"~anthropic/claude-sonnet-latest","alias_target":{"name":"Anthropic: Claude Sonnet 5","slug":"anthropic/claude-sonnet-5"},"hugging_face_id":null,"name":"Anthropic Claude Sonnet Latest","created":1777318368,"description":"This model always redirects to the latest model in the Anthropic Claude Sonnet family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~anthropic/claude-sonnet-latest/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":4.4e-06,"_priciest_blended_per_m":4.4e-06,"_provider_spread_multiplier":null},{"id":"~openai/gpt-latest","canonical_slug":"~openai/gpt-latest","alias_target":{"name":"OpenAI: GPT-5.6 Sol","slug":"openai/gpt-5.6-sol"},"hugging_face_id":null,"name":"OpenAI GPT Latest","created":1777318334,"description":"This model always redirects to the latest model in the OpenAI GPT family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/~openai/gpt-latest/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":2.5e-06,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":4.4e-06,"_priciest_blended_per_m":4.4e-06,"_provider_spread_multiplier":null},{"id":"qwen/qwen3.5-plus-20260420","canonical_slug":"qwen/qwen3.5-plus-20260420","hugging_face_id":null,"name":"Qwen: Qwen3.5 Plus 2026-04-20","created":1777261368,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000018","input_cache_write":"0.000000375","overrides":[{"min_prompt_tokens":256000,"prompt":"0.000000375","completion":"0.00000225","input_cache_write":"0.00000046875"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-plus-20260420/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":3e-07,"_completion_per_m":1.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":3.75e-07,"_endpoints":[{"name":"Alibaba | qwen/qwen3.5-plus-20260420","model_id":"qwen/qwen3.5-plus-20260420","model_name":"Qwen: Qwen3.5 Plus 2026-04-20","context_length":1000000,"pricing":{"prompt":"0.0000003","completion":"0.0000018","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.000000375","completion":"0.00000225","input_cache_write":"0.00000046875"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":3.75e-07}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":7.499999999999999e-07,"_priciest_blended_per_m":7.499999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.6-35b-a3b","canonical_slug":"qwen/qwen3.6-35b-a3b-20260415","hugging_face_id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen: Qwen3.6 35B A3B","created":1777260255,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000009","input_cache_read":"0.00000005"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-35b-a3b-20260415/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":32.1,"coding_index":41.9,"agentic_index":21.6}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":1e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Darkbloom | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":262144,"pricing":{"prompt":"0.00000005","completion":"0.0000007","discount":0},"provider_name":"Darkbloom","tag":"darkbloom/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.49164851125636,"uptime_last_5m":99.85549132947978,"uptime_last_1d":99.41983254971966,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"AkashML | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.0000009","input_cache_read":"0.00000005","discount":0},"provider_name":"AkashML","tag":"akashml/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.10688140556368,"uptime_last_5m":98.62313139260425,"uptime_last_1d":99.53611306931796,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.00000095","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.45283018867926,"uptime_last_5m":91.22257053291536,"uptime_last_1d":96.60486750302991,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":9.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":256000,"pricing":{"prompt":"0.0000001","completion":"0.000001","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":97.55590118569091,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.000001","input_cache_read":"0.00000005","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.89453701750686,"uptime_last_5m":100,"uptime_last_1d":99.65380034896924,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"AtlasCloud | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":262144,"pricing":{"prompt":"0.000000186","completion":"0.00000111375","input_cache_read":"0.000000186","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":98.58227848101265,"uptime_last_5m":98.74371859296483,"uptime_last_1d":99.82965009208104,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.86e-07,"_completion_per_m":1.11375e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.86e-07,"_cached_write_per_m":null},{"name":"Io Net | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":262140,"pricing":{"prompt":"0.00000019","completion":"0.00000119","input_cache_read":"0.00000009","discount":0},"provider_name":"Io Net","tag":"io-net/fp8","quantization":"fp8","max_completion_tokens":235926,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":83.87358184764992,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.9e-07,"_completion_per_m":1.19e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9e-08,"_cached_write_per_m":null},{"name":"Phala | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.00000127","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","tools","logprobs","top_logprobs","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.72602739726028,"uptime_last_5m":100,"uptime_last_1d":99.62009563109976,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.27e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.0000016","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":90.88319088319088,"uptime_last_5m":86.56716417910447,"uptime_last_1d":86.25568968929349,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"CoreWeave | qwen/qwen3.6-35b-a3b-20260415","model_id":"qwen/qwen3.6-35b-a3b","model_name":"Qwen: Qwen3.6 35B A3B","context_length":262144,"pricing":{"prompt":"0.00000025","completion":"0.00000125","input_cache_read":"0.00000025","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.93622448979592,"uptime_last_5m":99.77220956719817,"uptime_last_1d":99.9386195868129,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Darkbloom","_cheapest_blended_per_m":2.45e-07,"_priciest_blended_per_m":6.2e-07,"_provider_spread_multiplier":2.5306122448979593},{"id":"qwen/qwen3.6-flash","canonical_slug":"qwen/qwen3.6-flash","hugging_face_id":null,"name":"Qwen: Qwen3.6 Flash","created":1777261362,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000001875","completion":"0.000001125","input_cache_write":"0.000000234375","overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000075","completion":"0.000003","input_cache_write":"0.0000009375"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-flash/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1.875e-07,"_completion_per_m":1.125e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":2.34375e-07,"_endpoints":[{"name":"Alibaba | qwen/qwen3.6-flash","model_id":"qwen/qwen3.6-flash","model_name":"Qwen: Qwen3.6 Flash","context_length":1000000,"pricing":{"prompt":"0.0000001875","completion":"0.000001125","input_cache_write":"0.000000234375","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000075","completion":"0.000003","input_cache_write":"0.0000009375"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.875e-07,"_completion_per_m":1.125e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":2.34375e-07}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":4.6874999999999996e-07,"_priciest_blended_per_m":4.6874999999999996e-07,"_provider_spread_multiplier":1.0},{"id":"perceptron/perceptron-mk1","canonical_slug":"perceptron/perceptron-mk1-20260512","hugging_face_id":null,"name":"Perceptron: Perceptron Mk1","created":1778597029,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","context_length":32768,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000015"},"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/perceptron/perceptron-mk1-20260512/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Perceptron | perceptron/perceptron-mk1-20260512","model_id":"perceptron/perceptron-mk1","model_name":"Perceptron: Perceptron Mk1","context_length":32768,"pricing":{"prompt":"0.00000015","completion":"0.0000015","discount":0},"provider_name":"Perceptron","tag":"perceptron","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Perceptron","_cheapest_blended_per_m":5.55e-07,"_priciest_blended_per_m":5.55e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.6-max-preview","canonical_slug":"qwen/qwen3.6-max-preview-20260420","hugging_face_id":null,"name":"Qwen: Qwen3.6 Max Preview","created":1777260242,"description":"Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000001027","completion":"0.000006162","input_cache_write":"0.00000128375","overrides":[{"min_prompt_tokens":128000,"prompt":"0.00000158","completion":"0.00000948","input_cache_write":"0.000001975"}]},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-max-preview-20260420/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":1.027e-06,"_completion_per_m":6.162e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":1.28375e-06,"_endpoints":[{"name":"Alibaba | qwen/qwen3.6-max-preview-20260420","model_id":"qwen/qwen3.6-max-preview","model_name":"Qwen: Qwen3.6 Max Preview","context_length":262144,"pricing":{"prompt":"0.000001027","completion":"0.000006162","input_cache_write":"0.00000128375","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.00000158","completion":"0.00000948","input_cache_write":"0.000001975"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":229376,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_logprobs","logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.027e-06,"_completion_per_m":6.162e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":1.28375e-06}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":2.5674999999999996e-06,"_priciest_blended_per_m":2.5674999999999996e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.6-27b","canonical_slug":"qwen/qwen3.6-27b-20260422","hugging_face_id":"Qwen/Qwen3.6-27B","name":"Qwen: Qwen3.6 27B","created":1777255064,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000036","input_cache_read":"0.00000012"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-27b-20260422/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":37.7,"coding_index":53.7,"agentic_index":27.5}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":6e-07,"_completion_per_m":3.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Chutes | qwen/qwen3.6-27b-20260422","model_id":"qwen/qwen3.6-27b","model_name":"Qwen: Qwen3.6 27B","context_length":262144,"pricing":{"prompt":"0.0000003","completion":"0.000002","input_cache_read":"0.00000003","discount":0},"provider_name":"Chutes","tag":"chutes/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":70.53941908713693,"uptime_last_5m":null,"uptime_last_1d":88.09434367285607,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3.6-27b-20260422","model_id":"qwen/qwen3.6-27b","model_name":"Qwen: Qwen3.6 27B","context_length":262144,"pricing":{"prompt":"0.0000003","completion":"0.0000032","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.0105411103303,"uptime_last_5m":94.00749063670412,"uptime_last_1d":93.07171130916244,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Phala | qwen/qwen3.6-27b-20260422","model_id":"qwen/qwen3.6-27b","model_name":"Qwen: Qwen3.6 27B","context_length":262144,"pricing":{"prompt":"0.00000032","completion":"0.0000027","input_cache_read":"0.00000015","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":262140,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-5,"uptime_last_30m":18.69158878504673,"uptime_last_5m":null,"uptime_last_1d":82.7721375093097,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.2e-07,"_completion_per_m":2.7e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3.6-27b-20260422","model_id":"qwen/qwen3.6-27b","model_name":"Qwen: Qwen3.6 27B","context_length":262144,"pricing":{"prompt":"0.00000032","completion":"0.0000032","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":81920,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.83822042467139,"uptime_last_5m":99.81203007518798,"uptime_last_1d":98.36784166569811,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.2e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3.6-27b-20260422","model_id":"qwen/qwen3.6-27b","model_name":"Qwen: Qwen3.6 27B","context_length":256000,"pricing":{"prompt":"0.000000325","completion":"0.00000325","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tool_choice","tools","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.9829960891005,"uptime_last_5m":100,"uptime_last_1d":96.09886643023432,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.25e-07,"_completion_per_m":3.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3.6-27b-20260422","model_id":"qwen/qwen3.6-27b","model_name":"Qwen: Qwen3.6 27B","context_length":262144,"pricing":{"prompt":"0.00000045","completion":"0.0000027","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":258048,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_logprobs","logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.90475056554352,"uptime_last_5m":100,"uptime_last_1d":99.86997586125943,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":2.7e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"CoreWeave | qwen/qwen3.6-27b-20260422","model_id":"qwen/qwen3.6-27b","model_name":"Qwen: Qwen3.6 27B","context_length":262144,"pricing":{"prompt":"0.0000006","completion":"0.0000036","input_cache_read":"0.00000012","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","tools","structured_outputs","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97327632282203,"uptime_last_5m":100,"uptime_last_1d":99.77904040404042,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":3.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Chutes","_cheapest_blended_per_m":8.1e-07,"_priciest_blended_per_m":1.4999999999999998e-06,"_provider_spread_multiplier":1.8518518518518516},{"id":"openai/gpt-5.5","canonical_slug":"openai/gpt-5.5-20260423","hugging_face_id":"","name":"OpenAI: GPT-5.5","created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-12-01","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.5-20260423/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1179,"win_rate":52.4,"rank":14},{"arena":"agents","category":"agentichtmlslides","elo":1084,"win_rate":34.2,"rank":9},{"arena":"agents","category":"agenticslides","elo":1150,"win_rate":43.5,"rank":7},{"arena":"agents","category":"agenticslides(html)","elo":1077,"win_rate":33.2,"rank":9},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1155,"win_rate":45.2,"rank":7},{"arena":"agents","category":"androidnative","elo":1185,"win_rate":50.9,"rank":20},{"arena":"agents","category":"fullstack","elo":1113,"win_rate":43,"rank":27},{"arena":"agents","category":"godotgamedev","elo":1212,"win_rate":52.4,"rank":10},{"arena":"agents","category":"htmlslides","elo":1081,"win_rate":35.7,"rank":21},{"arena":"agents","category":"mobileapps","elo":1192,"win_rate":51.6,"rank":22},{"arena":"agents","category":"pptxslides","elo":1157,"win_rate":45.3,"rank":7},{"arena":"agents","category":"python-pptxslides","elo":1152,"win_rate":43.3,"rank":19},{"arena":"agents","category":"webapps","elo":1147,"win_rate":42.6,"rank":29},{"arena":"models","category":"3d","elo":1242,"win_rate":51.8,"rank":36},{"arena":"models","category":"asciiart","elo":1286,"win_rate":61.2,"rank":9},{"arena":"models","category":"codecategories","elo":1283,"win_rate":55,"rank":24},{"arena":"models","category":"dataviz","elo":1282,"win_rate":56.9,"rank":19},{"arena":"models","category":"gamedev","elo":1336,"win_rate":59.8,"rank":8},{"arena":"models","category":"svg","elo":1273,"win_rate":57.9,"rank":6},{"arena":"models","category":"uicomponent","elo":1281,"win_rate":55.2,"rank":26},{"arena":"models","category":"website","elo":1276,"win_rate":54,"rank":26}],"artificial_analysis":{"intelligence_index":56.3,"coding_index":74.9,"agentic_index":47.4}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.5-20260423","model_id":"openai/gpt-5.5","model_name":"OpenAI: GPT-5.5","context_length":1050000,"pricing":{"prompt":"0.0000025","completion":"0.000015","web_search":"0.01","input_cache_read":"0.00000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000005","completion":"0.0000225","input_cache_read":"0.0000005"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.5-20260423","model_id":"openai/gpt-5.5","model_name":"OpenAI: GPT-5.5","context_length":1050000,"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001"}]},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.95600527936648,"uptime_last_5m":99.89047097480832,"uptime_last_1d":99.95545404477272,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.5-20260423","model_id":"openai/gpt-5.5","model_name":"OpenAI: GPT-5.5","context_length":1050000,"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.67664145566152,"uptime_last_5m":99.46488294314382,"uptime_last_1d":99.46559594197899,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.5-20260423","model_id":"openai/gpt-5.5","model_name":"OpenAI: GPT-5.5","context_length":1050000,"pricing":{"prompt":"0.0000055","completion":"0.000033","web_search":"0.01","input_cache_read":"0.00000055","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000011","completion":"0.0000495","input_cache_read":"0.0000011"}]},"provider_name":"Azure","tag":"azure/eu","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":3.3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.5-20260423","model_id":"openai/gpt-5.5","model_name":"OpenAI: GPT-5.5","context_length":1050000,"pricing":{"prompt":"0.0000055","completion":"0.000033","web_search":"0.01","input_cache_read":"0.00000055","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000011","completion":"0.0000495","input_cache_read":"0.0000011"}]},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.93679886237953,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":3.3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null},{"name":"Amazon Bedrock | openai/gpt-5.5-20260423","model_id":"openai/gpt-5.5","model_name":"OpenAI: GPT-5.5","context_length":1050000,"pricing":{"prompt":"0.0000055","completion":"0.000033","web_search":"0.01","input_cache_read":"0.00000055","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000011","completion":"0.0000495","input_cache_read":"0.0000011"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us-east-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":3.3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.5-20260423","model_id":"openai/gpt-5.5","model_name":"OpenAI: GPT-5.5","context_length":1050000,"pricing":{"prompt":"0.0000125","completion":"0.000075","web_search":"0.01","input_cache_read":"0.00000125","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000025","completion":"0.0001125","input_cache_read":"0.0000025"}]},"provider_name":"OpenAI","tag":"openai/fast","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.79231568016614,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-05,"_completion_per_m":7.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":6.25e-06,"_priciest_blended_per_m":3.125e-05,"_provider_spread_multiplier":5.0},{"id":"openai/gpt-5.5-pro","canonical_slug":"openai/gpt-5.5-pro-20260423","hugging_face_id":"","name":"OpenAI: GPT-5.5 Pro","created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00003","completion":"0.00018","web_search":"0.01","overrides":[{"min_prompt_tokens":272000,"prompt":"0.00006","completion":"0.00027"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-12-01","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"_prompt_per_m":3e-05,"_completion_per_m":0.00018,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.5-pro-20260423","model_id":"openai/gpt-5.5-pro","model_name":"OpenAI: GPT-5.5 Pro","context_length":1050000,"pricing":{"prompt":"0.000015","completion":"0.00009","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00003","completion":"0.000135"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-05,"_completion_per_m":9e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.5-pro-20260423","model_id":"openai/gpt-5.5-pro","model_name":"OpenAI: GPT-5.5 Pro","context_length":1050000,"pricing":{"prompt":"0.00003","completion":"0.00018","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00006","completion":"0.00027"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-05,"_completion_per_m":0.00018,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":3.7500000000000003e-05,"_priciest_blended_per_m":7.500000000000001e-05,"_provider_spread_multiplier":2.0},{"id":"deepseek/deepseek-v4-pro","canonical_slug":"deepseek/deepseek-v4-pro-20260423","hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek: DeepSeek V4 Pro 0423","created":1777000679,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000087","completion":"0.00000174","input_cache_read":"0.0000000725"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":1},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"fullstack","elo":948,"win_rate":22.1,"rank":41},{"arena":"agents","category":"godotgamedev","elo":1059,"win_rate":34,"rank":27},{"arena":"agents","category":"webapps","elo":1000,"win_rate":26.4,"rank":37},{"arena":"models","category":"3d","elo":1300,"win_rate":57.6,"rank":16},{"arena":"models","category":"asciiart","elo":1177,"win_rate":46.6,"rank":33},{"arena":"models","category":"codecategories","elo":1266,"win_rate":52.7,"rank":31},{"arena":"models","category":"dataviz","elo":1220,"win_rate":48.4,"rank":44},{"arena":"models","category":"gamedev","elo":1269,"win_rate":54,"rank":28},{"arena":"models","category":"svg","elo":1176,"win_rate":45.6,"rank":42},{"arena":"models","category":"uicomponent","elo":1249,"win_rate":51,"rank":36},{"arena":"models","category":"website","elo":1255,"win_rate":51.2,"rank":35}],"artificial_analysis":{"intelligence_index":45.3,"coding_index":59.4,"agentic_index":37.8}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high"],"default_effort":"high"},"_prompt_per_m":8.7e-07,"_completion_per_m":1.74e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.25e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.000000792","completion":"0.000002376","input_cache_read":"0.0000000264","discount":0.4},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":97.63706204167151,"uptime_last_5m":98.86680613668062,"uptime_last_1d":98.18077053373435,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.92e-07,"_completion_per_m":2.376e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.64e-08,"_cached_write_per_m":null},{"name":"StreamLake | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1024000,"pricing":{"prompt":"0.00000087","completion":"0.00000174","input_cache_read":"0.0000000725","discount":0.5},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","response_format","logprobs","top_logprobs","structured_outputs","max_tokens","temperature","top_p","stop","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.44111709848016,"uptime_last_5m":98.84653410963419,"uptime_last_1d":99.74442987147285,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.7e-07,"_completion_per_m":1.74e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.25e-08,"_cached_write_per_m":null},{"name":"Ionstream | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.000001131","completion":"0.000002262","input_cache_read":"0.000000094","discount":0},"provider_name":"Ionstream","tag":"ionstream/fp4","quantization":"fp4","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.75924333619949,"uptime_last_5m":99.62453066332915,"uptime_last_1d":99.52952584465375,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.131e-06,"_completion_per_m":2.262e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9.4e-08,"_cached_write_per_m":null},{"name":"CoreWeave | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000115","completion":"0.00000255","input_cache_read":"0.0000002","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.91902834008097,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.15e-06,"_completion_per_m":2.55e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"DeepInfra | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.0000013","completion":"0.0000026","input_cache_read":"0.0000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.89171629669734,"uptime_last_5m":100,"uptime_last_1d":99.39937076937744,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-06,"_completion_per_m":2.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Alibaba | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1000000,"pricing":{"prompt":"0.000001416","completion":"0.000002832","input_cache_read":"0.000000118","discount":0},"provider_name":"Alibaba","tag":"alibaba/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":1000000,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.97620464009518,"uptime_last_5m":100,"uptime_last_1d":99.99842476450229,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.416e-06,"_completion_per_m":2.832e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.18e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000150162","completion":"0.000003135","input_cache_read":"0.000000135","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.780526735834,"uptime_last_5m":99.68992248062015,"uptime_last_1d":99.84721555891795,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.50162e-06,"_completion_per_m":3.135e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":null},{"name":"Novita | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.0000016","completion":"0.0000032","input_cache_read":"0.000000135","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.99181714036331,"uptime_last_5m":100,"uptime_last_1d":99.9266929567708,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.6e-06,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":null},{"name":"Venice | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1000000,"pricing":{"prompt":"0.00000165","completion":"0.000003301","input_cache_read":"0.00000033","discount":0},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.91130820399114,"uptime_last_5m":100,"uptime_last_1d":94.2620636239683,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.65e-06,"_completion_per_m":3.301e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-07,"_cached_write_per_m":null},{"name":"AtlasCloud | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000168","completion":"0.00000338","input_cache_read":"0.00000013","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp4","quantization":"fp4","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","tools","structured_outputs","response_format","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.01015228426397,"uptime_last_5m":99.39516129032258,"uptime_last_1d":99.33262711864407,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.68e-06,"_completion_per_m":3.38e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null},{"name":"Baidu | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000169","completion":"0.00000338","input_cache_read":"0.00000014","discount":0},"provider_name":"Baidu","tag":"baidu/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":98.7301439870127,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.69e-06,"_completion_per_m":3.38e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"NextBit | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000172","completion":"0.00000345","input_cache_read":"0.00000014","discount":0},"provider_name":"NextBit","tag":"nextbit/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.1981981981982,"uptime_last_5m":98.85057471264368,"uptime_last_1d":95.1053457820375,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.72e-06,"_completion_per_m":3.45e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"BaseTen | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000174","completion":"0.00000348","input_cache_read":"0.000000145","discount":0},"provider_name":"BaseTen","tag":"baseten/fp4","quantization":"fp4","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.4328922495274,"uptime_last_5m":96.63865546218487,"uptime_last_1d":99.93354156974812,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.74e-06,"_completion_per_m":3.48e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.45e-07,"_cached_write_per_m":null},{"name":"Fireworks | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000174","completion":"0.00000348","input_cache_read":"0.000000145","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":0,"uptime_last_5m":null,"uptime_last_1d":21.21966397013068,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.74e-06,"_completion_per_m":3.48e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.45e-07,"_cached_write_per_m":null},{"name":"Parasail | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000174","completion":"0.00000348","input_cache_read":"0.0000001","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":98.0368896196989,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.74e-06,"_completion_per_m":3.48e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000174","completion":"0.00000348","input_cache_read":"0.000000348","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","tool_choice","tools","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.90709197894085,"uptime_last_5m":99.80952380952381,"uptime_last_1d":99.83449400075406,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.74e-06,"_completion_per_m":3.48e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.48e-07,"_cached_write_per_m":null},{"name":"Azure | deepseek/deepseek-v4-pro-20260423","model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek: DeepSeek V4 Pro 0423","context_length":1048576,"pricing":{"prompt":"0.00000191","completion":"0.00000383","input_cache_read":"0.00000016","discount":0},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.05962008651495,"uptime_last_5m":98.53747714808044,"uptime_last_1d":99.0577392823006,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.91e-06,"_completion_per_m":3.83e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null}],"_cheapest_provider":"StreamLake","_cheapest_blended_per_m":1.131e-06,"_priciest_blended_per_m":2.4859999999999996e-06,"_provider_spread_multiplier":2.1980548187444735},{"id":"deepseek/deepseek-v4-flash","canonical_slug":"deepseek/deepseek-v4-flash-20260423","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek: DeepSeek V4 Flash 0423","created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.000000088606","completion":"0.000000177212","input_cache_read":"0.0000000177212"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1232,"win_rate":49.3,"rank":40},{"arena":"models","category":"asciiart","elo":1137,"win_rate":42.8,"rank":47},{"arena":"models","category":"codecategories","elo":1230,"win_rate":48.9,"rank":42},{"arena":"models","category":"dataviz","elo":1147,"win_rate":40.6,"rank":74},{"arena":"models","category":"gamedev","elo":1233,"win_rate":50.2,"rank":39},{"arena":"models","category":"svg","elo":1194,"win_rate":48.4,"rank":32},{"arena":"models","category":"uicomponent","elo":1190,"win_rate":44.7,"rank":58},{"arena":"models","category":"website","elo":1227,"win_rate":49.1,"rank":43}],"artificial_analysis":{"intelligence_index":42.1,"coding_index":56.2,"agentic_index":33.7}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high"],"default_effort":"high"},"_prompt_per_m":8.8606e-08,"_completion_per_m":1.77212e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.77212e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"StreamLake | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1024000,"pricing":{"prompt":"0.000000088606","completion":"0.000000177212","input_cache_read":"0.0000000177212","discount":0.3671},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","tools","tool_choice","logprobs","top_logprobs","structured_outputs","max_tokens","temperature","top_p","stop","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.90429178823544,"uptime_last_5m":99.88330537524615,"uptime_last_1d":99.95622499716653,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.8606e-08,"_completion_per_m":1.77212e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.77212e-08,"_cached_write_per_m":null},{"name":"DeepInfra | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000009","completion":"0.00000018","input_cache_read":"0.000000018","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.13191476711086,"uptime_last_5m":99.32519874283602,"uptime_last_1d":99.39850566168063,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":1.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.8e-08,"_cached_write_per_m":null},{"name":"GMICloud | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048575,"pricing":{"prompt":"0.000000112","completion":"0.000000224","input_cache_read":"0.0000000224","discount":0.2},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":943717,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":96.04554186384294,"uptime_last_5m":95.40242319342276,"uptime_last_1d":97.41689723083793,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.12e-07,"_completion_per_m":2.24e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.24e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000013","completion":"0.00000028","input_cache_read":"0.000000028","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":98.46179851250845,"uptime_last_5m":99.44033579852089,"uptime_last_1d":98.93341565700595,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"Alibaba | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1000000,"pricing":{"prompt":"0.000000134","completion":"0.000000268","input_cache_read":"0.0000000268","discount":0},"provider_name":"Alibaba","tag":"alibaba/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":1000000,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.86094642664655,"uptime_last_5m":99.89063489322511,"uptime_last_1d":99.81421813160381,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.34e-07,"_completion_per_m":2.68e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.68e-08,"_cached_write_per_m":null},{"name":"Venice | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1000000,"pricing":{"prompt":"0.000000138","completion":"0.000000275","input_cache_read":"0.000000028","discount":0},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.44280824643795,"uptime_last_5m":99.39744516751024,"uptime_last_1d":99.55216249278325,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.38e-07,"_completion_per_m":2.75e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"Novita | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.000000028","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tool_choice","tools","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.98520625889047,"uptime_last_5m":99.99324826142731,"uptime_last_1d":99.5826914685967,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"NextBit | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.000000028","discount":0},"provider_name":"NextBit","tag":"nextbit/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.9192625556262,"uptime_last_5m":98.70477891916035,"uptime_last_1d":98.60546876873563,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"AtlasCloud | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.000000028","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp4","quantization":"fp4","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":99.85282368277197,"uptime_last_5m":99.99128919860627,"uptime_last_1d":99.85155960765466,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"Baidu | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.000000028","discount":0},"provider_name":"Baidu","tag":"baidu/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.96568291008923,"uptime_last_5m":100,"uptime_last_1d":99.22920060682658,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"CoreWeave | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.00000007","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.95452561117578,"uptime_last_5m":99.95417048579284,"uptime_last_1d":99.70787476797841,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"DigitalOcean | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.000000028","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","tool_choice","tools","structured_outputs","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":99.95836995235672,"uptime_last_5m":99.9715424018213,"uptime_last_1d":99.74525526134487,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"Parasail | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.00000007","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","structured_outputs","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.74411764705883,"uptime_last_5m":99.7758685095256,"uptime_last_1d":99.67553939516793,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"Mancer 2 | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000016","completion":"0.00000045","discount":0},"provider_name":"Mancer 2","tag":"mancer/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","response_format","logprobs","top_logprobs","tools","structured_outputs","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.23531810766721,"uptime_last_5m":99.25158318940703,"uptime_last_1d":98.91062234502233,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.6e-07,"_completion_per_m":4.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Phala | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.0000002","completion":"0.0000004","input_cache_read":"0.00000007","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":393216,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8720175518786,"uptime_last_5m":99.923925446938,"uptime_last_1d":99.64408196386636,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"Azure | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":1048576,"pricing":{"prompt":"0.00000021","completion":"0.00000056","input_cache_read":"0.000000031","discount":0},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":384000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":69.48933419521654,"uptime_last_5m":83.87096774193549,"uptime_last_1d":88.69926427358693,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-07,"_completion_per_m":5.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.1e-08,"_cached_write_per_m":null},{"name":"Cloudflare | deepseek/deepseek-v4-flash-20260423","model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek: DeepSeek V4 Flash 0423","context_length":384000,"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":345600,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","structured_outputs","tool_choice","tools","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.98342587221347,"uptime_last_5m":99.9742334449884,"uptime_last_1d":99.98368655819004,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":1.32e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-08,"_cached_write_per_m":null}],"_cheapest_provider":"StreamLake","_cheapest_blended_per_m":1.151878e-07,"_priciest_blended_per_m":7.04e-07,"_provider_spread_multiplier":6.1117583632988906},{"id":"tencent/hy3-preview","canonical_slug":"tencent/hy3-preview-20260421","hugging_face_id":"tencent/Hy3-preview","name":"Tencent: Hy3 preview","created":1776878150,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000018","completion":"0.0000006","input_cache_read":"0.00000006"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy3-preview-20260421/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":42.2,"coding_index":58.8,"agentic_index":31.4}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"_prompt_per_m":1.8e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | tencent/hy3-preview-20260421","model_id":"tencent/hy3-preview","model_name":"Tencent: Hy3 preview","context_length":262144,"pricing":{"prompt":"0.00000018","completion":"0.0000006","input_cache_read":"0.00000006","discount":0},"provider_name":"GMICloud","tag":"gmicloud/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99119658698449,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.8e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":3.06e-07,"_priciest_blended_per_m":3.06e-07,"_provider_spread_multiplier":1.0},{"id":"xiaomi/mimo-v2.5-pro","canonical_slug":"xiaomi/mimo-v2.5-pro-20260422","hugging_face_id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"Xiaomi: MiMo-V2.5-Pro","created":1776874273,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","context_length":1050000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000435","completion":"0.00000087","input_cache_read":"0.0000000036"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.5-pro-20260422/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1293,"win_rate":56,"rank":21},{"arena":"models","category":"asciiart","elo":1179,"win_rate":47.5,"rank":29},{"arena":"models","category":"codecategories","elo":1297,"win_rate":54.9,"rank":18},{"arena":"models","category":"dataviz","elo":1284,"win_rate":52.5,"rank":18},{"arena":"models","category":"gamedev","elo":1301,"win_rate":56.1,"rank":17},{"arena":"models","category":"svg","elo":1222,"win_rate":51,"rank":22},{"arena":"models","category":"uicomponent","elo":1289,"win_rate":55.2,"rank":23},{"arena":"models","category":"website","elo":1295,"win_rate":54.4,"rank":15}],"artificial_analysis":{"intelligence_index":42.9,"coding_index":60.2,"agentic_index":29.5}},"reasoning":{"mandatory":false},"_prompt_per_m":4.35e-07,"_completion_per_m":8.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.6e-09,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | xiaomi/mimo-v2.5-pro-20260422","model_id":"xiaomi/mimo-v2.5-pro","model_name":"Xiaomi: MiMo-V2.5-Pro","context_length":1050000,"pricing":{"prompt":"0.0000003045","completion":"0.000000609","input_cache_read":"0.0000000028","discount":0.3},"provider_name":"GMICloud","tag":"gmicloud/bf16","quantization":"bf16","max_completion_tokens":945000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format"],"supports_tool_choice":{"none":false,"auto":false,"required":false,"function":false},"status":-5,"uptime_last_30m":38.16793893129771,"uptime_last_5m":null,"uptime_last_1d":64.28837555886736,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.045e-07,"_completion_per_m":6.09e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-09,"_cached_write_per_m":null},{"name":"DeepInfra | xiaomi/mimo-v2.5-pro-20260422","model_id":"xiaomi/mimo-v2.5-pro","model_name":"Xiaomi: MiMo-V2.5-Pro","context_length":1048576,"pricing":{"prompt":"0.00000039","completion":"0.00000117","input_cache_read":"0.000000078","discount":0.61},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.89183342347215,"uptime_last_5m":100,"uptime_last_1d":98.89188345112373,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.9e-07,"_completion_per_m":1.17e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.8e-08,"_cached_write_per_m":null},{"name":"Xiaomi | xiaomi/mimo-v2.5-pro-20260422","model_id":"xiaomi/mimo-v2.5-pro","model_name":"Xiaomi: MiMo-V2.5-Pro","context_length":1048576,"pricing":{"prompt":"0.000000435","completion":"0.00000087","input_cache_read":"0.0000000036","discount":0},"provider_name":"Xiaomi","tag":"xiaomi/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":false},"status":-2,"uptime_last_30m":94.82999917675146,"uptime_last_5m":95.85492227979275,"uptime_last_1d":98.37857328130478,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.35e-07,"_completion_per_m":8.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.6e-09,"_cached_write_per_m":null},{"name":"AtlasCloud | xiaomi/mimo-v2.5-pro-20260422","model_id":"xiaomi/mimo-v2.5-pro","model_name":"Xiaomi: MiMo-V2.5-Pro","context_length":1024000,"pricing":{"prompt":"0.000000435","completion":"0.00000087","input_cache_read":"0.0000000036","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":96.73469387755102,"uptime_last_5m":94.5054945054945,"uptime_last_1d":97.52914217395636,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.35e-07,"_completion_per_m":8.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.6e-09,"_cached_write_per_m":null},{"name":"Novita | xiaomi/mimo-v2.5-pro-20260422","model_id":"xiaomi/mimo-v2.5-pro","model_name":"Xiaomi: MiMo-V2.5-Pro","context_length":1048576,"pricing":{"prompt":"0.00000048024","completion":"0.00000096048","input_cache_read":"0.000000003956","discount":0.08},"provider_name":"Novita","tag":"novita","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.47637566218575,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.8024e-07,"_completion_per_m":9.6048e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.956e-09,"_cached_write_per_m":null},{"name":"StreamLake | xiaomi/mimo-v2.5-pro-20260422","model_id":"xiaomi/mimo-v2.5-pro","model_name":"Xiaomi: MiMo-V2.5-Pro","context_length":1000000,"pricing":{"prompt":"0.000000522","completion":"0.000001044","input_cache_read":"0.00000000432","discount":-0.2},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","tools","tool_choice","max_tokens","temperature","top_p","stop"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":93.43205399415734,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.22e-07,"_completion_per_m":1.044e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.32e-09,"_cached_write_per_m":null},{"name":"DigitalOcean | xiaomi/mimo-v2.5-pro-20260422","model_id":"xiaomi/mimo-v2.5-pro","model_name":"Xiaomi: MiMo-V2.5-Pro","context_length":262144,"pricing":{"prompt":"0.0000008","completion":"0.000003","input_cache_read":"0.00000016","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.84383133784488,"uptime_last_5m":100,"uptime_last_1d":99.58291800010493,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":3.9585e-07,"_priciest_blended_per_m":1.46e-06,"_provider_spread_multiplier":3.6882657572312745},{"id":"~anthropic/claude-opus-latest","canonical_slug":"~anthropic/claude-opus-latest","alias_target":{"name":"Claude Opus 5","slug":"anthropic/claude-opus-5"},"hugging_face_id":"","name":"Anthropic: Claude Opus Latest","created":1776795361,"description":"This model always redirects to the latest model in the Claude Opus family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~anthropic/claude-opus-latest/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":1.1e-05,"_priciest_blended_per_m":1.1e-05,"_provider_spread_multiplier":null},{"id":"openai/gpt-5.4-image-2","canonical_slug":"openai/gpt-5.4-image-2-20260421","hugging_face_id":"","name":"OpenAI: GPT-5.4 Image 2","created":1776797528,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","context_length":272000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000008","completion":"0.000015","image_output":"0.00003","web_search":"0.01","input_cache_read":"0.000002"},"top_provider":{"context_length":272000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-image-2-20260421/endpoints"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":8e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-06,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.4-image-2-20260421","model_id":"openai/gpt-5.4-image-2","model_name":"OpenAI: GPT-5.4 Image 2","context_length":272000,"pricing":{"prompt":"0.000008","completion":"0.000015","image_output":"0.00003","web_search":"0.01","input_cache_read":"0.000002","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99477588548741,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-06,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":1.01e-05,"_priciest_blended_per_m":1.01e-05,"_provider_spread_multiplier":1.0},{"id":"xiaomi/mimo-v2.5","canonical_slug":"xiaomi/mimo-v2.5-20260422","hugging_face_id":"XiaomiMiMo/MiMo-V2.5","name":"Xiaomi: MiMo-V2.5","created":1776874269,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.0000000028"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.5-20260422/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1257,"win_rate":51.5,"rank":30},{"arena":"models","category":"asciiart","elo":1163,"win_rate":45.9,"rank":39},{"arena":"models","category":"codecategories","elo":1284,"win_rate":54.5,"rank":23},{"arena":"models","category":"dataviz","elo":1273,"win_rate":55.1,"rank":22},{"arena":"models","category":"gamedev","elo":1278,"win_rate":54.8,"rank":25},{"arena":"models","category":"svg","elo":1213,"win_rate":52.1,"rank":27},{"arena":"models","category":"uicomponent","elo":1284,"win_rate":54.9,"rank":24},{"arena":"models","category":"website","elo":1287,"win_rate":54.7,"rank":23}],"artificial_analysis":{"intelligence_index":38,"coding_index":56.8,"agentic_index":24.4}},"reasoning":{"mandatory":false},"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-09,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | xiaomi/mimo-v2.5-20260422","model_id":"xiaomi/mimo-v2.5","model_name":"Xiaomi: MiMo-V2.5","context_length":1050000,"pricing":{"prompt":"0.000000119","completion":"0.000000238","input_cache_read":"0.00000000255","discount":0.15},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":945000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-5,"uptime_last_30m":67.68699654775604,"uptime_last_5m":76.16580310880829,"uptime_last_1d":68.70522105239864,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.19e-07,"_completion_per_m":2.38e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.55e-09,"_cached_write_per_m":null},{"name":"DeepInfra | xiaomi/mimo-v2.5-20260422","model_id":"xiaomi/mimo-v2.5","model_name":"Xiaomi: MiMo-V2.5","context_length":262144,"pricing":{"prompt":"0.00000013","completion":"0.00000065","input_cache_read":"0.000000026","discount":0.675},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":96.15214506855374,"uptime_last_5m":97.68115942028986,"uptime_last_1d":98.7290462005724,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":6.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-08,"_cached_write_per_m":null},{"name":"Xiaomi | xiaomi/mimo-v2.5-20260422","model_id":"xiaomi/mimo-v2.5","model_name":"Xiaomi: MiMo-V2.5","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.0000000028","discount":0},"provider_name":"Xiaomi","tag":"xiaomi/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","tools","tool_choice","frequency_penalty","presence_penalty"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":99.08807707086787,"uptime_last_5m":98.97750511247445,"uptime_last_1d":99.39574561606233,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-09,"_cached_write_per_m":null},{"name":"Parasail | xiaomi/mimo-v2.5-20260422","model_id":"xiaomi/mimo-v2.5","model_name":"Xiaomi: MiMo-V2.5","context_length":1048576,"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.00000005","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":943718,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":96.36557990379477,"uptime_last_5m":98.15950920245399,"uptime_last_1d":98.81420787622976,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"StreamLake | xiaomi/mimo-v2.5-20260422","model_id":"xiaomi/mimo-v2.5","model_name":"Xiaomi: MiMo-V2.5","context_length":1000000,"pricing":{"prompt":"0.000000168","completion":"0.000000336","input_cache_read":"0.00000000336","discount":-0.2},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":90.54982817869416,"uptime_last_5m":92.14285714285714,"uptime_last_1d":91.61953727506426,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.68e-07,"_completion_per_m":3.36e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.36e-09,"_cached_write_per_m":null},{"name":"Novita | xiaomi/mimo-v2.5-20260422","model_id":"xiaomi/mimo-v2.5","model_name":"Xiaomi: MiMo-V2.5","context_length":1048576,"pricing":{"prompt":"0.000000168","completion":"0.000000336","input_cache_read":"0.0000000034","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.86531986531986,"uptime_last_5m":100,"uptime_last_1d":99.17150048068095,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.68e-07,"_completion_per_m":3.36e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.4e-09,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":1.5469999999999998e-07,"_priciest_blended_per_m":2.86e-07,"_provider_spread_multiplier":1.8487394957983196},{"id":"moonshotai/kimi-k2.6","canonical_slug":"moonshotai/kimi-k2.6-20260420","hugging_face_id":"moonshotai/Kimi-K2.6","name":"MoonshotAI: Kimi K2.6","created":1776699402,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000016"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2.6-20260420/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1139,"win_rate":47.4,"rank":20},{"arena":"agents","category":"agentichtmlslides","elo":1248,"win_rate":59,"rank":2},{"arena":"agents","category":"agenticslides","elo":1187,"win_rate":45.8,"rank":5},{"arena":"agents","category":"agenticslides(html)","elo":1252,"win_rate":59.2,"rank":2},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1186,"win_rate":45.5,"rank":5},{"arena":"agents","category":"androidnative","elo":1188,"win_rate":51.2,"rank":19},{"arena":"agents","category":"fullstack","elo":1181,"win_rate":52.4,"rank":23},{"arena":"agents","category":"godotgamedev","elo":1160,"win_rate":47.1,"rank":15},{"arena":"agents","category":"htmlslides","elo":1201,"win_rate":52.8,"rank":9},{"arena":"agents","category":"mobileapps","elo":1199,"win_rate":50.6,"rank":20},{"arena":"agents","category":"pptxslides","elo":1181,"win_rate":44.3,"rank":5},{"arena":"agents","category":"python-pptxslides","elo":1180,"win_rate":42.1,"rank":14},{"arena":"agents","category":"webapps","elo":1268,"win_rate":59.3,"rank":8},{"arena":"models","category":"3d","elo":1313,"win_rate":57.7,"rank":13},{"arena":"models","category":"asciiart","elo":1192,"win_rate":47.9,"rank":26},{"arena":"models","category":"codecategories","elo":1298,"win_rate":55,"rank":17},{"arena":"models","category":"dataviz","elo":1273,"win_rate":52.1,"rank":21},{"arena":"models","category":"gamedev","elo":1288,"win_rate":54.9,"rank":24},{"arena":"models","category":"svg","elo":1221,"win_rate":51.3,"rank":24},{"arena":"models","category":"uicomponent","elo":1293,"win_rate":55.8,"rank":20},{"arena":"models","category":"website","elo":1291,"win_rate":54.6,"rank":17}],"artificial_analysis":{"intelligence_index":45.1,"coding_index":61.8,"agentic_index":31.2}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Decart | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.0000005372","completion":"0.0000022618","input_cache_read":"0.0000000905","discount":0},"provider_name":"Decart","tag":"decart/fp4","quantization":"fp4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.92966744423214,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.372e-07,"_completion_per_m":2.2618e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9.05e-08,"_cached_write_per_m":null},{"name":"Inceptron | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000054","completion":"0.00000339","input_cache_read":"0.00000017","discount":0},"provider_name":"Inceptron","tag":"inceptron/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8868778280543,"uptime_last_5m":100,"uptime_last_1d":99.83507267329651,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.4e-07,"_completion_per_m":3.39e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.7e-07,"_cached_write_per_m":null},{"name":"Chutes | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000058","completion":"0.0000034","input_cache_read":"0.000000058","discount":0},"provider_name":"Chutes","tag":"chutes/int4","quantization":"int4","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.35185185185185,"uptime_last_5m":98.49246231155779,"uptime_last_1d":98.7450521770421,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.8e-07,"_completion_per_m":3.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.8e-08,"_cached_write_per_m":null},{"name":"StreamLake | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":256000,"pricing":{"prompt":"0.0000005985","completion":"0.00000252","input_cache_read":"0.0000001008","discount":0.37},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":230400,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","stop","top_p","temperature","max_tokens","tool_choice","tools","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.97727272727272,"uptime_last_5m":100,"uptime_last_1d":98.71636150387698,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.985e-07,"_completion_per_m":2.52e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.008e-07,"_cached_write_per_m":null},{"name":"CoreWeave | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000065","completion":"0.00000341","input_cache_read":"0.00000015","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp4","quantization":"fp4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":97.02276707530648,"uptime_last_5m":97.93510324483776,"uptime_last_1d":98.99423948099401,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.5e-07,"_completion_per_m":3.41e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"Crusoe | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.0000007","completion":"0.0000035","input_cache_read":"0.00000035","discount":0},"provider_name":"Crusoe","tag":"crusoe/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":99.66722129783693,"uptime_last_5m":100,"uptime_last_1d":98.79232170854696,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-07,"_cached_write_per_m":null},{"name":"DeepInfra | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000075","completion":"0.0000035","input_cache_read":"0.00000015","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.38969404186795,"uptime_last_5m":92.53731343283582,"uptime_last_1d":99.69341240066159,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"Venice | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":256000,"pricing":{"prompt":"0.00000075","completion":"0.0000035","input_cache_read":"0.00000016","discount":0},"provider_name":"Venice","tag":"venice/int4","quantization":"int4","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tool_choice","tools","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.03846153846155,"uptime_last_5m":98.73417721518987,"uptime_last_1d":83.11711550505503,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"Parasail | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000075","completion":"0.0000035","input_cache_read":"0.00000016","discount":0},"provider_name":"Parasail","tag":"parasail/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.83319432860718,"uptime_last_5m":100,"uptime_last_1d":99.09895316581286,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000077","completion":"0.0000034","input_cache_read":"0.00000014","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","response_format","tools","tool_choice","structured_outputs","max_tokens"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.92129771326134,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.7e-07,"_completion_per_m":3.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"Novita | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.0000008","completion":"0.0000034","input_cache_read":"0.00000016","discount":0},"provider_name":"Novita","tag":"novita","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.5609220636663,"uptime_last_5m":98.47328244274809,"uptime_last_1d":99.35928573080749,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":3.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"GMICloud | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.000000855","completion":"0.0000036","input_cache_read":"0.000000144","discount":0.1},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-2,"uptime_last_30m":88.57142857142857,"uptime_last_5m":null,"uptime_last_1d":89.10869245477276,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.55e-07,"_completion_per_m":3.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.44e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000019","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","structured_outputs","response_format","tool_choice","tools","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.86637229839647,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.9e-07,"_cached_write_per_m":null},{"name":"Baidu | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000016","discount":0},"provider_name":"Baidu","tag":"baidu/fp4","quantization":"fp4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","stop","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97811386826058,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"Cloudflare | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000016","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","min_p","stop","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.75961538461539,"uptime_last_5m":100,"uptime_last_1d":99.93478969677209,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"Moonshot AI | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000016","discount":0},"provider_name":"Moonshot AI","tag":"moonshotai/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","frequency_penalty","presence_penalty","structured_outputs","response_format","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.48979591836735,"uptime_last_5m":99.35483870967742,"uptime_last_1d":99.67755479049458,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"AtlasCloud | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000016","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","tool_choice","tools","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.2248062015504,"uptime_last_5m":99.4949494949495,"uptime_last_1d":98.08110065170168,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"Phala | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000109","completion":"0.0000046","input_cache_read":"0.00000037","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","response_format","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.71986970684038,"uptime_last_5m":null,"uptime_last_1d":98.84997927890593,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.09e-06,"_completion_per_m":4.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.7e-07,"_cached_write_per_m":null},{"name":"Fireworks | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262144,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000016","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":0.3558718861209964,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"BaseTen | moonshotai/kimi-k2.6-20260420","model_id":"moonshotai/kimi-k2.6","model_name":"MoonshotAI: Kimi K2.6","context_length":262000,"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000016","discount":0},"provider_name":"BaseTen","tag":"baseten/fp4","quantization":"fp4","max_completion_tokens":235800,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Decart","_cheapest_blended_per_m":1.05458e-06,"_priciest_blended_per_m":2.1429999999999996e-06,"_provider_spread_multiplier":2.032088603994007},{"id":"anthropic/claude-opus-4.7","canonical_slug":"anthropic/claude-4.7-opus-20260416","hugging_face_id":null,"name":"Anthropic: Claude Opus 4.7","created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1247,"win_rate":59.1,"rank":3},{"arena":"agents","category":"agentichtmlslides","elo":1243,"win_rate":58,"rank":3},{"arena":"agents","category":"agenticslides","elo":1334,"win_rate":64.7,"rank":1},{"arena":"agents","category":"agenticslides(html)","elo":1242,"win_rate":57.8,"rank":3},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1331,"win_rate":65.2,"rank":1},{"arena":"agents","category":"androidnative","elo":1249,"win_rate":56,"rank":8},{"arena":"agents","category":"fullstack","elo":1503,"win_rate":80.1,"rank":1},{"arena":"agents","category":"godotgamedev","elo":1270,"win_rate":60.9,"rank":2},{"arena":"agents","category":"htmlslides","elo":1225,"win_rate":56.8,"rank":5},{"arena":"agents","category":"pptxslides","elo":1333,"win_rate":64.9,"rank":1},{"arena":"agents","category":"python-pptxslides","elo":1336,"win_rate":63.1,"rank":1},{"arena":"agents","category":"webapps","elo":1278,"win_rate":60.5,"rank":4},{"arena":"models","category":"3d","elo":1294,"win_rate":56.7,"rank":20},{"arena":"models","category":"asciiart","elo":1313,"win_rate":65.6,"rank":4},{"arena":"models","category":"codecategories","elo":1316,"win_rate":57.9,"rank":10},{"arena":"models","category":"dataviz","elo":1309,"win_rate":56.1,"rank":10},{"arena":"models","category":"gamedev","elo":1327,"win_rate":59.4,"rank":10},{"arena":"models","category":"svg","elo":1264,"win_rate":58.9,"rank":11},{"arena":"models","category":"uicomponent","elo":1334,"win_rate":60.4,"rank":7},{"arena":"models","category":"website","elo":1315,"win_rate":58,"rank":9}],"artificial_analysis":{"intelligence_index":55,"coding_index":73.6,"agentic_index":46.3}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06,"_endpoints":[{"name":"Amazon Bedrock | anthropic/claude-4.7-opus-20260416","model_id":"anthropic/claude-opus-4.7","model_name":"Anthropic: Claude Opus 4.7","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96870631923727,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Google | anthropic/claude-4.7-opus-20260416","model_id":"anthropic/claude-opus-4.7","model_name":"Anthropic: Claude Opus 4.7","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.97548118180704,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Claude Platform on AWS | anthropic/claude-4.7-opus-20260416","model_id":"anthropic/claude-opus-4.7","model_name":"Anthropic: Claude Opus 4.7","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Claude Platform on AWS","tag":"claude-on-aws","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.87387680286103,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Anthropic | anthropic/claude-4.7-opus-20260416","model_id":"anthropic/claude-opus-4.7","model_name":"Anthropic: Claude Opus 4.7","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.97885388031297,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Azure | anthropic/claude-4.7-opus-20260416","model_id":"anthropic/claude-opus-4.7","model_name":"Anthropic: Claude Opus 4.7","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Azure","tag":"azure/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Amazon Bedrock | anthropic/claude-4.7-opus-20260416","model_id":"anthropic/claude-opus-4.7","model_name":"Anthropic: Claude Opus 4.7","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06},{"name":"Google | anthropic/claude-4.7-opus-20260416","model_id":"anthropic/claude-opus-4.7","model_name":"Anthropic: Claude Opus 4.7","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Google","tag":"google-vertex/europe","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06},{"name":"Google | anthropic/claude-4.7-opus-20260416","model_id":"anthropic/claude-opus-4.7","model_name":"Anthropic: Claude Opus 4.7","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":1.1e-05,"_priciest_blended_per_m":1.21e-05,"_provider_spread_multiplier":1.0999999999999999},{"id":"anthropic/claude-opus-4.7:batch","canonical_slug":"anthropic/claude-4.7-opus-20260416","hugging_face_id":null,"name":"Anthropic: Claude Opus 4.7 (batch)","created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1247,"win_rate":59.1,"rank":3},{"arena":"agents","category":"agentichtmlslides","elo":1243,"win_rate":58,"rank":3},{"arena":"agents","category":"agenticslides","elo":1334,"win_rate":64.7,"rank":1},{"arena":"agents","category":"agenticslides(html)","elo":1242,"win_rate":57.8,"rank":3},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1331,"win_rate":65.2,"rank":1},{"arena":"agents","category":"androidnative","elo":1249,"win_rate":56,"rank":8},{"arena":"agents","category":"fullstack","elo":1503,"win_rate":80.1,"rank":1},{"arena":"agents","category":"godotgamedev","elo":1270,"win_rate":60.9,"rank":2},{"arena":"agents","category":"htmlslides","elo":1225,"win_rate":56.8,"rank":5},{"arena":"agents","category":"pptxslides","elo":1333,"win_rate":64.9,"rank":1},{"arena":"agents","category":"python-pptxslides","elo":1336,"win_rate":63.1,"rank":1},{"arena":"agents","category":"webapps","elo":1278,"win_rate":60.5,"rank":4},{"arena":"models","category":"3d","elo":1294,"win_rate":56.7,"rank":20},{"arena":"models","category":"asciiart","elo":1313,"win_rate":65.6,"rank":4},{"arena":"models","category":"codecategories","elo":1316,"win_rate":57.9,"rank":10},{"arena":"models","category":"dataviz","elo":1309,"win_rate":56.1,"rank":10},{"arena":"models","category":"gamedev","elo":1327,"win_rate":59.4,"rank":10},{"arena":"models","category":"svg","elo":1264,"win_rate":58.9,"rank":11},{"arena":"models","category":"uicomponent","elo":1334,"win_rate":60.4,"rank":7},{"arena":"models","category":"website","elo":1315,"win_rate":58,"rank":9}],"artificial_analysis":{"intelligence_index":55,"coding_index":73.6,"agentic_index":46.3}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.7-opus-20260416:batch","model_id":"anthropic/claude-opus-4.7:batch","model_name":"Anthropic: Claude Opus 4.7","context_length":1000000,"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":5.5e-06,"_priciest_blended_per_m":5.5e-06,"_provider_spread_multiplier":1.0},{"id":"z-ai/glm-5.1","canonical_slug":"z-ai/glm-5.1-20260406","hugging_face_id":"zai-org/GLM-5.1","name":"Z.ai: GLM 5.1","created":1775578025,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000126","completion":"0.00000396","input_cache_read":"0.000000234"},"top_provider":{"context_length":202752,"max_completion_tokens":182476,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.1-20260406/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1336,"win_rate":62.6,"rank":8},{"arena":"models","category":"asciiart","elo":1162,"win_rate":45.8,"rank":40},{"arena":"models","category":"codecategories","elo":1293,"win_rate":54.6,"rank":19},{"arena":"models","category":"dataviz","elo":1366,"win_rate":67,"rank":2},{"arena":"models","category":"gamedev","elo":1298,"win_rate":57.4,"rank":18},{"arena":"models","category":"svg","elo":1258,"win_rate":58.3,"rank":14},{"arena":"models","category":"uicomponent","elo":1294,"win_rate":54.6,"rank":19},{"arena":"models","category":"website","elo":1290,"win_rate":55.1,"rank":18},{"arena":"agents","category":"agenticgamedev","elo":1169,"win_rate":50.7,"rank":17},{"arena":"agents","category":"agentichtmlslides","elo":1205,"win_rate":52,"rank":6},{"arena":"agents","category":"agenticslides","elo":1245,"win_rate":54.4,"rank":3},{"arena":"agents","category":"agenticslides(html)","elo":1204,"win_rate":51.8,"rank":6},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1240,"win_rate":53.3,"rank":4},{"arena":"agents","category":"androidnative","elo":1200,"win_rate":52.4,"rank":17},{"arena":"agents","category":"fullstack","elo":1190,"win_rate":54.1,"rank":21},{"arena":"agents","category":"godotgamedev","elo":1104,"win_rate":39.5,"rank":25},{"arena":"agents","category":"htmlslides","elo":1185,"win_rate":49.3,"rank":11},{"arena":"agents","category":"mobileapps","elo":1203,"win_rate":52.7,"rank":17},{"arena":"agents","category":"pptxslides","elo":1241,"win_rate":53.5,"rank":4},{"arena":"agents","category":"python-pptxslides","elo":1258,"win_rate":54.2,"rank":5},{"arena":"agents","category":"webapps","elo":1207,"win_rate":51.8,"rank":21}],"artificial_analysis":{"intelligence_index":41,"coding_index":55.8,"agentic_index":30.6}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":1.26e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.34e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.00000091","completion":"0.00000286","input_cache_read":"0.000000169","discount":0.35},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.581589958159,"uptime_last_5m":98.61111111111111,"uptime_last_1d":99.58759737284252,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.1e-07,"_completion_per_m":2.86e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.69e-07,"_cached_write_per_m":null},{"name":"StreamLake | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":200000,"pricing":{"prompt":"0.000000966","completion":"0.000003036","input_cache_read":"0.0000001794","discount":0.31},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8768472906404,"uptime_last_5m":100,"uptime_last_1d":99.92063593655996,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.66e-07,"_completion_per_m":3.036e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.794e-07,"_cached_write_per_m":null},{"name":"Chutes | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.00000098","completion":"0.00000308","input_cache_read":"0.000000098","discount":0},"provider_name":"Chutes","tag":"chutes/fp8","quantization":"fp8","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","structured_outputs","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":-2,"uptime_last_30m":84.93150684931507,"uptime_last_5m":68.29268292682927,"uptime_last_1d":93.89980824544583,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.8e-07,"_completion_per_m":3.08e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9.8e-08,"_cached_write_per_m":null},{"name":"DeepInfra | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.00000105","completion":"0.0000035","input_cache_read":"0.000000205","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.94964028776978,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.05e-06,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.05e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":204800,"pricing":{"prompt":"0.00000119","completion":"0.00000374","input_cache_read":"0.0000006","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99373688660633,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.19e-06,"_completion_per_m":3.74e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-07,"_cached_write_per_m":null},{"name":"Crusoe | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.0000012","completion":"0.0000044","input_cache_read":"0.00000025","discount":0},"provider_name":"Crusoe","tag":"crusoe/fp8","quantization":"fp8","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.65463391194666,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.2e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null},{"name":"Phala | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.00000121","completion":"0.0000042","input_cache_read":"0.0000006","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","tool_choice","tools","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":86.11111111111111,"uptime_last_5m":75.67567567567568,"uptime_last_1d":94.07831900668577,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.21e-06,"_completion_per_m":4.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-07,"_cached_write_per_m":null},{"name":"AtlasCloud | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.00000126","completion":"0.00000396","input_cache_read":"0.000000234","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.92503992438809,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.26e-06,"_completion_per_m":3.96e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.34e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":163840,"pricing":{"prompt":"0.0000013","completion":"0.0000043","input_cache_read":"0.00000026","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":98.03332422835291,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-06,"_completion_per_m":4.3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Alibaba | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202745,"pricing":{"prompt":"0.00000133","completion":"0.00000418","input_cache_read":"0.000000247","discount":0},"provider_name":"Alibaba","tag":"alibaba/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":169984,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","structured_outputs","tools","logprobs","top_logprobs","top_k","frequency_penalty","stop","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.92764109985528,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.33e-06,"_completion_per_m":4.18e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.47e-07,"_cached_write_per_m":null},{"name":"Novita | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":204800,"pricing":{"prompt":"0.00000138","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":96.77137107358475,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.38e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Baidu | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Baidu","tag":"baidu/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96345591629482,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Nebius | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.0000014","completion":"0.0000044","discount":0},"provider_name":"Nebius","tag":"nebius/fp8","quantization":"fp8","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.63945578231292,"uptime_last_5m":93.54838709677419,"uptime_last_1d":96.64109281437125,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Z.AI | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.92012779552716,"uptime_last_5m":100,"uptime_last_1d":99.82247893593345,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Parasail | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":77.44618395303327,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Friendli | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":202752,"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"provider_name":"Friendli","tag":"friendli","quantization":"unknown","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":99.72972972972973,"uptime_last_5m":100,"uptime_last_1d":99.9315025842207,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.6e-07,"_cached_write_per_m":null},{"name":"Venice | z-ai/glm-5.1-20260406","model_id":"z-ai/glm-5.1","model_name":"Z.ai: GLM 5.1","context_length":200000,"pricing":{"prompt":"0.00000154","completion":"0.00000484","input_cache_read":"0.000000286","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":80000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":98.59970611115914,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.54e-06,"_completion_per_m":4.84e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.86e-07,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":1.4949999999999999e-06,"_priciest_blended_per_m":2.53e-06,"_provider_spread_multiplier":1.6923076923076923},{"id":"google/gemma-4-26b-a4b-it","canonical_slug":"google/gemma-4-26b-a4b-it-20260403","hugging_face_id":"google/gemma-4-26B-A4B-it","name":"Google: Gemma 4 26B A4B ","created":1775227989,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0.00000007","completion":"0.00000034"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":26.1,"coding_index":39.3,"agentic_index":11}},"reasoning":{"mandatory":false,"default_enabled":false},"_prompt_per_m":7e-08,"_completion_per_m":3.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Darkbloom | google/gemma-4-26b-a4b-it-20260403","model_id":"google/gemma-4-26b-a4b-it","model_name":"Google: Gemma 4 26B A4B ","context_length":131072,"pricing":{"prompt":"0.000000042","completion":"0.00000022","discount":0},"provider_name":"Darkbloom","tag":"darkbloom","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.95032290114257,"uptime_last_5m":99.99122036874452,"uptime_last_1d":95.50855451371001,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.2e-08,"_completion_per_m":2.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | google/gemma-4-26b-a4b-it-20260403","model_id":"google/gemma-4-26b-a4b-it","model_name":"Google: Gemma 4 26B A4B ","context_length":262144,"pricing":{"prompt":"0.00000007","completion":"0.00000034","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools","structured_outputs","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.1451395372964,"uptime_last_5m":98.99557187601253,"uptime_last_1d":99.54082171295849,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":3.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Cloudflare | google/gemma-4-26b-a4b-it-20260403","model_id":"google/gemma-4-26b-a4b-it","model_name":"Google: Gemma 4 26B A4B ","context_length":256000,"pricing":{"prompt":"0.0000001","completion":"0.0000003","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":230400,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97638724911452,"uptime_last_5m":100,"uptime_last_1d":99.94597630876586,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"NextBit | google/gemma-4-26b-a4b-it-20260403","model_id":"google/gemma-4-26b-a4b-it","model_name":"Google: Gemma 4 26B A4B ","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.0000004","input_cache_read":"0.00000005","discount":0},"provider_name":"NextBit","tag":"nextbit/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.90862851399507,"uptime_last_5m":99.92079207920793,"uptime_last_1d":98.0955109396819,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | google/gemma-4-26b-a4b-it-20260403","model_id":"google/gemma-4-26b-a4b-it","model_name":"Google: Gemma 4 26B A4B ","context_length":262144,"pricing":{"prompt":"0.00000012","completion":"0.0000004","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.93941229930324,"uptime_last_5m":99.75,"uptime_last_1d":91.72921613761187,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.2e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | google/gemma-4-26b-a4b-it-20260403","model_id":"google/gemma-4-26b-a4b-it","model_name":"Google: Gemma 4 26B A4B ","context_length":262144,"pricing":{"prompt":"0.00000013","completion":"0.0000004","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.46412233694943,"uptime_last_5m":99.30313588850174,"uptime_last_1d":99.5277993025959,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Venice | google/gemma-4-26b-a4b-it-20260403","model_id":"google/gemma-4-26b-a4b-it","model_name":"Google: Gemma 4 26B A4B ","context_length":256000,"pricing":{"prompt":"0.00000013","completion":"0.0000004","input_cache_read":"0.00000005","discount":0},"provider_name":"Venice","tag":"venice/bf16","quantization":"bf16","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.6481636559397,"uptime_last_5m":98.3149708360337,"uptime_last_1d":98.42410495281301,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Parasail | google/gemma-4-26b-a4b-it-20260403","model_id":"google/gemma-4-26b-a4b-it","model_name":"Google: Gemma 4 26B A4B ","context_length":262144,"pricing":{"prompt":"0.00000013","completion":"0.0000004","input_cache_read":"0.00000005","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":false,"required":false,"function":false},"status":0,"uptime_last_30m":98.73530724594555,"uptime_last_5m":98.59839282377125,"uptime_last_1d":98.1454013033867,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Google | google/gemma-4-26b-a4b-it-20260403","model_id":"google/gemma-4-26b-a4b-it","model_name":"Google: Gemma 4 26B A4B ","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.62825278810409,"uptime_last_5m":99.46737683089214,"uptime_last_1d":99.23149621965777,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Darkbloom","_cheapest_blended_per_m":9.54e-08,"_priciest_blended_per_m":2.8499999999999997e-07,"_provider_spread_multiplier":2.9874213836477987},{"id":"google/gemma-4-26b-a4b-it:free","canonical_slug":"google/gemma-4-26b-a4b-it-20260403","hugging_face_id":"google/gemma-4-26B-A4B-it","name":"Google: Gemma 4 26B A4B  (free)","created":1775227989,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":26.1,"coding_index":39.3,"agentic_index":11}},"reasoning":{"mandatory":false,"default_enabled":false},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Google AI Studio | google/gemma-4-26b-a4b-it-20260403:free","model_id":"google/gemma-4-26b-a4b-it:free","model_name":"Google: Gemma 4 26B A4B ","context_length":262144,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.3516086671044,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"google/gemma-4-31b-it","canonical_slug":"google/gemma-4-31b-it-20260402","hugging_face_id":"google/gemma-4-31B-it","name":"Google: Gemma 4 31B","created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0.00000009","completion":"0.00000034","input_cache_read":"0.00000005"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-31b-it-20260402/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":29.7,"coding_index":43.4,"agentic_index":14.4}},"reasoning":{"mandatory":false,"default_enabled":false},"_prompt_per_m":9e-08,"_completion_per_m":3.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenInference | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000008","completion":"0.00000035","input_cache_read":"0.00000001","discount":0},"provider_name":"OpenInference","tag":"open-inference/bf16","quantization":"bf16","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","stop","seed","response_format","tools","tool_choice","structured_outputs","top_p","frequency_penalty","presence_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.86747165365925,"uptime_last_5m":100,"uptime_last_1d":99.7706471489068,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-08,"_completion_per_m":3.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null},{"name":"DeepInfra | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000009","completion":"0.00000034","input_cache_read":"0.00000005","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/turbo","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.7671932533555,"uptime_last_5m":99.87771739130434,"uptime_last_1d":99.751428308775,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":3.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"CoreWeave | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.00000034","input_cache_read":"0.0000001","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp4","quantization":"fp4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.32228989581242,"uptime_last_5m":97.47920029802557,"uptime_last_1d":98.15429379204078,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Venice | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":256000,"pricing":{"prompt":"0.00000012","completion":"0.00000036","input_cache_read":"0.00000009","discount":0},"provider_name":"Venice","tag":"venice/bf16","quantization":"bf16","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.80153894363009,"uptime_last_5m":99.68089955933749,"uptime_last_1d":99.52340349545769,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.2e-07,"_completion_per_m":3.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9e-08,"_cached_write_per_m":null},{"name":"Chutes | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":131072,"pricing":{"prompt":"0.00000012","completion":"0.00000037","input_cache_read":"0.000000012","discount":0},"provider_name":"Chutes","tag":"chutes/fp4","quantization":"fp4","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.06139805019706,"uptime_last_5m":98.39407041383569,"uptime_last_1d":94.90459487090138,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.2e-07,"_completion_per_m":3.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-08,"_cached_write_per_m":null},{"name":"DeepInfra | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000013","completion":"0.00000038","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools","structured_outputs","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.95422494509305,"uptime_last_5m":98.30508474576271,"uptime_last_1d":98.43327420659618,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":3.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000013","completion":"0.0000004","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.81268582755203,"uptime_last_5m":98.4536082474227,"uptime_last_1d":92.09863341816549,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Crusoe | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000014","completion":"0.0000004","input_cache_read":"0.00000014","discount":0},"provider_name":"Crusoe","tag":"crusoe","quantization":"unknown","max_completion_tokens":262141,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.71276204486944,"uptime_last_5m":96.71428571428572,"uptime_last_1d":99.06045659305983,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"Friendli | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000014","completion":"0.0000004","discount":0},"provider_name":"Friendli","tag":"friendli","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.99040491268471,"uptime_last_5m":100,"uptime_last_1d":99.96681833824893,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000014","completion":"0.0000004","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.75,"uptime_last_5m":99.71631205673759,"uptime_last_1d":98.3955917662216,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000004","input_cache_read":"0.00000006","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.71267807973183,"uptime_last_5m":99.84813971146545,"uptime_last_1d":99.75526950683694,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Phala | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.00000046","input_cache_read":"0.000000075","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-5,"uptime_last_30m":57.519788918205805,"uptime_last_5m":null,"uptime_last_1d":79.3301358592041,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":4.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null},{"name":"DeepInfra | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":131072,"pricing":{"prompt":"0.00000027","completion":"0.00000076","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/ultra","quantization":"fp8","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":14.414797641962574,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":7.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SambaNova | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":131072,"pricing":{"prompt":"0.00000038","completion":"0.00000115","discount":0},"provider_name":"SambaNova","tag":"sambanova","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.96385977593062,"uptime_last_5m":100,"uptime_last_1d":99.59593507214205,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.8e-07,"_completion_per_m":1.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Together | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000039","completion":"0.00000097","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","structured_outputs","response_format","tool_choice","tools"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.3265306122449,"uptime_last_5m":null,"uptime_last_1d":95.21045443258008,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.9e-07,"_completion_per_m":9.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"ModelRun | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0.00000075","completion":"0.000001","input_cache_read":"0.00000075","discount":0},"provider_name":"ModelRun","tag":"modelrun/fp4","quantization":"fp4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","presence_penalty","repetition_penalty","frequency_penalty","top_p","top_k","stop","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.89840839823908,"uptime_last_5m":99.76470588235294,"uptime_last_1d":99.9733258815161,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-07,"_cached_write_per_m":null},{"name":"Cerebras | google/gemma-4-31b-it-20260402","model_id":"google/gemma-4-31b-it","model_name":"Google: Gemma 4 31B","context_length":131072,"pricing":{"prompt":"0.00000099","completion":"0.00000149","input_cache_read":"0.00000099","discount":0},"provider_name":"Cerebras","tag":"cerebras/fp16","quantization":"fp16","max_completion_tokens":40960,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","stop","seed","tools","tool_choice","frequency_penalty","presence_penalty","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.95615407276141,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.9e-07,"_completion_per_m":1.49e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9.9e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenInference","_cheapest_blended_per_m":1.6099999999999997e-07,"_priciest_blended_per_m":1.1399999999999999e-06,"_provider_spread_multiplier":7.080745341614907},{"id":"google/gemma-4-31b-it:free","canonical_slug":"google/gemma-4-31b-it-20260402","hugging_face_id":"google/gemma-4-31B-it","name":"Google: Gemma 4 31B (free)","created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-31b-it-20260402/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":29.7,"coding_index":43.4,"agentic_index":14.4}},"reasoning":{"mandatory":false,"default_enabled":false},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Google AI Studio | google/gemma-4-31b-it-20260402:free","model_id":"google/gemma-4-31b-it:free","model_name":"Google: Gemma 4 31B","context_length":262144,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.49016751638747,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"qwen/qwen3.6-plus","canonical_slug":"qwen/qwen3.6-plus-04-02","hugging_face_id":"","name":"Qwen: Qwen3.6 Plus","created":1775133557,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.000000325","completion":"0.00000195","input_cache_write":"0.00000040625","overrides":[{"min_prompt_tokens":256000,"prompt":"0.0000013","completion":"0.0000039","input_cache_write":"0.000001625"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-plus-04-02/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1245,"win_rate":51.4,"rank":35},{"arena":"models","category":"asciiart","elo":1133,"win_rate":42.1,"rank":49},{"arena":"models","category":"codecategories","elo":1259,"win_rate":51.6,"rank":34},{"arena":"models","category":"dataviz","elo":1250,"win_rate":51.4,"rank":31},{"arena":"models","category":"gamedev","elo":1244,"win_rate":50.4,"rank":36},{"arena":"models","category":"svg","elo":1202,"win_rate":51.5,"rank":31},{"arena":"models","category":"uicomponent","elo":1262,"win_rate":52.3,"rank":34},{"arena":"models","category":"website","elo":1260,"win_rate":51.5,"rank":34}],"artificial_analysis":{"intelligence_index":40.5,"coding_index":54.5,"agentic_index":29}},"reasoning":{"mandatory":false},"_prompt_per_m":3.25e-07,"_completion_per_m":1.95e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":4.0625e-07,"_endpoints":[{"name":"Alibaba | qwen/qwen3.6-plus-04-02","model_id":"qwen/qwen3.6-plus","model_name":"Qwen: Qwen3.6 Plus","context_length":1000000,"pricing":{"prompt":"0.000000325","completion":"0.00000195","input_cache_write":"0.00000040625","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.0000013","completion":"0.0000039","input_cache_write":"0.000001625"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99980785489203,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.25e-07,"_completion_per_m":1.95e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":4.0625e-07}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":8.125000000000001e-07,"_priciest_blended_per_m":8.125000000000001e-07,"_provider_spread_multiplier":1.0},{"id":"x-ai/grok-4.20-multi-agent","canonical_slug":"x-ai/grok-4.20-multi-agent-20260309","hugging_face_id":"","name":"SpaceXAI: Grok 4.20 Multi-Agent","created":1774979158,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","context_length":2000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.0000025","web_search":"0.005","input_cache_read":"0.0000002","overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}]},"top_provider":{"context_length":2000000,"max_completion_tokens":1800000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-09-01","expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-4.20-multi-agent-20260309/endpoints"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"_prompt_per_m":1.25e-06,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"xAI | x-ai/grok-4.20-multi-agent-20260309","model_id":"x-ai/grok-4.20-multi-agent","model_name":"SpaceXAI: Grok 4.20 Multi-Agent","context_length":2000000,"pricing":{"prompt":"0.00000125","completion":"0.0000025","web_search":"0.005","input_cache_read":"0.0000002","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}]},"provider_name":"xAI","tag":"xai/zdr","quantization":"unknown","max_completion_tokens":1800000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":81.80242634315424,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.20-multi-agent-20260309","model_id":"x-ai/grok-4.20-multi-agent","model_name":"SpaceXAI: Grok 4.20 Multi-Agent","context_length":2000000,"pricing":{"prompt":"0.0000025","completion":"0.000005","web_search":"0.005","input_cache_read":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000005","completion":"0.00001","input_cache_read":"0.0000008"}]},"provider_name":"xAI","tag":"xai/zdr/priority","quantization":"unknown","max_completion_tokens":1800000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":81.80242634315424,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.20-multi-agent-20260309","model_id":"x-ai/grok-4.20-multi-agent","model_name":"SpaceXAI: Grok 4.20 Multi-Agent","context_length":2000000,"pricing":{"prompt":"0.00000125","completion":"0.0000025","web_search":"0.005","input_cache_read":"0.0000002","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}]},"provider_name":"xAI","tag":"xai","quantization":"unknown","max_completion_tokens":1800000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":82.66129032258065,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.20-multi-agent-20260309","model_id":"x-ai/grok-4.20-multi-agent","model_name":"SpaceXAI: Grok 4.20 Multi-Agent","context_length":2000000,"pricing":{"prompt":"0.0000025","completion":"0.000005","web_search":"0.005","input_cache_read":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000005","completion":"0.00001","input_cache_read":"0.0000008"}]},"provider_name":"xAI","tag":"xai/priority","quantization":"unknown","max_completion_tokens":1800000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":82.66129032258065,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":null}],"_cheapest_provider":"xAI","_cheapest_blended_per_m":1.6250000000000001e-06,"_priciest_blended_per_m":3.2500000000000002e-06,"_provider_spread_multiplier":2.0},{"id":"arcee-ai/trinity-large-thinking","canonical_slug":"arcee-ai/trinity-large-thinking","hugging_face_id":"arcee-ai/Trinity-Large-Thinking","name":"Arcee AI: Trinity Large Thinking","created":1775058318,"description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000022","completion":"0.00000085","input_cache_read":"0.00000006"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.3,"top_p":0.8,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/arcee-ai/trinity-large-thinking/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1126,"win_rate":41.3,"rank":77},{"arena":"models","category":"asciiart","elo":1067,"win_rate":37.1,"rank":57},{"arena":"models","category":"codecategories","elo":1142,"win_rate":40.1,"rank":80},{"arena":"models","category":"dataviz","elo":1119,"win_rate":39.3,"rank":83},{"arena":"models","category":"gamedev","elo":1115,"win_rate":38.4,"rank":85},{"arena":"models","category":"svg","elo":1056,"win_rate":35.2,"rank":69},{"arena":"models","category":"uicomponent","elo":1071,"win_rate":32.6,"rank":90},{"arena":"models","category":"website","elo":1157,"win_rate":41.3,"rank":77}],"artificial_analysis":{"intelligence_index":18.7,"coding_index":25.8,"agentic_index":3.7}},"reasoning":{"mandatory":true},"_prompt_per_m":2.2e-07,"_completion_per_m":8.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Parasail | arcee-ai/trinity-large-thinking","model_id":"arcee-ai/trinity-large-thinking","model_name":"Arcee AI: Trinity Large Thinking","context_length":262144,"pricing":{"prompt":"0.00000022","completion":"0.00000085","input_cache_read":"0.00000006","discount":0},"provider_name":"Parasail","tag":"parasail/fp4","quantization":"fp4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":null,"uptime_last_5m":0,"uptime_last_1d":84.77795612627074,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":8.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Arcee AI | arcee-ai/trinity-large-thinking","model_id":"arcee-ai/trinity-large-thinking","model_name":"Arcee AI: Trinity Large Thinking","context_length":262144,"pricing":{"prompt":"0.00000025","completion":"0.0000008","input_cache_read":"0.00000006","discount":0},"provider_name":"Arcee AI","tag":"arcee-ai","quantization":"unknown","max_completion_tokens":80000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_k","top_p","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98437092992967,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Parasail","_cheapest_blended_per_m":4.09e-07,"_priciest_blended_per_m":4.1499999999999994e-07,"_provider_spread_multiplier":1.0146699266503665},{"id":"google/lyria-3-pro-preview","canonical_slug":"google/lyria-3-pro-preview-20260330","hugging_face_id":null,"name":"Google: Lyria 3 Pro Preview","created":1774907286,"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...","context_length":1048576,"architecture":{"modality":"text+image->text+audio","input_modalities":["text","image"],"output_modalities":["text","audio"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/lyria-3-pro-preview-20260330/endpoints"},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Google AI Studio | google/lyria-3-pro-preview-20260330","model_id":"google/lyria-3-pro-preview","model_name":"Google: Lyria 3 Pro Preview","context_length":1048576,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.79245935662401,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"x-ai/grok-4.20","canonical_slug":"x-ai/grok-4.20-20260309","hugging_face_id":"","name":"SpaceXAI: Grok 4.20","created":1774979019,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","context_length":2000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.0000025","web_search":"0.005","input_cache_read":"0.0000002","overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}]},"top_provider":{"context_length":2000000,"max_completion_tokens":1800000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-09-01","expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-4.20-20260309/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1068,"win_rate":35.1,"rank":34},{"arena":"agents","category":"fullstack","elo":1077,"win_rate":41,"rank":31},{"arena":"agents","category":"godotgamedev","elo":1089,"win_rate":38.5,"rank":26},{"arena":"agents","category":"htmlslides","elo":1180,"win_rate":45.7,"rank":13},{"arena":"agents","category":"mobileapps","elo":1130,"win_rate":45.4,"rank":35},{"arena":"agents","category":"webapps","elo":1175,"win_rate":49.7,"rank":24},{"arena":"models","category":"3d","elo":1237,"win_rate":52.8,"rank":38},{"arena":"models","category":"asciiart","elo":1203,"win_rate":48.5,"rank":21},{"arena":"models","category":"codecategories","elo":1245,"win_rate":52.6,"rank":38},{"arena":"models","category":"dataviz","elo":1239,"win_rate":52.5,"rank":38},{"arena":"models","category":"gamedev","elo":1232,"win_rate":51.6,"rank":40},{"arena":"models","category":"svg","elo":1203,"win_rate":52.9,"rank":30},{"arena":"models","category":"uicomponent","elo":1227,"win_rate":49.9,"rank":42},{"arena":"models","category":"website","elo":1249,"win_rate":52.6,"rank":37}]},"reasoning":{"mandatory":false,"default_enabled":false},"_prompt_per_m":1.25e-06,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"xAI | x-ai/grok-4.20-20260309","model_id":"x-ai/grok-4.20","model_name":"SpaceXAI: Grok 4.20","context_length":2000000,"pricing":{"prompt":"0.00000125","completion":"0.0000025","web_search":"0.005","input_cache_read":"0.0000002","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}]},"provider_name":"xAI","tag":"xai/zdr","quantization":"unknown","max_completion_tokens":1800000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.73614775725594,"uptime_last_5m":100,"uptime_last_1d":99.84975316591543,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.20-20260309","model_id":"x-ai/grok-4.20","model_name":"SpaceXAI: Grok 4.20","context_length":2000000,"pricing":{"prompt":"0.0000025","completion":"0.000005","web_search":"0.005","input_cache_read":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000005","completion":"0.00001","input_cache_read":"0.0000008"}]},"provider_name":"xAI","tag":"xai/zdr/priority","quantization":"unknown","max_completion_tokens":1800000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.73614775725594,"uptime_last_5m":100,"uptime_last_1d":99.84975316591543,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.20-20260309","model_id":"x-ai/grok-4.20","model_name":"SpaceXAI: Grok 4.20","context_length":2000000,"pricing":{"prompt":"0.00000125","completion":"0.0000025","web_search":"0.005","input_cache_read":"0.0000002","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}]},"provider_name":"xAI","tag":"xai","quantization":"unknown","max_completion_tokens":1800000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.93970818762811,"uptime_last_5m":100,"uptime_last_1d":99.94744402008708,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"xAI | x-ai/grok-4.20-20260309","model_id":"x-ai/grok-4.20","model_name":"SpaceXAI: Grok 4.20","context_length":2000000,"pricing":{"prompt":"0.0000025","completion":"0.000005","web_search":"0.005","input_cache_read":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000005","completion":"0.00001","input_cache_read":"0.0000008"}]},"provider_name":"xAI","tag":"xai/priority","quantization":"unknown","max_completion_tokens":1800000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.93970818762811,"uptime_last_5m":100,"uptime_last_1d":99.94744402008708,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":null}],"_cheapest_provider":"xAI","_cheapest_blended_per_m":1.6250000000000001e-06,"_priciest_blended_per_m":3.2500000000000002e-06,"_provider_spread_multiplier":2.0},{"id":"google/lyria-3-clip-preview","canonical_slug":"google/lyria-3-clip-preview-20260330","hugging_face_id":null,"name":"Google: Lyria 3 Clip Preview","created":1774907255,"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...","context_length":1048576,"architecture":{"modality":"text+image->text+audio","input_modalities":["text","image"],"output_modalities":["text","audio"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/lyria-3-clip-preview-20260330/endpoints"},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Google AI Studio | google/lyria-3-clip-preview-20260330","model_id":"google/lyria-3-clip-preview","model_name":"Google: Lyria 3 Clip Preview","context_length":1048576,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.818401937046,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"rekaai/reka-edge","canonical_slug":"rekaai/reka-edge-2603","hugging_face_id":"RekaAI/reka-edge-2603","name":"Reka Edge","created":1774026965,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...","context_length":16384,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000001"},"top_provider":{"context_length":16384,"max_completion_tokens":14745,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/rekaai/reka-edge-2603/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1e-07,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Reka | rekaai/reka-edge-2603","model_id":"rekaai/reka-edge","model_name":"Reka Edge","context_length":16384,"pricing":{"prompt":"0.0000001","completion":"0.0000001","discount":0},"provider_name":"Reka","tag":"reka/bf16","quantization":"bf16","max_completion_tokens":14745,"max_prompt_tokens":null,"supported_parameters":["tool_choice","tools","top_k","top_p","stop","seed","temperature","frequency_penalty","presence_penalty","max_tokens","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Reka","_cheapest_blended_per_m":1e-07,"_priciest_blended_per_m":1e-07,"_provider_spread_multiplier":1.0},{"id":"z-ai/glm-5v-turbo","canonical_slug":"z-ai/glm-5v-turbo-20260401","hugging_face_id":"","name":"Z.ai: GLM 5V Turbo","created":1775061458,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","context_length":202752,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024"},"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2098-12-31","links":{"details":"/api/v1/models/z-ai/glm-5v-turbo-20260401/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1102,"win_rate":42.6,"rank":23},{"arena":"agents","category":"agentichtmlslides","elo":1134,"win_rate":41.7,"rank":8},{"arena":"agents","category":"agenticslides","elo":1171,"win_rate":51.6,"rank":6},{"arena":"agents","category":"agenticslides(html)","elo":1137,"win_rate":41.8,"rank":8},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1183,"win_rate":53.9,"rank":6},{"arena":"agents","category":"androidnative","elo":1267,"win_rate":54.8,"rank":4},{"arena":"agents","category":"fullstack","elo":1173,"win_rate":52.1,"rank":24},{"arena":"agents","category":"godotgamedev","elo":996,"win_rate":26.8,"rank":30},{"arena":"agents","category":"htmlslides","elo":1135,"win_rate":44.7,"rank":20},{"arena":"agents","category":"mobileapps","elo":1174,"win_rate":50.4,"rank":28},{"arena":"agents","category":"pptxslides","elo":1164,"win_rate":52.1,"rank":6},{"arena":"agents","category":"python-pptxslides","elo":1166,"win_rate":49.3,"rank":18},{"arena":"agents","category":"webapps","elo":1155,"win_rate":44.7,"rank":28},{"arena":"models","category":"3d","elo":1254,"win_rate":54,"rank":32},{"arena":"models","category":"asciiart","elo":1134,"win_rate":42.9,"rank":48},{"arena":"models","category":"codecategories","elo":1253,"win_rate":51.2,"rank":37},{"arena":"models","category":"dataviz","elo":1218,"win_rate":47.8,"rank":45},{"arena":"models","category":"gamedev","elo":1253,"win_rate":52.4,"rank":31},{"arena":"models","category":"svg","elo":1190,"win_rate":50.4,"rank":35},{"arena":"models","category":"uicomponent","elo":1241,"win_rate":50.2,"rank":39},{"arena":"models","category":"website","elo":1250,"win_rate":50,"rank":36}]},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":1.2e-06,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.4e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Z.AI | z-ai/glm-5v-turbo-20260401","model_id":"z-ai/glm-5v-turbo","model_name":"Z.ai: GLM 5V Turbo","context_length":202752,"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format","top_k"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.84917043740573,"uptime_last_5m":100,"uptime_last_1d":99.30091385242488,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.2e-06,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.4e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Z.AI","_cheapest_blended_per_m":2.04e-06,"_priciest_blended_per_m":2.04e-06,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.4-nano","canonical_slug":"openai/gpt-5.4-nano-20260317","hugging_face_id":"","name":"OpenAI: GPT-5.4 Nano","created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.00000125","web_search":"0.01","input_cache_read":"0.00000002"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-08-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-nano-20260317/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":39.7,"coding_index":56.1,"agentic_index":29.7}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.4-nano-20260317","model_id":"openai/gpt-5.4-nano","model_name":"OpenAI: GPT-5.4 Nano","context_length":400000,"pricing":{"prompt":"0.0000001","completion":"0.000000625","web_search":"0.01","input_cache_read":"0.00000001","discount":0},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":6.25e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.4-nano-20260317","model_id":"openai/gpt-5.4-nano","model_name":"OpenAI: GPT-5.4 Nano","context_length":400000,"pricing":{"prompt":"0.0000002","completion":"0.00000125","web_search":"0.01","input_cache_read":"0.00000002","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":75.47333875627612,"uptime_last_5m":92.97018157587873,"uptime_last_1d":85.00559682100567,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.4-nano-20260317","model_id":"openai/gpt-5.4-nano","model_name":"OpenAI: GPT-5.4 Nano","context_length":400000,"pricing":{"prompt":"0.0000002","completion":"0.00000125","web_search":"0.01","input_cache_read":"0.00000002","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.99609497032176,"uptime_last_5m":100,"uptime_last_1d":99.99227676175374,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.4-nano-20260317","model_id":"openai/gpt-5.4-nano","model_name":"OpenAI: GPT-5.4 Nano","context_length":400000,"pricing":{"prompt":"0.00000022","completion":"0.000001375","web_search":"0.01","input_cache_read":"0.000000022","discount":0},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.89172467130703,"uptime_last_5m":99.80430528375733,"uptime_last_1d":99.98203675233815,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":1.375e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-08,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.5749999999999997e-07,"_priciest_blended_per_m":5.665e-07,"_provider_spread_multiplier":2.2},{"id":"openai/gpt-5.4-mini","canonical_slug":"openai/gpt-5.4-mini-20260317","hugging_face_id":"","name":"OpenAI: GPT-5.4 Mini","created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.0000045","web_search":"0.01","input_cache_read":"0.000000075"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-08-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-mini-20260317/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":40.9,"coding_index":56.1,"agentic_index":31.5}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":7.5e-07,"_completion_per_m":4.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.4-mini-20260317","model_id":"openai/gpt-5.4-mini","model_name":"OpenAI: GPT-5.4 Mini","context_length":400000,"pricing":{"prompt":"0.000000375","completion":"0.00000225","web_search":"0.01","input_cache_read":"0.0000000375","discount":0},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.91789819376025,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.75e-07,"_completion_per_m":2.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.4-mini-20260317","model_id":"openai/gpt-5.4-mini","model_name":"OpenAI: GPT-5.4 Mini","context_length":400000,"pricing":{"prompt":"0.00000075","completion":"0.0000045","web_search":"0.01","input_cache_read":"0.000000075","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98411452942904,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":4.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.4-mini-20260317","model_id":"openai/gpt-5.4-mini","model_name":"OpenAI: GPT-5.4 Mini","context_length":400000,"pricing":{"prompt":"0.00000075","completion":"0.0000045","web_search":"0.01","input_cache_read":"0.000000075","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.52090484775147,"uptime_last_5m":99.61013645224172,"uptime_last_1d":99.62671684317279,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":4.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.4-mini-20260317","model_id":"openai/gpt-5.4-mini","model_name":"OpenAI: GPT-5.4 Mini","context_length":400000,"pricing":{"prompt":"0.000000825","completion":"0.00000495","web_search":"0.01","input_cache_read":"0.0000000825","discount":0},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.78641606151217,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.25e-07,"_completion_per_m":4.95e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8.25e-08,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.4-mini-20260317","model_id":"openai/gpt-5.4-mini","model_name":"OpenAI: GPT-5.4 Mini","context_length":400000,"pricing":{"prompt":"0.0000015","completion":"0.000009","web_search":"0.01","input_cache_read":"0.00000015","discount":0},"provider_name":"OpenAI","tag":"openai/fast","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-06,"_completion_per_m":9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":9.374999999999999e-07,"_priciest_blended_per_m":3.7499999999999997e-06,"_provider_spread_multiplier":4.0},{"id":"thinkingmachines/inkling-small","canonical_slug":"thinkingmachines/inkling-small-20260730","hugging_face_id":"thinkingmachines/Inkling-Small","name":"Thinking Machines: Inkling Small","created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","context_length":1048576,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000045","completion":"0.0000012","input_cache_read":"0.0000001"},"top_provider":{"context_length":524288,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/thinkingmachines/inkling-small-20260730/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":41.2,"coding_index":52.9,"agentic_index":31.9}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"},"_prompt_per_m":4.5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | thinkingmachines/inkling-small-20260730","model_id":"thinkingmachines/inkling-small","model_name":"Thinking Machines: Inkling Small","context_length":524288,"pricing":{"prompt":"0.00000045","completion":"0.0000012","input_cache_read":"0.0000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":262144,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.41110392483917,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"BaseTen | thinkingmachines/inkling-small-20260730","model_id":"thinkingmachines/inkling-small","model_name":"Thinking Machines: Inkling Small","context_length":1048576,"pricing":{"prompt":"0.0000005","completion":"0.0000012","input_cache_read":"0.0000001","discount":0},"provider_name":"BaseTen","tag":"baseten/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.97183363064501,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Together | thinkingmachines/inkling-small-20260730","model_id":"thinkingmachines/inkling-small","model_name":"Thinking Machines: Inkling Small","context_length":524288,"pricing":{"prompt":"0.0000005","completion":"0.0000012","input_cache_read":"0.0000001","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":471859,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":95.30335951863613,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":6.749999999999999e-07,"_priciest_blended_per_m":7.1e-07,"_provider_spread_multiplier":1.051851851851852},{"id":"minimax/minimax-m2.7","canonical_slug":"minimax/minimax-m2.7-20260318","hugging_face_id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax: MiniMax M2.7","created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006"},"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m2.7-20260318/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1238,"win_rate":50.7,"rank":37},{"arena":"models","category":"asciiart","elo":1167,"win_rate":47.9,"rank":36},{"arena":"models","category":"codecategories","elo":1259,"win_rate":52.3,"rank":33},{"arena":"models","category":"dataviz","elo":1251,"win_rate":52.6,"rank":30},{"arena":"models","category":"gamedev","elo":1244,"win_rate":51.7,"rank":35},{"arena":"models","category":"svg","elo":1177,"win_rate":49.4,"rank":41},{"arena":"models","category":"uicomponent","elo":1236,"win_rate":49.5,"rank":40},{"arena":"models","category":"website","elo":1265,"win_rate":52.9,"rank":32}],"artificial_analysis":{"intelligence_index":38.9,"coding_index":52.6,"agentic_index":25.9}},"reasoning":{"mandatory":true},"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mara | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":196608,"pricing":{"prompt":"0.00000024","completion":"0.00000096","discount":0.6},"provider_name":"Mara","tag":"mara","quantization":"unknown","max_completion_tokens":176947,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_k","top_p","tool_choice","tools","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.62311557788944,"uptime_last_5m":98.95287958115183,"uptime_last_1d":97.06082872509658,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.4e-07,"_completion_per_m":9.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":196608,"pricing":{"prompt":"0.00000025","completion":"0.000001","input_cache_read":"0.00000005","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9764846336125,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Novita | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":204800,"pricing":{"prompt":"0.00000027","completion":"0.00000108","input_cache_read":"0.000000054","discount":0.1},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.71112181030333,"uptime_last_5m":99.24242424242425,"uptime_last_1d":99.5298581326295,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":1.08e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.4e-08,"_cached_write_per_m":null},{"name":"AtlasCloud | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":196608,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":176947,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.32885906040269,"uptime_last_5m":null,"uptime_last_1d":99.44323494771406,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Minimax | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":204800,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"Minimax","tag":"minimax/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.77134146341463,"uptime_last_5m":100,"uptime_last_1d":99.33920002550735,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Fireworks | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":196608,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000059","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":176947,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":0,"uptime_last_5m":0,"uptime_last_1d":0.034048348655090224,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.9e-08,"_cached_write_per_m":null},{"name":"GMICloud | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":196608,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":176947,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-2,"uptime_last_30m":94.5945945945946,"uptime_last_5m":null,"uptime_last_1d":95.15039901780233,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"DeepInfra | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":196608,"pricing":{"prompt":"0.00000038","completion":"0.0000017","input_cache_read":"0.00000007","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/turbo","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":59.12661737523105,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.8e-07,"_completion_per_m":1.7e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"Groq | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":196608,"pricing":{"prompt":"0.0000006","completion":"0.0000018","discount":0},"provider_name":"Groq","tag":"groq","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.50124688279301,"uptime_last_5m":100,"uptime_last_1d":98.29825715225255,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":1.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SambaNova | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":196608,"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.00000006","discount":0},"provider_name":"SambaNova","tag":"sambanova","quantization":"unknown","max_completion_tokens":176947,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":73.42657342657343,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Minimax | minimax/minimax-m2.7-20260318","model_id":"minimax/minimax-m2.7","model_name":"MiniMax: MiniMax M2.7","context_length":204800,"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.00000006","discount":0},"provider_name":"Minimax","tag":"minimax/highspeed","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":96.88473520249221,"uptime_last_5m":100,"uptime_last_1d":98.69767913246174,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mara","_cheapest_blended_per_m":4.5599999999999995e-07,"_priciest_blended_per_m":1.1399999999999999e-06,"_provider_spread_multiplier":2.5},{"id":"mistralai/mistral-small-2603","canonical_slug":"mistralai/mistral-small-2603","hugging_face_id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral: Mistral Small 4","created":1773695685,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-2603/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":19.7,"coding_index":26.6,"agentic_index":4.6}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","none"],"default_effort":"high"},"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-small-2603","model_id":"mistralai/mistral-small-2603","model_name":"Mistral: Mistral Small 4","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.88839285714286,"uptime_last_5m":99.85590778097982,"uptime_last_1d":99.53389001905884,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-small-2603","model_id":"mistralai/mistral-small-2603","model_name":"Mistral: Mistral Small 4","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.78777589134125,"uptime_last_5m":100,"uptime_last_1d":99.47599183036172,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-small-2603","model_id":"mistralai/mistral-small-2603","model_name":"Mistral: Mistral Small 4","context_length":262144,"pricing":{"prompt":"0.000000165","completion":"0.00000066","input_cache_read":"0.0000000165","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.65e-07,"_completion_per_m":6.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.65e-08,"_cached_write_per_m":null},{"name":"Venice | mistralai/mistral-small-2603","model_id":"mistralai/mistral-small-2603","model_name":"Mistral: Mistral Small 4","context_length":256000,"pricing":{"prompt":"0.0000001875","completion":"0.00000075","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.95257666772052,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.875e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":2.8499999999999997e-07,"_priciest_blended_per_m":3.5625e-07,"_provider_spread_multiplier":1.25},{"id":"z-ai/glm-5-turbo","canonical_slug":"z-ai/glm-5-turbo-20260315","hugging_face_id":"","name":"Z.ai: GLM 5 Turbo","created":1773583573,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024"},"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2098-12-31","links":{"details":"/api/v1/models/z-ai/glm-5-turbo-20260315/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1295,"win_rate":57.6,"rank":18},{"arena":"models","category":"asciiart","elo":1176,"win_rate":49,"rank":34},{"arena":"models","category":"codecategories","elo":1291,"win_rate":55.5,"rank":20},{"arena":"models","category":"dataviz","elo":1286,"win_rate":57,"rank":17},{"arena":"models","category":"gamedev","elo":1291,"win_rate":55.9,"rank":22},{"arena":"models","category":"svg","elo":1247,"win_rate":56.5,"rank":16},{"arena":"models","category":"uicomponent","elo":1291,"win_rate":56.9,"rank":21},{"arena":"models","category":"website","elo":1288,"win_rate":54.6,"rank":22}]},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":1.2e-06,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.4e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Z.AI | z-ai/glm-5-turbo-20260315","model_id":"z-ai/glm-5-turbo","model_name":"Z.ai: GLM 5 Turbo","context_length":202752,"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024","discount":0},"provider_name":"Z.AI","tag":"z-ai","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format","top_k"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.2e-06,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.4e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Z.AI","_cheapest_blended_per_m":2.04e-06,"_priciest_blended_per_m":2.04e-06,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-small-2603:batch","canonical_slug":"mistralai/mistral-small-2603","hugging_face_id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral: Mistral Small 4 (batch)","created":1773695685,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-2603/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":19.7,"coding_index":26.6,"agentic_index":4.6}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","none"],"default_effort":"high"},"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-small-2603:batch","model_id":"mistralai/mistral-small-2603:batch","model_name":"Mistral: Mistral Small 4","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":2.8499999999999997e-07,"_priciest_blended_per_m":2.8499999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"minimax/minimax-m2.7:free","canonical_slug":"minimax/minimax-m2.7-20260318","hugging_face_id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax: MiniMax M2.7 (free)","created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","context_length":196608,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":196608,"max_completion_tokens":176947,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m2.7-20260318/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1238,"win_rate":50.7,"rank":37},{"arena":"models","category":"asciiart","elo":1167,"win_rate":47.9,"rank":36},{"arena":"models","category":"codecategories","elo":1259,"win_rate":52.3,"rank":33},{"arena":"models","category":"dataviz","elo":1251,"win_rate":52.6,"rank":30},{"arena":"models","category":"gamedev","elo":1244,"win_rate":51.7,"rank":35},{"arena":"models","category":"svg","elo":1177,"win_rate":49.4,"rank":41},{"arena":"models","category":"uicomponent","elo":1236,"win_rate":49.5,"rank":40},{"arena":"models","category":"website","elo":1265,"win_rate":52.9,"rank":32}],"artificial_analysis":{"intelligence_index":38.9,"coding_index":52.6,"agentic_index":25.9}},"reasoning":{"mandatory":true},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | minimax/minimax-m2.7-20260318:free","model_id":"minimax/minimax-m2.7:free","model_name":"MiniMax: MiniMax M2.7","context_length":196608,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":176947,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":98.5426211175643,"uptime_last_5m":97.9920518719933,"uptime_last_1d":98.47296746919169,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"nvidia/nemotron-3-super-120b-a12b:free","canonical_slug":"nvidia/nemotron-3-super-120b-a12b-20230311","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","name":"NVIDIA: Nemotron 3 Super (free)","created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":25.7,"coding_index":37.7,"agentic_index":8.8}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["medium","low"],"default_effort":"medium"},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Nvidia | nvidia/nemotron-3-super-120b-a12b-20230311:free","model_id":"nvidia/nemotron-3-super-120b-a12b:free","model_name":"NVIDIA: Nemotron 3 Super","context_length":262144,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"Nvidia","tag":"nvidia","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.65542256075445,"uptime_last_5m":99.73881246735155,"uptime_last_1d":99.7362151530745,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Nvidia","_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"bytedance-seed/seed-2.0-lite","canonical_slug":"bytedance-seed/seed-2.0-lite-20260309","hugging_face_id":null,"name":"ByteDance Seed: Seed-2.0-Lite","created":1773157231,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000002","overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000005","completion":"0.000004"}]},"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-2.0-lite-20260309/endpoints"},"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Seed | bytedance-seed/seed-2.0-lite-20260309","model_id":"bytedance-seed/seed-2.0-lite","model_name":"ByteDance Seed: Seed-2.0-Lite","context_length":262144,"pricing":{"prompt":"0.00000025","completion":"0.000002","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000005","completion":"0.000004"}]},"provider_name":"Seed","tag":"seed/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","structured_outputs","tool_choice","tools","response_format","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Seed","_cheapest_blended_per_m":7.75e-07,"_priciest_blended_per_m":7.75e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.5-9b","canonical_slug":"qwen/qwen3.5-9b-20260310","hugging_face_id":"Qwen/Qwen3.5-9B","name":"Qwen: Qwen3.5-9B","created":1773152396,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.00000015"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-9b-20260310/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":21.8,"coding_index":28.7,"agentic_index":7}},"reasoning":{"mandatory":false},"_prompt_per_m":1e-07,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | qwen/qwen3.5-9b-20260310","model_id":"qwen/qwen3.5-9b","model_name":"Qwen: Qwen3.5-9B","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.00000015","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":81920,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":99.7883202589964,"uptime_last_5m":99.57492029755579,"uptime_last_1d":98.53538283062645,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3.5-9b-20260310","model_id":"qwen/qwen3.5-9b","model_name":"Qwen: Qwen3.5-9B","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.00000015","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":97.79408284023668,"uptime_last_5m":98.47103793002057,"uptime_last_1d":96.82971681715561,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3.5-9b-20260310","model_id":"qwen/qwen3.5-9b","model_name":"Qwen: Qwen3.5-9B","context_length":256000,"pricing":{"prompt":"0.0000001","completion":"0.00000015","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.96116504854369,"uptime_last_5m":100,"uptime_last_1d":99.96200039868434,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen3.5-9b-20260310","model_id":"qwen/qwen3.5-9b","model_name":"Qwen: Qwen3.5-9B","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.00000025","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.56598814108442,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Together | qwen/qwen3.5-9b-20260310","model_id":"qwen/qwen3.5-9b","model_name":"Qwen: Qwen3.5-9B","context_length":262144,"pricing":{"prompt":"0.00000017","completion":"0.00000025","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.82078853046595,"uptime_last_5m":100,"uptime_last_1d":99.81425118610689,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.7e-07,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.1499999999999998e-07,"_priciest_blended_per_m":1.9399999999999996e-07,"_provider_spread_multiplier":1.6869565217391302},{"id":"inception/mercury-2","canonical_slug":"inception/mercury-2-20260304","hugging_face_id":null,"name":"Inception: Mercury 2","created":1772636275,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.00000075","input_cache_read":"0.000000025"},"top_provider":{"context_length":128000,"max_completion_tokens":50000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{"temperature":0.75,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/inception/mercury-2-20260304/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1020,"win_rate":23,"rank":100},{"arena":"models","category":"asciiart","elo":1038,"win_rate":28,"rank":59},{"arena":"models","category":"codecategories","elo":1030,"win_rate":21.2,"rank":106},{"arena":"models","category":"dataviz","elo":1019,"win_rate":22.1,"rank":100},{"arena":"models","category":"gamedev","elo":1008,"win_rate":19.6,"rank":106},{"arena":"models","category":"svg","elo":1027,"win_rate":25.2,"rank":76},{"arena":"models","category":"uicomponent","elo":1004,"win_rate":19.3,"rank":101},{"arena":"models","category":"website","elo":1036,"win_rate":21.2,"rank":108}],"artificial_analysis":{"intelligence_index":21.9,"coding_index":31.1,"agentic_index":9.5}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Inception | inception/mercury-2-20260304","model_id":"inception/mercury-2","model_name":"Inception: Mercury 2","context_length":128000,"pricing":{"prompt":"0.00000025","completion":"0.00000075","input_cache_read":"0.000000025","discount":0},"provider_name":"Inception","tag":"inception","quantization":"unknown","max_completion_tokens":50000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","temperature","tools","tool_choice","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99739112286072,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Inception","_cheapest_blended_per_m":4e-07,"_priciest_blended_per_m":4e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.4-pro","canonical_slug":"openai/gpt-5.4-pro-20260305","hugging_face_id":"","name":"OpenAI: GPT-5.4 Pro","created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00003","completion":"0.00018","web_search":"0.01","overrides":[{"min_prompt_tokens":272000,"prompt":"0.00006","completion":"0.00027"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"_prompt_per_m":3e-05,"_completion_per_m":0.00018,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.4-pro-20260305","model_id":"openai/gpt-5.4-pro","model_name":"OpenAI: GPT-5.4 Pro","context_length":1050000,"pricing":{"prompt":"0.000015","completion":"0.00009","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00003","completion":"0.000135"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-05,"_completion_per_m":9e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.4-pro-20260305","model_id":"openai/gpt-5.4-pro","model_name":"OpenAI: GPT-5.4 Pro","context_length":1050000,"pricing":{"prompt":"0.00003","completion":"0.00018","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00006","completion":"0.00027"}]},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-05,"_completion_per_m":0.00018,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.4-pro-20260305","model_id":"openai/gpt-5.4-pro","model_name":"OpenAI: GPT-5.4 Pro","context_length":1050000,"pricing":{"prompt":"0.00003","completion":"0.00018","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00006","completion":"0.00027"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.38993390950687,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-05,"_completion_per_m":0.00018,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":3.7500000000000003e-05,"_priciest_blended_per_m":7.500000000000001e-05,"_provider_spread_multiplier":2.0},{"id":"nvidia/nemotron-3-super-120b-a12b","canonical_slug":"nvidia/nemotron-3-super-120b-a12b-20230311","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","name":"NVIDIA: Nemotron 3 Super","created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000085","completion":"0.0000004"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":25.7,"coding_index":37.7,"agentic_index":8.8}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["medium","low"],"default_effort":"medium"},"_prompt_per_m":8.5e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | nvidia/nemotron-3-super-120b-a12b-20230311","model_id":"nvidia/nemotron-3-super-120b-a12b","model_name":"NVIDIA: Nemotron 3 Super","context_length":262144,"pricing":{"prompt":"0.000000085","completion":"0.0000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97515047766305,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.5e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DigitalOcean | nvidia/nemotron-3-super-120b-a12b-20230311","model_id":"nvidia/nemotron-3-super-120b-a12b","model_name":"NVIDIA: Nemotron 3 Super","context_length":1000000,"pricing":{"prompt":"0.0000003","completion":"0.00000065","input_cache_read":"0.00000006","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":900000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","structured_outputs","response_format","tool_choice","tools","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.2861816667658,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":6.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.7949999999999999e-07,"_priciest_blended_per_m":4.05e-07,"_provider_spread_multiplier":2.256267409470752},{"id":"google/gemini-3.1-flash-lite-preview","canonical_slug":"google/gemini-3.1-flash-lite-preview-20260303","hugging_face_id":"","name":"Google: Gemini 3.1 Flash Lite Preview","created":1772512673,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-lite-preview-20260303/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1092,"win_rate":38.7,"rank":88},{"arena":"models","category":"asciiart","elo":1193,"win_rate":50.7,"rank":24},{"arena":"models","category":"codecategories","elo":1096,"win_rate":36.5,"rank":92},{"arena":"models","category":"dataviz","elo":1066,"win_rate":33.3,"rank":95},{"arena":"models","category":"gamedev","elo":1065,"win_rate":33.7,"rank":96},{"arena":"models","category":"svg","elo":1092,"win_rate":42.5,"rank":59},{"arena":"models","category":"uicomponent","elo":1098,"win_rate":37.7,"rank":86},{"arena":"models","category":"website","elo":1102,"win_rate":36.6,"rank":93}],"artificial_analysis":{"intelligence_index":25.6,"coding_index":34.7,"agentic_index":6.5}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"},"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":2.5e-07,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":8.33333333333333e-08,"_endpoints":[{"name":"Google AI Studio | google/gemini-3.1-flash-lite-preview-20260303","model_id":"google/gemini-3.1-flash-lite-preview","model_name":"Google: Gemini 3.1 Flash Lite Preview","context_length":1048576,"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.06385427952328,"uptime_last_5m":99.17837837837837,"uptime_last_1d":98.6881358456412,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":2.5e-07,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-3.1-flash-lite-preview-20260303","model_id":"google/gemini-3.1-flash-lite-preview","model_name":"Google: Gemini 3.1 Flash Lite Preview","context_length":1048576,"pricing":{"prompt":"0.000000125","completion":"0.00000075","image":"0.000000125","audio":"0.00000025","input_audio_cache":"0.000000025","web_search":"0.014","internal_reasoning":"0.00000075","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.06385427952328,"uptime_last_5m":99.17837837837837,"uptime_last_1d":98.6881358456412,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-07,"_completion_per_m":7.5e-07,"_image_per_m":1.25e-07,"_request_per_m":null,"_cached_read_per_m":1.25e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-3.1-flash-lite-preview-20260303","model_id":"google/gemini-3.1-flash-lite-preview","model_name":"Google: Gemini 3.1 Flash Lite Preview","context_length":1048576,"pricing":{"prompt":"0.00000045","completion":"0.0000027","image":"0.00000045","audio":"0.0000009","input_audio_cache":"0.00000009","web_search":"0.014","internal_reasoning":"0.0000027","input_cache_read":"0.000000045","input_cache_write":"0.00000015","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.06385427952328,"uptime_last_5m":99.17837837837837,"uptime_last_1d":98.6881358456412,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":2.7e-06,"_image_per_m":4.5e-07,"_request_per_m":null,"_cached_read_per_m":4.5e-08,"_cached_write_per_m":1.5e-07}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":3.1249999999999997e-07,"_priciest_blended_per_m":1.1249999999999998e-06,"_provider_spread_multiplier":3.5999999999999996},{"id":"qwen/qwen3.5-35b-a3b","canonical_slug":"qwen/qwen3.5-35b-a3b-20260224","hugging_face_id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen: Qwen3.5-35B-A3B","created":1772053822,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.00000125","input_cache_read":"0.00000025"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-35b-a3b-20260224/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":24.3,"coding_index":37,"agentic_index":11.8}},"reasoning":{"mandatory":false},"_prompt_per_m":2.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Darkbloom | qwen/qwen3.5-35b-a3b-20260224","model_id":"qwen/qwen3.5-35b-a3b","model_name":"Qwen: Qwen3.5-35B-A3B","context_length":262144,"pricing":{"prompt":"0.00000008","completion":"0.00000075","discount":0},"provider_name":"Darkbloom","tag":"darkbloom/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","structured_outputs","logprobs","top_logprobs","tools","response_format","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.42694479443745,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-08,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3.5-35b-a3b-20260224","model_id":"qwen/qwen3.5-35b-a3b","model_name":"Qwen: Qwen3.5-35B-A3B","context_length":262144,"pricing":{"prompt":"0.00000014","completion":"0.000001","input_cache_read":"0.00000005","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":81920,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.90996784565917,"uptime_last_5m":98.38998211091234,"uptime_last_1d":95.47467950083053,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen3.5-35b-a3b-20260224","model_id":"qwen/qwen3.5-35b-a3b","model_name":"Qwen: Qwen3.5-35B-A3B","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.000001","input_cache_read":"0.00000005","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.38870909744696,"uptime_last_5m":100,"uptime_last_1d":99.64009161304396,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3.5-35b-a3b-20260224","model_id":"qwen/qwen3.5-35b-a3b","model_name":"Qwen: Qwen3.5-35B-A3B","context_length":262144,"pricing":{"prompt":"0.0000001625","completion":"0.0000013","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":258048,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_logprobs","logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.77246871444824,"uptime_last_5m":100,"uptime_last_1d":99.37106918238993,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.625e-07,"_completion_per_m":1.3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"AtlasCloud | qwen/qwen3.5-35b-a3b-20260224","model_id":"qwen/qwen3.5-35b-a3b","model_name":"Qwen: Qwen3.5-35B-A3B","context_length":262144,"pricing":{"prompt":"0.000000225","completion":"0.0000018","input_cache_read":"0.000000225","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.76790800717376,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.25e-07,"_completion_per_m":1.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.25e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3.5-35b-a3b-20260224","model_id":"qwen/qwen3.5-35b-a3b","model_name":"Qwen: Qwen3.5-35B-A3B","context_length":262144,"pricing":{"prompt":"0.00000024","completion":"0.0000018","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.14529914529915,"uptime_last_5m":null,"uptime_last_1d":94.75751366120218,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.4e-07,"_completion_per_m":1.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"CoreWeave | qwen/qwen3.5-35b-a3b-20260224","model_id":"qwen/qwen3.5-35b-a3b","model_name":"Qwen: Qwen3.5-35B-A3B","context_length":262144,"pricing":{"prompt":"0.00000025","completion":"0.00000125","input_cache_read":"0.00000025","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.95746979780911,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3.5-35b-a3b-20260224","model_id":"qwen/qwen3.5-35b-a3b","model_name":"Qwen: Qwen3.5-35B-A3B","context_length":256000,"pricing":{"prompt":"0.0000003125","completion":"0.00000125","input_cache_read":"0.00000015625","discount":0},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tool_choice","logprobs","response_format","structured_outputs","tools","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.84756097560977,"uptime_last_5m":100,"uptime_last_1d":99.7518452532451,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.125e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5625e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Darkbloom","_cheapest_blended_per_m":2.81e-07,"_priciest_blended_per_m":7.079999999999998e-07,"_provider_spread_multiplier":2.5195729537366542},{"id":"bytedance-seed/seed-2.0-mini","canonical_slug":"bytedance-seed/seed-2.0-mini-20260224","hugging_face_id":"","name":"ByteDance Seed: Seed-2.0-Mini","created":1772131107,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000004","overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000002","completion":"0.0000008"}]},"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-2.0-mini-20260224/endpoints"},"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Seed | bytedance-seed/seed-2.0-mini-20260224","model_id":"bytedance-seed/seed-2.0-mini","model_name":"ByteDance Seed: Seed-2.0-Mini","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000002","completion":"0.0000008"}]},"provider_name":"Seed","tag":"seed/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Seed","_cheapest_blended_per_m":1.8999999999999998e-07,"_priciest_blended_per_m":1.8999999999999998e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.4","canonical_slug":"openai/gpt-5.4-20260305","hugging_face_id":"","name":"OpenAI: GPT-5.4","created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.000015","web_search":"0.01","input_cache_read":"0.00000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000005","completion":"0.0000225","input_cache_read":"0.0000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-20260305/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1146,"win_rate":42.4,"rank":67},{"arena":"models","category":"asciiart","elo":1225,"win_rate":55.4,"rank":19},{"arena":"models","category":"codecategories","elo":1236,"win_rate":52.5,"rank":40},{"arena":"models","category":"dataviz","elo":1256,"win_rate":56.6,"rank":27},{"arena":"models","category":"gamedev","elo":1274,"win_rate":57.6,"rank":26},{"arena":"models","category":"svg","elo":1234,"win_rate":57.8,"rank":19},{"arena":"models","category":"uicomponent","elo":1266,"win_rate":57.4,"rank":29},{"arena":"models","category":"website","elo":1240,"win_rate":52.5,"rank":40},{"arena":"agents","category":"androidnative","elo":1057,"win_rate":47.4,"rank":35},{"arena":"agents","category":"fullstack","elo":1041,"win_rate":40.8,"rank":37},{"arena":"agents","category":"godotgamedev","elo":1135,"win_rate":46.9,"rank":22},{"arena":"agents","category":"mobileapps","elo":1127,"win_rate":46.1,"rank":36},{"arena":"agents","category":"webapps","elo":1090,"win_rate":40.3,"rank":33}],"artificial_analysis":{"intelligence_index":53.1,"coding_index":71.1,"agentic_index":44.2}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":2.5e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.4-20260305","model_id":"openai/gpt-5.4","model_name":"OpenAI: GPT-5.4","context_length":1050000,"pricing":{"prompt":"0.00000125","completion":"0.0000075","web_search":"0.01","input_cache_read":"0.000000125","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000025","completion":"0.00001125","input_cache_read":"0.00000025"}]},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":89.79558728098638,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":7.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.4-20260305","model_id":"openai/gpt-5.4","model_name":"OpenAI: GPT-5.4","context_length":1050000,"pricing":{"prompt":"0.0000025","completion":"0.000015","web_search":"0.01","input_cache_read":"0.00000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000005","completion":"0.0000225","input_cache_read":"0.0000005"}]},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.37531642758805,"uptime_last_5m":96.43446682073291,"uptime_last_1d":97.13864325950374,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.4-20260305","model_id":"openai/gpt-5.4","model_name":"OpenAI: GPT-5.4","context_length":1050000,"pricing":{"prompt":"0.0000025","completion":"0.000015","web_search":"0.01","input_cache_read":"0.00000025","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000005","completion":"0.0000225","input_cache_read":"0.0000005"}]},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96403740110286,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.4-20260305","model_id":"openai/gpt-5.4","model_name":"OpenAI: GPT-5.4","context_length":1050000,"pricing":{"prompt":"0.00000275","completion":"0.0000165","web_search":"0.01","input_cache_read":"0.000000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000055","completion":"0.00002475","input_cache_read":"0.00000055"}]},"provider_name":"Azure","tag":"azure/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.75e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.75e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.4-20260305","model_id":"openai/gpt-5.4","model_name":"OpenAI: GPT-5.4","context_length":1050000,"pricing":{"prompt":"0.00000275","completion":"0.0000165","web_search":"0.01","input_cache_read":"0.000000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000055","completion":"0.00002475","input_cache_read":"0.00000055"}]},"provider_name":"Azure","tag":"azure/eu","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.96534396118524,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.75e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.75e-07,"_cached_write_per_m":null},{"name":"Amazon Bedrock | openai/gpt-5.4-20260305","model_id":"openai/gpt-5.4","model_name":"OpenAI: GPT-5.4","context_length":1050000,"pricing":{"prompt":"0.00000275","completion":"0.0000165","web_search":"0.01","input_cache_read":"0.000000275","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000055","completion":"0.00002475","input_cache_read":"0.00000055"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us-east-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.75e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.75e-07,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.4-20260305","model_id":"openai/gpt-5.4","model_name":"OpenAI: GPT-5.4","context_length":1050000,"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001"}]},"provider_name":"OpenAI","tag":"openai/fast","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":922000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":3.125e-06,"_priciest_blended_per_m":1.25e-05,"_provider_spread_multiplier":4.0},{"id":"google/gemini-3.1-flash-image-preview","canonical_slug":"google/gemini-3.1-flash-image-preview-20260226","hugging_face_id":"","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","created":1772119558,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000003","image_output":"0.00006","web_search":"0.014"},"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-image-preview-20260226/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1283,"win_rate":66.3,"rank":2},{"arena":"models","category":"image","elo":1294,"win_rate":65.1,"rank":2},{"arena":"models","category":"logo","elo":1273,"win_rate":62.9,"rank":2}]},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal"],"default_effort":"minimal"},"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Google AI Studio | google/gemini-3.1-flash-image-preview-20260226","model_id":"google/gemini-3.1-flash-image-preview","model_name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","context_length":65536,"pricing":{"prompt":"0.0000005","completion":"0.000003","image_output":"0.00006","web_search":"0.014","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":58982,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.90435198469632,"uptime_last_5m":100,"uptime_last_1d":99.9712336648311,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":1.2499999999999999e-06,"_priciest_blended_per_m":1.2499999999999999e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.5-27b","canonical_slug":"qwen/qwen3.5-27b-20260224","hugging_face_id":"Qwen/Qwen3.5-27B","name":"Qwen: Qwen3.5-27B","created":1772053810,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.000000195","completion":"0.00000156"},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-27b-20260224/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1.95e-07,"_completion_per_m":1.56e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3.5-27b-20260224","model_id":"qwen/qwen3.5-27b","model_name":"Qwen: Qwen3.5-27B","context_length":262144,"pricing":{"prompt":"0.000000195","completion":"0.00000156","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":258048,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_logprobs","logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.69278033794163,"uptime_last_5m":100,"uptime_last_1d":98.00779231961427,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.95e-07,"_completion_per_m":1.56e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3.5-27b-20260224","model_id":"qwen/qwen3.5-27b","model_name":"Qwen: Qwen3.5-27B","context_length":262144,"pricing":{"prompt":"0.00000025","completion":"0.000002","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":99.41792782305005,"uptime_last_5m":99.8003992015968,"uptime_last_1d":98.69090138628246,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3.5-27b-20260224","model_id":"qwen/qwen3.5-27b","model_name":"Qwen: Qwen3.5-27B","context_length":262144,"pricing":{"prompt":"0.00000026","completion":"0.0000026","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":81920,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.92867332382312,"uptime_last_5m":100,"uptime_last_1d":99.33893687621851,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-07,"_completion_per_m":2.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"AtlasCloud | qwen/qwen3.5-27b-20260224","model_id":"qwen/qwen3.5-27b","model_name":"Qwen: Qwen3.5-27B","context_length":262144,"pricing":{"prompt":"0.00000027","completion":"0.00000216","input_cache_read":"0.00000027","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.73658725547162,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":2.16e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.7e-07,"_cached_write_per_m":null},{"name":"Phala | qwen/qwen3.5-27b-20260224","model_id":"qwen/qwen3.5-27b","model_name":"Qwen: Qwen3.5-27B","context_length":262144,"pricing":{"prompt":"0.0000003","completion":"0.0000024","input_cache_read":"0.00000015","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":92.91524224920428,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3.5-27b-20260224","model_id":"qwen/qwen3.5-27b","model_name":"Qwen: Qwen3.5-27B","context_length":262144,"pricing":{"prompt":"0.0000003","completion":"0.0000024","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.50617283950616,"uptime_last_5m":100,"uptime_last_1d":99.70603024794028,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":6.045e-07,"_priciest_blended_per_m":9.62e-07,"_provider_spread_multiplier":1.5913978494623657},{"id":"google/gemini-3.1-pro-preview-customtools","canonical_slug":"google/gemini-3.1-pro-preview-customtools-20260219","hugging_face_id":null,"name":"Google: Gemini 3.1 Pro Preview Custom Tools","created":1772045923,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000018","audio":"0.000004","input_audio_cache":"0.0000004","input_cache_read":"0.0000004"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-pro-preview-customtools-20260219/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07,"_endpoints":[{"name":"Google AI Studio | google/gemini-3.1-pro-preview-customtools-20260219","model_id":"google/gemini-3.1-pro-preview-customtools","model_name":"Google: Gemini 3.1 Pro Preview Custom Tools","context_length":1048576,"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000018","audio":"0.000004","input_audio_cache":"0.0000004","input_cache_read":"0.0000004"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.91007194244604,"uptime_last_5m":100,"uptime_last_1d":99.8119417019276,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":4.9999999999999996e-06,"_priciest_blended_per_m":4.9999999999999996e-06,"_provider_spread_multiplier":1.0},{"id":"aion-labs/aion-2.0","canonical_slug":"aion-labs/aion-2.0-20260223","hugging_face_id":null,"name":"AionLabs: Aion-2.0","created":1771881306,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000008","completion":"0.0000016","input_cache_read":"0.0000002"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/aion-labs/aion-2.0-20260223/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":8e-07,"_completion_per_m":1.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"AionLabs | aion-labs/aion-2.0-20260223","model_id":"aion-labs/aion-2.0","model_name":"AionLabs: Aion-2.0","context_length":131072,"pricing":{"prompt":"0.0000008","completion":"0.0000016","input_cache_read":"0.0000002","discount":0},"provider_name":"AionLabs","tag":"aion-labs","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":1.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"AionLabs","_cheapest_blended_per_m":1.0399999999999998e-06,"_priciest_blended_per_m":1.0399999999999998e-06,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.3-codex","canonical_slug":"openai/gpt-5.3-codex-20260224","hugging_face_id":"","name":"OpenAI: GPT-5.3-Codex","created":1771959164,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.3-codex-20260224/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1084,"win_rate":35.2,"rank":31},{"arena":"agents","category":"fullstack","elo":1006,"win_rate":36.5,"rank":40},{"arena":"agents","category":"godotgamedev","elo":1124,"win_rate":45.1,"rank":24},{"arena":"agents","category":"mobileapps","elo":1094,"win_rate":41.4,"rank":39},{"arena":"agents","category":"webapps","elo":1063,"win_rate":36.9,"rank":35},{"arena":"models","category":"3d","elo":1052,"win_rate":35.3,"rank":94},{"arena":"models","category":"asciiart","elo":1178,"win_rate":51.2,"rank":31},{"arena":"models","category":"codecategories","elo":1169,"win_rate":47.2,"rank":68},{"arena":"models","category":"dataviz","elo":1185,"win_rate":50.6,"rank":59},{"arena":"models","category":"gamedev","elo":1198,"win_rate":51.3,"rank":52},{"arena":"models","category":"svg","elo":1169,"win_rate":54,"rank":44},{"arena":"models","category":"uicomponent","elo":1163,"win_rate":47.3,"rank":67},{"arena":"models","category":"website","elo":1182,"win_rate":48.6,"rank":67}]},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.3-codex-20260224","model_id":"openai/gpt-5.3-codex","model_name":"OpenAI: GPT-5.3-Codex","context_length":400000,"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.24605894448251,"uptime_last_5m":99.5850622406639,"uptime_last_1d":99.77750862318649,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.3-codex-20260224","model_id":"openai/gpt-5.3-codex","model_name":"OpenAI: GPT-5.3-Codex","context_length":400000,"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.3-codex-20260224","model_id":"openai/gpt-5.3-codex","model_name":"OpenAI: GPT-5.3-Codex","context_length":400000,"pricing":{"prompt":"0.0000035","completion":"0.000028","web_search":"0.01","input_cache_read":"0.00000035","discount":0},"provider_name":"OpenAI","tag":"openai/fast","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-06,"_completion_per_m":2.8e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":5.425e-06,"_priciest_blended_per_m":1.085e-05,"_provider_spread_multiplier":2.0},{"id":"google/gemini-3.1-pro-preview","canonical_slug":"google/gemini-3.1-pro-preview-20260219","hugging_face_id":"","name":"Google: Gemini 3.1 Pro Preview","created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000018","audio":"0.000004","input_audio_cache":"0.0000004","input_cache_read":"0.0000004"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1114,"win_rate":44.4,"rank":22},{"arena":"agents","category":"agentichtmlslides","elo":1226,"win_rate":55.8,"rank":5},{"arena":"agents","category":"agenticslides","elo":1112,"win_rate":33.8,"rank":8},{"arena":"agents","category":"agenticslides(html)","elo":1219,"win_rate":54.4,"rank":5},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1107,"win_rate":33.9,"rank":8},{"arena":"agents","category":"androidnative","elo":1075,"win_rate":41.4,"rank":33},{"arena":"agents","category":"fullstack","elo":1094,"win_rate":42.1,"rank":28},{"arena":"agents","category":"godotgamedev","elo":1236,"win_rate":60,"rank":6},{"arena":"agents","category":"htmlslides","elo":1169,"win_rate":48.9,"rank":16},{"arena":"agents","category":"mobileapps","elo":1131,"win_rate":43.8,"rank":32},{"arena":"agents","category":"pptxslides","elo":1110,"win_rate":34.1,"rank":8},{"arena":"agents","category":"python-pptxslides","elo":1109,"win_rate":31.9,"rank":20},{"arena":"agents","category":"webapps","elo":1156,"win_rate":45.2,"rank":27},{"arena":"models","category":"3d","elo":1279,"win_rate":59.2,"rank":26},{"arena":"models","category":"asciiart","elo":1298,"win_rate":63.7,"rank":7},{"arena":"models","category":"codecategories","elo":1268,"win_rate":64.4,"rank":29},{"arena":"models","category":"dataviz","elo":1259,"win_rate":61.8,"rank":26},{"arena":"models","category":"gamedev","elo":1238,"win_rate":53.4,"rank":38},{"arena":"models","category":"svg","elo":1327,"win_rate":68.5,"rank":4},{"arena":"models","category":"uicomponent","elo":1306,"win_rate":69.4,"rank":13},{"arena":"models","category":"website","elo":1272,"win_rate":64.4,"rank":28}],"artificial_analysis":{"intelligence_index":47.7,"coding_index":68.8,"agentic_index":23}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07,"_endpoints":[{"name":"Google AI Studio | google/gemini-3.1-pro-preview-20260219","model_id":"google/gemini-3.1-pro-preview","model_name":"Google: Gemini 3.1 Pro Preview","context_length":1048576,"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000018","audio":"0.000004","input_audio_cache":"0.0000004","input_cache_read":"0.0000004"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.75510204081633,"uptime_last_5m":99.35691318327974,"uptime_last_1d":99.41862477073745,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07},{"name":"Google AI Studio | google/gemini-3.1-pro-preview-20260219","model_id":"google/gemini-3.1-pro-preview","model_name":"Google: Gemini 3.1 Pro Preview","context_length":1048576,"pricing":{"prompt":"0.000001","completion":"0.000006","image":"0.000001","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.000006","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000002","completion":"0.000009","audio":"0.000002","input_audio_cache":"0.0000002","input_cache_read":"0.0000002"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.75510204081633,"uptime_last_5m":99.35691318327974,"uptime_last_1d":99.41862477073745,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":6e-06,"_image_per_m":1e-06,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.875e-07},{"name":"Google AI Studio | google/gemini-3.1-pro-preview-20260219","model_id":"google/gemini-3.1-pro-preview","model_name":"Google: Gemini 3.1 Pro Preview","context_length":1048576,"pricing":{"prompt":"0.0000036","completion":"0.0000216","image":"0.0000036","audio":"0.0000036","input_audio_cache":"0.00000036","web_search":"0.014","internal_reasoning":"0.0000216","input_cache_read":"0.00000036","input_cache_write":"0.000000675","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000072","completion":"0.0000324","audio":"0.0000072","input_audio_cache":"0.00000072","input_cache_read":"0.00000072"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.75510204081633,"uptime_last_5m":99.35691318327974,"uptime_last_1d":99.41862477073745,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.6e-06,"_completion_per_m":2.16e-05,"_image_per_m":3.6e-06,"_request_per_m":null,"_cached_read_per_m":3.6e-07,"_cached_write_per_m":6.75e-07},{"name":"Google | google/gemini-3.1-pro-preview-20260219","model_id":"google/gemini-3.1-pro-preview","model_name":"Google: Gemini 3.1 Pro Preview","context_length":1048576,"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000018","audio":"0.000004","input_audio_cache":"0.0000004","input_cache_read":"0.0000004"}]},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.4275858147425,"uptime_last_5m":99.1230592294422,"uptime_last_1d":96.47836065910302,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07},{"name":"Google | google/gemini-3.1-pro-preview-20260219","model_id":"google/gemini-3.1-pro-preview","model_name":"Google: Gemini 3.1 Pro Preview","context_length":1048576,"pricing":{"prompt":"0.000001","completion":"0.000006","image":"0.000001","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.000006","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000002","completion":"0.000009","audio":"0.000002","input_audio_cache":"0.0000002","input_cache_read":"0.0000002"}]},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.4275858147425,"uptime_last_5m":99.1230592294422,"uptime_last_1d":96.47836065910302,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":6e-06,"_image_per_m":1e-06,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.875e-07},{"name":"Google | google/gemini-3.1-pro-preview-20260219","model_id":"google/gemini-3.1-pro-preview","model_name":"Google: Gemini 3.1 Pro Preview","context_length":1048576,"pricing":{"prompt":"0.0000036","completion":"0.0000216","image":"0.0000036","audio":"0.0000036","input_audio_cache":"0.00000036","web_search":"0.014","internal_reasoning":"0.0000216","input_cache_read":"0.00000036","input_cache_write":"0.000000675","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000072","completion":"0.0000324","audio":"0.0000072","input_audio_cache":"0.00000072","input_cache_read":"0.00000072"}]},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.4275858147425,"uptime_last_5m":99.1230592294422,"uptime_last_1d":96.47836065910302,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.6e-06,"_completion_per_m":2.16e-05,"_image_per_m":3.6e-06,"_request_per_m":null,"_cached_read_per_m":3.6e-07,"_cached_write_per_m":6.75e-07}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":2.4999999999999998e-06,"_priciest_blended_per_m":8.999999999999999e-06,"_provider_spread_multiplier":3.5999999999999996},{"id":"qwen/qwen3.5-122b-a10b","canonical_slug":"qwen/qwen3.5-122b-a10b-20260224","hugging_face_id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen: Qwen3.5-122B-A10B","created":1772053789,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000026","completion":"0.00000208"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-122b-a10b-20260224/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":32.8,"coding_index":45.7,"agentic_index":21.3}},"reasoning":{"mandatory":false},"_prompt_per_m":2.6e-07,"_completion_per_m":2.08e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"SiliconFlow | qwen/qwen3.5-122b-a10b-20260224","model_id":"qwen/qwen3.5-122b-a10b","model_name":"Qwen: Qwen3.5-122B-A10B","context_length":262144,"pricing":{"prompt":"0.00000026","completion":"0.00000208","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","structured_outputs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.52941176470588,"uptime_last_5m":100,"uptime_last_1d":99.60990121239335,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-07,"_completion_per_m":2.08e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3.5-122b-a10b-20260224","model_id":"qwen/qwen3.5-122b-a10b","model_name":"Qwen: Qwen3.5-122B-A10B","context_length":262144,"pricing":{"prompt":"0.00000026","completion":"0.00000208","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":258048,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":95.70707070707071,"uptime_last_5m":85.6,"uptime_last_1d":99.60657416891704,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-07,"_completion_per_m":2.08e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3.5-122b-a10b-20260224","model_id":"qwen/qwen3.5-122b-a10b","model_name":"Qwen: Qwen3.5-122B-A10B","context_length":262144,"pricing":{"prompt":"0.00000029","completion":"0.0000024","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":81920,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.8792270531401,"uptime_last_5m":100,"uptime_last_1d":99.14500683994528,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.9e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"AtlasCloud | qwen/qwen3.5-122b-a10b-20260224","model_id":"qwen/qwen3.5-122b-a10b","model_name":"Qwen: Qwen3.5-122B-A10B","context_length":262144,"pricing":{"prompt":"0.0000003","completion":"0.0000024","input_cache_read":"0.0000003","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.79779824758481,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3.5-122b-a10b-20260224","model_id":"qwen/qwen3.5-122b-a10b","model_name":"Qwen: Qwen3.5-122B-A10B","context_length":262144,"pricing":{"prompt":"0.0000004","completion":"0.0000032","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.59514170040485,"uptime_last_5m":98.63013698630137,"uptime_last_1d":99.8051965145971,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"SiliconFlow","_cheapest_blended_per_m":8.06e-07,"_priciest_blended_per_m":1.24e-06,"_provider_spread_multiplier":1.5384615384615385},{"id":"qwen/qwen3.5-flash-02-23","canonical_slug":"qwen/qwen3.5-flash-20260224","hugging_face_id":null,"name":"Qwen: Qwen3.5-Flash","created":1772053776,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.000000065","completion":"0.00000026"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-flash-20260224/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":6.5e-08,"_completion_per_m":2.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3.5-flash-20260224","model_id":"qwen/qwen3.5-flash-02-23","model_name":"Qwen: Qwen3.5-Flash","context_length":1000000,"pricing":{"prompt":"0.000000065","completion":"0.00000026","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99953625958989,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.5e-08,"_completion_per_m":2.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":1.235e-07,"_priciest_blended_per_m":1.235e-07,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-sonnet-4.6","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","hugging_face_id":"","name":"Anthropic: Claude Sonnet 4.6","created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1176,"win_rate":52.2,"rank":15},{"arena":"agents","category":"androidnative","elo":1221,"win_rate":62,"rank":12},{"arena":"agents","category":"fullstack","elo":1237,"win_rate":64.3,"rank":12},{"arena":"agents","category":"godotgamedev","elo":1226,"win_rate":60.6,"rank":7},{"arena":"agents","category":"mobileapps","elo":1252,"win_rate":63.6,"rank":6},{"arena":"agents","category":"webapps","elo":1221,"win_rate":57,"rank":20},{"arena":"models","category":"3d","elo":1279,"win_rate":57.6,"rank":25},{"arena":"models","category":"asciiart","elo":1260,"win_rate":60.1,"rank":13},{"arena":"models","category":"codecategories","elo":1301,"win_rate":59.4,"rank":13},{"arena":"models","category":"dataviz","elo":1300,"win_rate":58.3,"rank":12},{"arena":"models","category":"gamedev","elo":1296,"win_rate":58.8,"rank":20},{"arena":"models","category":"svg","elo":1237,"win_rate":58.8,"rank":18},{"arena":"models","category":"uicomponent","elo":1298,"win_rate":58.3,"rank":17},{"arena":"models","category":"website","elo":1305,"win_rate":60,"rank":11}],"artificial_analysis":{"intelligence_index":48.4,"coding_index":63,"agentic_index":42.1}},"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low"],"default_effort":"medium"},"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06,"_endpoints":[{"name":"Claude Platform on AWS | anthropic/claude-4.6-sonnet-20260217","model_id":"anthropic/claude-sonnet-4.6","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0},"provider_name":"Claude Platform on AWS","tag":"claude-on-aws","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98290598290598,"uptime_last_5m":100,"uptime_last_1d":99.98098609601651,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Anthropic | anthropic/claude-4.6-sonnet-20260217","model_id":"anthropic/claude-sonnet-4.6","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.67288191036965,"uptime_last_5m":100,"uptime_last_1d":99.82826862058813,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Amazon Bedrock | anthropic/claude-4.6-sonnet-20260217","model_id":"anthropic/claude-sonnet-4.6","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97100849037068,"uptime_last_5m":100,"uptime_last_1d":99.95348190350133,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Azure | anthropic/claude-4.6-sonnet-20260217","model_id":"anthropic/claude-sonnet-4.6","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0},"provider_name":"Azure","tag":"azure/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","response_format","verbosity","top_k","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Google | anthropic/claude-4.6-sonnet-20260217","model_id":"anthropic/claude-sonnet-4.6","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.95718953677331,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Amazon Bedrock | anthropic/claude-4.6-sonnet-20260217","model_id":"anthropic/claude-sonnet-4.6","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.0000033","completion":"0.0000165","web_search":"0.01","input_cache_read":"0.00000033","input_cache_write":"0.000004125","input_cache_write_1h":"0.0000066","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-07,"_cached_write_per_m":4.125e-06},{"name":"Amazon Bedrock | anthropic/claude-4.6-sonnet-20260217","model_id":"anthropic/claude-sonnet-4.6","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.0000033","completion":"0.0000165","web_search":"0.01","input_cache_read":"0.00000033","input_cache_write":"0.000004125","input_cache_write_1h":"0.0000066","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-07,"_cached_write_per_m":4.125e-06},{"name":"Google | anthropic/claude-4.6-sonnet-20260217","model_id":"anthropic/claude-sonnet-4.6","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.0000033","completion":"0.0000165","web_search":"0.01","input_cache_read":"0.00000033","input_cache_write":"0.000004125","input_cache_write_1h":"0.0000066","discount":0},"provider_name":"Google","tag":"google-vertex/us-east5","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.52380952380952,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-07,"_cached_write_per_m":4.125e-06},{"name":"Google | anthropic/claude-4.6-sonnet-20260217","model_id":"anthropic/claude-sonnet-4.6","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.0000033","completion":"0.0000165","web_search":"0.01","input_cache_read":"0.00000033","input_cache_write":"0.000004125","input_cache_write_1h":"0.0000066","discount":0},"provider_name":"Google","tag":"google-vertex/europe","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.66442953020133,"uptime_last_5m":null,"uptime_last_1d":99.92102665350444,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-07,"_cached_write_per_m":4.125e-06}],"_cheapest_provider":"Claude Platform on AWS","_cheapest_blended_per_m":6.5999999999999995e-06,"_priciest_blended_per_m":7.26e-06,"_provider_spread_multiplier":1.1},{"id":"anthropic/claude-sonnet-4.6:batch","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","hugging_face_id":"","name":"Anthropic: Claude Sonnet 4.6 (batch)","created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.0000075","web_search":"0.01","input_cache_read":"0.00000015","input_cache_write":"0.000001875","input_cache_write_1h":"0.000003"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1176,"win_rate":52.2,"rank":15},{"arena":"agents","category":"androidnative","elo":1221,"win_rate":62,"rank":12},{"arena":"agents","category":"fullstack","elo":1237,"win_rate":64.3,"rank":12},{"arena":"agents","category":"godotgamedev","elo":1226,"win_rate":60.6,"rank":7},{"arena":"agents","category":"mobileapps","elo":1252,"win_rate":63.6,"rank":6},{"arena":"agents","category":"webapps","elo":1221,"win_rate":57,"rank":20},{"arena":"models","category":"3d","elo":1279,"win_rate":57.6,"rank":25},{"arena":"models","category":"asciiart","elo":1260,"win_rate":60.1,"rank":13},{"arena":"models","category":"codecategories","elo":1301,"win_rate":59.4,"rank":13},{"arena":"models","category":"dataviz","elo":1300,"win_rate":58.3,"rank":12},{"arena":"models","category":"gamedev","elo":1296,"win_rate":58.8,"rank":20},{"arena":"models","category":"svg","elo":1237,"win_rate":58.8,"rank":18},{"arena":"models","category":"uicomponent","elo":1298,"win_rate":58.3,"rank":17},{"arena":"models","category":"website","elo":1305,"win_rate":60,"rank":11}],"artificial_analysis":{"intelligence_index":48.4,"coding_index":63,"agentic_index":42.1}},"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low"],"default_effort":"medium"},"_prompt_per_m":1.5e-06,"_completion_per_m":7.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":1.875e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.6-sonnet-20260217:batch","model_id":"anthropic/claude-sonnet-4.6:batch","model_name":"Anthropic: Claude Sonnet 4.6","context_length":1000000,"pricing":{"prompt":"0.0000015","completion":"0.0000075","web_search":"0.01","input_cache_read":"0.00000015","input_cache_write":"0.000001875","input_cache_write_1h":"0.000003","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-06,"_completion_per_m":7.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":1.875e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":3.2999999999999997e-06,"_priciest_blended_per_m":3.2999999999999997e-06,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3.1-pro-preview:batch","canonical_slug":"google/gemini-3.1-pro-preview-20260219","hugging_face_id":"","name":"Google: Gemini 3.1 Pro Preview (batch)","created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000006","image":"0.000001","audio":"0.000001","web_search":"0.014","internal_reasoning":"0.000006","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000002","completion":"0.000009","audio":"0.000002"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1114,"win_rate":44.4,"rank":22},{"arena":"agents","category":"agentichtmlslides","elo":1226,"win_rate":55.8,"rank":5},{"arena":"agents","category":"agenticslides","elo":1112,"win_rate":33.8,"rank":8},{"arena":"agents","category":"agenticslides(html)","elo":1219,"win_rate":54.4,"rank":5},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1107,"win_rate":33.9,"rank":8},{"arena":"agents","category":"androidnative","elo":1075,"win_rate":41.4,"rank":33},{"arena":"agents","category":"fullstack","elo":1094,"win_rate":42.1,"rank":28},{"arena":"agents","category":"godotgamedev","elo":1236,"win_rate":60,"rank":6},{"arena":"agents","category":"htmlslides","elo":1169,"win_rate":48.9,"rank":16},{"arena":"agents","category":"mobileapps","elo":1131,"win_rate":43.8,"rank":32},{"arena":"agents","category":"pptxslides","elo":1110,"win_rate":34.1,"rank":8},{"arena":"agents","category":"python-pptxslides","elo":1109,"win_rate":31.9,"rank":20},{"arena":"agents","category":"webapps","elo":1156,"win_rate":45.2,"rank":27},{"arena":"models","category":"3d","elo":1279,"win_rate":59.2,"rank":26},{"arena":"models","category":"asciiart","elo":1298,"win_rate":63.7,"rank":7},{"arena":"models","category":"codecategories","elo":1268,"win_rate":64.4,"rank":29},{"arena":"models","category":"dataviz","elo":1259,"win_rate":61.8,"rank":26},{"arena":"models","category":"gamedev","elo":1238,"win_rate":53.4,"rank":38},{"arena":"models","category":"svg","elo":1327,"win_rate":68.5,"rank":4},{"arena":"models","category":"uicomponent","elo":1306,"win_rate":69.4,"rank":13},{"arena":"models","category":"website","elo":1272,"win_rate":64.4,"rank":28}],"artificial_analysis":{"intelligence_index":47.7,"coding_index":68.8,"agentic_index":23}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":1e-06,"_completion_per_m":6e-06,"_image_per_m":1e-06,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | google/gemini-3.1-pro-preview-20260219:batch","model_id":"google/gemini-3.1-pro-preview:batch","model_name":"Google: Gemini 3.1 Pro Preview","context_length":1048576,"pricing":{"prompt":"0.000001","completion":"0.000006","image":"0.000001","audio":"0.000001","web_search":"0.014","internal_reasoning":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000002","completion":"0.000009","audio":"0.000002"}]},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":6e-06,"_image_per_m":1e-06,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Google","_cheapest_blended_per_m":2.4999999999999998e-06,"_priciest_blended_per_m":2.4999999999999998e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3.5-plus-02-15","canonical_slug":"qwen/qwen3.5-plus-20260216","hugging_face_id":"","name":"Qwen: Qwen3.5 Plus 2026-02-15","created":1771229416,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000026","completion":"0.00000156","overrides":[{"min_prompt_tokens":256000,"prompt":"0.000000325","completion":"0.00000195"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-plus-20260216/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1163,"win_rate":47.7,"rank":65},{"arena":"models","category":"asciiart","elo":1120,"win_rate":43.2,"rank":53},{"arena":"models","category":"codecategories","elo":1191,"win_rate":48.5,"rank":60},{"arena":"models","category":"dataviz","elo":1157,"win_rate":44.9,"rank":71},{"arena":"models","category":"gamedev","elo":1142,"win_rate":42.6,"rank":73},{"arena":"models","category":"svg","elo":1147,"win_rate":48.9,"rank":48},{"arena":"models","category":"uicomponent","elo":1204,"win_rate":52.2,"rank":49},{"arena":"models","category":"website","elo":1207,"win_rate":50,"rank":55}]},"reasoning":{"mandatory":false},"_prompt_per_m":2.6e-07,"_completion_per_m":1.56e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3.5-plus-20260216","model_id":"qwen/qwen3.5-plus-02-15","model_name":"Qwen: Qwen3.5 Plus 2026-02-15","context_length":1000000,"pricing":{"prompt":"0.00000026","completion":"0.00000156","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.000000325","completion":"0.00000195"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":983616,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99619554879209,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-07,"_completion_per_m":1.56e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":6.5e-07,"_priciest_blended_per_m":6.5e-07,"_provider_spread_multiplier":1.0},{"id":"minimax/minimax-m2.5","canonical_slug":"minimax/minimax-m2.5-20260211","hugging_face_id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax: MiniMax M2.5","created":1770908502,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000027","completion":"0.00000108","input_cache_read":"0.000000027"},"top_provider":{"context_length":200000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m2.5-20260211/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1214,"win_rate":57.6,"rank":43},{"arena":"models","category":"codecategories","elo":1231,"win_rate":56.8,"rank":41},{"arena":"models","category":"dataviz","elo":1193,"win_rate":51.2,"rank":53},{"arena":"models","category":"gamedev","elo":1212,"win_rate":55.5,"rank":45},{"arena":"models","category":"svg","elo":1190,"win_rate":54.5,"rank":34},{"arena":"models","category":"uicomponent","elo":1199,"win_rate":53.4,"rank":53},{"arena":"models","category":"website","elo":1242,"win_rate":57.5,"rank":39}]},"reasoning":{"mandatory":true},"_prompt_per_m":2.7e-07,"_completion_per_m":1.08e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.7e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Venice | minimax/minimax-m2.5-20260211","model_id":"minimax/minimax-m2.5","model_name":"MiniMax: MiniMax M2.5","context_length":198000,"pricing":{"prompt":"0.00000027","completion":"0.00000095","input_cache_read":"0.00000003","discount":0},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9695238095238,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":9.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"StreamLake | minimax/minimax-m2.5-20260211","model_id":"minimax/minimax-m2.5","model_name":"MiniMax: MiniMax M2.5","context_length":200000,"pricing":{"prompt":"0.00000027","completion":"0.00000108","input_cache_read":"0.000000027","discount":0.1},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.9728555917481,"uptime_last_5m":100,"uptime_last_1d":97.86339513405473,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":1.08e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.7e-08,"_cached_write_per_m":null},{"name":"AtlasCloud | minimax/minimax-m2.5-20260211","model_id":"minimax/minimax-m2.5","model_name":"MiniMax: MiniMax M2.5","context_length":196608,"pricing":{"prompt":"0.000000295","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":176947,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","structured_outputs","response_format","seed","stop","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.36211244622459,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.95e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Novita | minimax/minimax-m2.5-20260211","model_id":"minimax/minimax-m2.5","model_name":"MiniMax: MiniMax M2.5","context_length":204800,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131100,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.73544114782834,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Minimax | minimax/minimax-m2.5-20260211","model_id":"minimax/minimax-m2.5","model_name":"MiniMax: MiniMax M2.5","context_length":204800,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","discount":0},"provider_name":"Minimax","tag":"minimax/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.76336302895324,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"DigitalOcean | minimax/minimax-m2.5-20260211","model_id":"minimax/minimax-m2.5","model_name":"MiniMax: MiniMax M2.5","context_length":65536,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":58982,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","structured_outputs","response_format","tool_choice","tools","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99235532451648,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | minimax/minimax-m2.5-20260211","model_id":"minimax/minimax-m2.5","model_name":"MiniMax: MiniMax M2.5","context_length":196608,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","response_format","tools","tool_choice","structured_outputs","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.86375093671231,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Friendli | minimax/minimax-m2.5-20260211","model_id":"minimax/minimax-m2.5","model_name":"MiniMax: MiniMax M2.5","context_length":196608,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"Friendli","tag":"friendli","quantization":"unknown","max_completion_tokens":176947,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97481636935991,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"Minimax | minimax/minimax-m2.5-20260211","model_id":"minimax/minimax-m2.5","model_name":"MiniMax: MiniMax M2.5","context_length":204800,"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.00000006","discount":0},"provider_name":"Minimax","tag":"minimax/highspeed","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.83948635634029,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Venice","_cheapest_blended_per_m":4.7399999999999993e-07,"_priciest_blended_per_m":1.1399999999999999e-06,"_provider_spread_multiplier":2.4050632911392404},{"id":"qwen/qwen3.5-397b-a17b","canonical_slug":"qwen/qwen3.5-397b-a17b-20260216","hugging_face_id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen: Qwen3.5 397B A17B","created":1771223018,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000039","completion":"0.00000234"},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-397b-a17b-20260216/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1205,"win_rate":56.7,"rank":46},{"arena":"models","category":"codecategories","elo":1204,"win_rate":52.6,"rank":50},{"arena":"models","category":"dataviz","elo":1196,"win_rate":53.2,"rank":52},{"arena":"models","category":"gamedev","elo":1176,"win_rate":50.1,"rank":59},{"arena":"models","category":"svg","elo":1180,"win_rate":56.1,"rank":39},{"arena":"models","category":"uicomponent","elo":1190,"win_rate":51.4,"rank":59},{"arena":"models","category":"website","elo":1210,"win_rate":52.5,"rank":51}],"artificial_analysis":{"intelligence_index":34.3,"coding_index":48.2,"agentic_index":19.8}},"reasoning":{"mandatory":false},"_prompt_per_m":3.9e-07,"_completion_per_m":2.34e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":262144,"pricing":{"prompt":"0.00000039","completion":"0.00000234","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":258048,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.93924665856622,"uptime_last_5m":100,"uptime_last_1d":99.91182859175503,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.9e-07,"_completion_per_m":2.34e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":262144,"pricing":{"prompt":"0.00000045","completion":"0.000003","input_cache_read":"0.00000022","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":81920,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":97.86053882725832,"uptime_last_5m":96.55172413793103,"uptime_last_1d":97.77946961045552,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.0000036","input_cache_read":"0.0000003","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.92719330178377,"uptime_last_5m":100,"uptime_last_1d":99.66737357115831,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":3.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":131072,"pricing":{"prompt":"0.00000055","completion":"0.0000035","input_cache_read":"0.000000111","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":98.03814713896458,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.11e-07,"_cached_write_per_m":null},{"name":"AtlasCloud | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":262144,"pricing":{"prompt":"0.00000055","completion":"0.0000035","input_cache_read":"0.00000055","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.64912280701755,"uptime_last_5m":100,"uptime_last_1d":98.32067978661456,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null},{"name":"Phala | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":262144,"pricing":{"prompt":"0.00000055","completion":"0.0000035","input_cache_read":"0.000000225","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.36708860759494,"uptime_last_5m":null,"uptime_last_1d":99.58305767958521,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.25e-07,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":262144,"pricing":{"prompt":"0.0000006","completion":"0.0000036","discount":0},"provider_name":"Novita","tag":"novita","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.71264367816092,"uptime_last_5m":null,"uptime_last_1d":95.81390710314393,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":3.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"GMICloud | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":262144,"pricing":{"prompt":"0.0000006","completion":"0.0000036","discount":0},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":62.88352695859398,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":3.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"StreamLake | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":256000,"pricing":{"prompt":"0.0000006","completion":"0.0000036","input_cache_read":"0.00000012","discount":0},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":98.26267340853106,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":3.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3.5-397b-a17b-20260216","model_id":"qwen/qwen3.5-397b-a17b","model_name":"Qwen: Qwen3.5 397B A17B","context_length":128000,"pricing":{"prompt":"0.00000075","completion":"0.0000045","discount":0},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":96.60872043317184,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":4.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":9.75e-07,"_priciest_blended_per_m":1.8749999999999998e-06,"_provider_spread_multiplier":1.923076923076923},{"id":"anthropic/claude-opus-4.6","canonical_slug":"anthropic/claude-4.6-opus-20260205","hugging_face_id":"","name":"Anthropic: Claude Opus 4.6","created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.6-opus-20260205/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1233,"win_rate":65.6,"rank":11},{"arena":"agents","category":"fullstack","elo":1240,"win_rate":62,"rank":11},{"arena":"agents","category":"mobileapps","elo":1248,"win_rate":61,"rank":9},{"arena":"agents","category":"webapps","elo":1234,"win_rate":57.9,"rank":15},{"arena":"models","category":"3d","elo":1319,"win_rate":62.5,"rank":11},{"arena":"models","category":"asciiart","elo":1279,"win_rate":63.1,"rank":12},{"arena":"models","category":"codecategories","elo":1314,"win_rate":61.2,"rank":11},{"arena":"models","category":"dataviz","elo":1302,"win_rate":58.6,"rank":11},{"arena":"models","category":"gamedev","elo":1315,"win_rate":61,"rank":13},{"arena":"models","category":"svg","elo":1268,"win_rate":60.9,"rank":9},{"arena":"models","category":"uicomponent","elo":1311,"win_rate":59.9,"rank":11},{"arena":"models","category":"website","elo":1311,"win_rate":61.2,"rank":10}]},"reasoning":{"mandatory":false,"default_enabled":false,"supports_max_tokens":true,"supported_efforts":["max","high","medium","low"],"default_effort":"high"},"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06,"_endpoints":[{"name":"Azure | anthropic/claude-4.6-opus-20260205","model_id":"anthropic/claude-opus-4.6","model_name":"Anthropic: Claude Opus 4.6","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Azure","tag":"azure/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","response_format","verbosity","top_k","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.91423670668954,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Google | anthropic/claude-4.6-opus-20260205","model_id":"anthropic/claude-opus-4.6","model_name":"Anthropic: Claude Opus 4.6","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97019966226284,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Amazon Bedrock | anthropic/claude-4.6-opus-20260205","model_id":"anthropic/claude-opus-4.6","model_name":"Anthropic: Claude Opus 4.6","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.78181818181818,"uptime_last_5m":100,"uptime_last_1d":99.75871313672923,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Anthropic | anthropic/claude-4.6-opus-20260205","model_id":"anthropic/claude-opus-4.6","model_name":"Anthropic: Claude Opus 4.6","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.93048128342245,"uptime_last_5m":100,"uptime_last_1d":99.61649543108754,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Claude Platform on AWS | anthropic/claude-4.6-opus-20260205","model_id":"anthropic/claude-opus-4.6","model_name":"Anthropic: Claude Opus 4.6","context_length":1000000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Claude Platform on AWS","tag":"claude-on-aws","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.87984895296945,"uptime_last_5m":99.85074626865672,"uptime_last_1d":99.93557443020718,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Google | anthropic/claude-4.6-opus-20260205","model_id":"anthropic/claude-opus-4.6","model_name":"Anthropic: Claude Opus 4.6","context_length":1000000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Google","tag":"google-vertex/europe","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":1.1e-05,"_priciest_blended_per_m":1.21e-05,"_provider_spread_multiplier":1.0999999999999999},{"id":"z-ai/glm-5","canonical_slug":"z-ai/glm-5-20260211","hugging_face_id":"zai-org/GLM-5","name":"Z.ai: GLM 5","created":1770829182,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.00000192","input_cache_read":"0.00000012"},"top_provider":{"context_length":198000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5-20260211/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1170,"win_rate":55.2,"rank":24},{"arena":"agents","category":"fullstack","elo":1146,"win_rate":51.7,"rank":25},{"arena":"agents","category":"godotgamedev","elo":1144,"win_rate":46.7,"rank":16},{"arena":"agents","category":"htmlslides","elo":1161,"win_rate":45.2,"rank":17},{"arena":"agents","category":"mobileapps","elo":1177,"win_rate":51.7,"rank":27},{"arena":"models","category":"3d","elo":1273,"win_rate":56.3,"rank":27},{"arena":"models","category":"asciiart","elo":1174,"win_rate":47.9,"rank":35},{"arena":"models","category":"codecategories","elo":1271,"win_rate":55.5,"rank":28},{"arena":"models","category":"dataviz","elo":1249,"win_rate":53,"rank":32},{"arena":"models","category":"gamedev","elo":1270,"win_rate":57.4,"rank":27},{"arena":"models","category":"svg","elo":1208,"win_rate":54.4,"rank":29},{"arena":"models","category":"uicomponent","elo":1257,"win_rate":53.6,"rank":35},{"arena":"models","category":"website","elo":1268,"win_rate":55,"rank":30}]},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":6e-07,"_completion_per_m":1.92e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":202752,"pricing":{"prompt":"0.0000006","completion":"0.00000192","input_cache_read":"0.00000012","discount":0.4},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.61904761904762,"uptime_last_5m":100,"uptime_last_1d":99.63910897249761,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":1.92e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null},{"name":"StreamLake | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":198000,"pricing":{"prompt":"0.0000006","completion":"0.00000192","input_cache_read":"0.00000012","discount":0.4},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tool_choice","tools","max_tokens","temperature","top_p","stop","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.86910994764398,"uptime_last_5m":100,"uptime_last_1d":99.95840431010578,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":1.92e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null},{"name":"DeepInfra | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":202752,"pricing":{"prompt":"0.0000006","completion":"0.00000208","input_cache_read":"0.00000012","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.48536235552181,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.08e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null},{"name":"Baidu | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":202752,"pricing":{"prompt":"0.0000007","completion":"0.00000224","input_cache_read":"0.00000014","discount":0},"provider_name":"Baidu","tag":"baidu/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","tool_choice","tools","response_format","structured_outputs","frequency_penalty","presence_penalty","repetition_penalty","stop","seed"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.97511044738971,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-07,"_completion_per_m":2.24e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.4e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":204800,"pricing":{"prompt":"0.00000095","completion":"0.00000255","input_cache_read":"0.0000002","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98512480290364,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":2.55e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"AtlasCloud | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":202752,"pricing":{"prompt":"0.00000095","completion":"0.00000315","input_cache_read":"0.00000019","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format","seed","logit_bias","stop","min_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.95537208523932,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.5e-07,"_completion_per_m":3.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.9e-07,"_cached_write_per_m":null},{"name":"Venice | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":198000,"pricing":{"prompt":"0.000001","completion":"0.0000032","input_cache_read":"0.0000002","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":89.41483414088707,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"Z.AI | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":202752,"pricing":{"prompt":"0.000001","completion":"0.0000032","input_cache_read":"0.0000002","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.83277591973244,"uptime_last_5m":100,"uptime_last_1d":99.98431181146283,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"Novita | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":202800,"pricing":{"prompt":"0.000001","completion":"0.0000032","input_cache_read":"0.0000002","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.98397264665029,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"Amazon Bedrock | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":202752,"pricing":{"prompt":"0.000001","completion":"0.0000032","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tools","tool_choice","seed"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":87.14983294782832,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DigitalOcean | z-ai/glm-5-20260211","model_id":"z-ai/glm-5","model_name":"Z.ai: GLM 5","context_length":64000,"pricing":{"prompt":"0.000001","completion":"0.0000032","input_cache_read":"0.0000002","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":57600,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","structured_outputs","response_format","tool_choice","tools","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.74647887323944,"uptime_last_5m":97.95918367346938,"uptime_last_1d":94.32159432159433,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":9.959999999999999e-07,"_priciest_blended_per_m":1.6599999999999998e-06,"_provider_spread_multiplier":1.6666666666666667},{"id":"qwen/qwen3-max-thinking","canonical_slug":"qwen/qwen3-max-thinking-20260123","hugging_face_id":null,"name":"Qwen: Qwen3 Max Thinking","created":1770671901,"description":"Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000078","completion":"0.0000039","overrides":[{"min_prompt_tokens":32000,"prompt":"0.00000156","completion":"0.0000078"},{"min_prompt_tokens":128000,"prompt":"0.00000195","completion":"0.00000975"}]},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-max-thinking-20260123/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":7.8e-07,"_completion_per_m":3.9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-max-thinking-20260123","model_id":"qwen/qwen3-max-thinking","model_name":"Qwen: Qwen3 Max Thinking","context_length":262144,"pricing":{"prompt":"0.00000078","completion":"0.0000039","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.00000156","completion":"0.0000078"},{"min_prompt_tokens":128000,"prompt":"0.00000195","completion":"0.00000975"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":258048,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.8e-07,"_completion_per_m":3.9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":1.7160000000000002e-06,"_priciest_blended_per_m":1.7160000000000002e-06,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-opus-4.6:batch","canonical_slug":"anthropic/claude-4.6-opus-20260205","hugging_face_id":"","name":"Anthropic: Claude Opus 4.6 (batch)","created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.6-opus-20260205/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1233,"win_rate":65.6,"rank":11},{"arena":"agents","category":"fullstack","elo":1240,"win_rate":62,"rank":11},{"arena":"agents","category":"mobileapps","elo":1248,"win_rate":61,"rank":9},{"arena":"agents","category":"webapps","elo":1234,"win_rate":57.9,"rank":15},{"arena":"models","category":"3d","elo":1319,"win_rate":62.5,"rank":11},{"arena":"models","category":"asciiart","elo":1279,"win_rate":63.1,"rank":12},{"arena":"models","category":"codecategories","elo":1314,"win_rate":61.2,"rank":11},{"arena":"models","category":"dataviz","elo":1302,"win_rate":58.6,"rank":11},{"arena":"models","category":"gamedev","elo":1315,"win_rate":61,"rank":13},{"arena":"models","category":"svg","elo":1268,"win_rate":60.9,"rank":9},{"arena":"models","category":"uicomponent","elo":1311,"win_rate":59.9,"rank":11},{"arena":"models","category":"website","elo":1311,"win_rate":61.2,"rank":10}]},"reasoning":{"mandatory":false,"default_enabled":false,"supports_max_tokens":true,"supported_efforts":["max","high","medium","low"],"default_effort":"high"},"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.6-opus-20260205:batch","model_id":"anthropic/claude-opus-4.6:batch","model_name":"Anthropic: Claude Opus 4.6","context_length":1000000,"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":5.5e-06,"_priciest_blended_per_m":5.5e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-coder-next","canonical_slug":"qwen/qwen3-coder-next-2025-02-03","hugging_face_id":"Qwen/Qwen3-Coder-Next","name":"Qwen: Qwen3 Coder Next","created":1770164101,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000012","completion":"0.0000008","input_cache_read":"0.00000007"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-next-2025-02-03/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":21.3,"coding_index":36.2,"agentic_index":8.9}},"_prompt_per_m":1.2e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Parasail | qwen/qwen3-coder-next-2025-02-03","model_id":"qwen/qwen3-coder-next","model_name":"Qwen: Qwen3 Coder Next","context_length":262144,"pricing":{"prompt":"0.00000012","completion":"0.0000008","input_cache_read":"0.00000007","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97062600186315,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.2e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"StreamLake | qwen/qwen3-coder-next-2025-02-03","model_id":"qwen/qwen3-coder-next","model_name":"Qwen: Qwen3 Coder Next","context_length":256000,"pricing":{"prompt":"0.00000018","completion":"0.0000009","input_cache_read":"0.000000036","discount":0.4},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["tools","tool_choice","response_format","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.28952042628775,"uptime_last_5m":100,"uptime_last_1d":99.65584131155747,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.8e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.6e-08,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3-coder-next-2025-02-03","model_id":"qwen/qwen3-coder-next","model_name":"Qwen: Qwen3 Coder Next","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.0000015","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.10714285714286,"uptime_last_5m":null,"uptime_last_1d":99.2990186260765,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3-coder-next-2025-02-03","model_id":"qwen/qwen3-coder-next","model_name":"Qwen: Qwen3 Coder Next","context_length":262144,"pricing":{"prompt":"0.0000003","completion":"0.0000015","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.0000005","completion":"0.0000025"},{"min_prompt_tokens":128000,"prompt":"0.0000008","completion":"0.000004"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":204800,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":98.83509282854023,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Parasail","_cheapest_blended_per_m":3.24e-07,"_priciest_blended_per_m":6.599999999999999e-07,"_provider_spread_multiplier":2.0370370370370368},{"id":"openrouter/free","canonical_slug":"openrouter/free","hugging_face_id":"","name":"Free Models Router","created":1769917427,"description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openrouter/free/endpoints"},"_prompt_per_m":0.0,"_completion_per_m":0.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":0.0,"_priciest_blended_per_m":0.0,"_provider_spread_multiplier":null},{"id":"moonshotai/kimi-k2.5","canonical_slug":"moonshotai/kimi-k2.5-0127","hugging_face_id":"moonshotai/Kimi-K2.5","name":"MoonshotAI: Kimi K2.5","created":1769487076,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.000003","input_cache_read":"0.0000001"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2026-08-31","links":{"details":"/api/v1/models/moonshotai/kimi-k2.5-0127/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1145,"win_rate":57.9,"rank":26},{"arena":"agents","category":"fullstack","elo":1137,"win_rate":54.4,"rank":26},{"arena":"agents","category":"godotgamedev","elo":1219,"win_rate":59.8,"rank":9},{"arena":"agents","category":"mobileapps","elo":1187,"win_rate":54.6,"rank":25},{"arena":"agents","category":"webapps","elo":1167,"win_rate":51.6,"rank":25},{"arena":"models","category":"3d","elo":1249,"win_rate":53.1,"rank":34},{"arena":"models","category":"asciiart","elo":1196,"win_rate":46.5,"rank":22},{"arena":"models","category":"codecategories","elo":1261,"win_rate":54.1,"rank":32},{"arena":"models","category":"dataviz","elo":1240,"win_rate":51.3,"rank":37},{"arena":"models","category":"gamedev","elo":1243,"win_rate":53.4,"rank":37},{"arena":"models","category":"svg","elo":1189,"win_rate":48.4,"rank":37},{"arena":"models","category":"uicomponent","elo":1263,"win_rate":53.6,"rank":33},{"arena":"models","category":"website","elo":1269,"win_rate":55.2,"rank":29}],"artificial_analysis":{"intelligence_index":36,"coding_index":46.8,"agentic_index":21.7}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":6e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":262144,"pricing":{"prompt":"0.00000045","completion":"0.00000225","input_cache_read":"0.00000007","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":98.65728900255755,"uptime_last_5m":99.43820224719101,"uptime_last_1d":99.82405299109915,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":2.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":262144,"pricing":{"prompt":"0.00000045","completion":"0.00000225","input_cache_read":"0.00000007","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","response_format","tools","tool_choice","structured_outputs","max_tokens"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97902807721023,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":2.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"AtlasCloud | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":262144,"pricing":{"prompt":"0.00000049","completion":"0.0000025","input_cache_read":"0.0000002","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.74358974358975,"uptime_last_5m":100,"uptime_last_1d":99.29544310784266,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.9e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.0000027","input_cache_read":"0.000000203","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","tool_choice","tools","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.76269929551353,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":2.7e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.03e-07,"_cached_write_per_m":null},{"name":"Venice | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":256000,"pricing":{"prompt":"0.000000532","completion":"0.000003325","input_cache_read":"0.000000209","discount":0.05},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.96625042186973,"uptime_last_5m":100,"uptime_last_1d":96.40331232347486,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.32e-07,"_completion_per_m":3.325e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.09e-07,"_cached_write_per_m":null},{"name":"StreamLake | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":256000,"pricing":{"prompt":"0.00000054","completion":"0.0000027","input_cache_read":"0.00000009","discount":0.1},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":230400,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","response_format","logprobs","top_logprobs","structured_outputs","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.82658959537572,"uptime_last_5m":99.61832061068702,"uptime_last_1d":98.89126352720264,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.4e-07,"_completion_per_m":2.7e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9e-08,"_cached_write_per_m":null},{"name":"Novita | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":262144,"pricing":{"prompt":"0.00000057","completion":"0.00000285","input_cache_read":"0.000000095","discount":0.05},"provider_name":"Novita","tag":"novita","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.4475138121547,"uptime_last_5m":null,"uptime_last_1d":93.91155735953856,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.7e-07,"_completion_per_m":2.85e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9.5e-08,"_cached_write_per_m":null},{"name":"Amazon Bedrock | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":262144,"pricing":{"prompt":"0.0000006","completion":"0.000003","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us-east-2","quantization":"unknown","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":98.82753403933434,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Moonshot AI | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":262144,"pricing":{"prompt":"0.0000006","completion":"0.000003","input_cache_read":"0.0000001","discount":0},"provider_name":"Moonshot AI","tag":"moonshotai/int4","quantization":"int4","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","frequency_penalty","presence_penalty","structured_outputs","response_format","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98309668695065,"uptime_last_5m":100,"uptime_last_1d":99.98747273477568,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Phala | moonshotai/kimi-k2.5-0127","model_id":"moonshotai/kimi-k2.5","model_name":"MoonshotAI: Kimi K2.5","context_length":262144,"pricing":{"prompt":"0.0000006","completion":"0.000003","input_cache_read":"0.00000022","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tool_choice","tools"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":87.2159090909091,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":9.899999999999998e-07,"_priciest_blended_per_m":1.3699e-06,"_provider_spread_multiplier":1.383737373737374},{"id":"upstage/solar-pro-3","canonical_slug":"upstage/solar-pro-3","hugging_face_id":"","name":"Upstage: Solar Pro 3","created":1769481200,"description":"Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/upstage/solar-pro-3/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":14.5,"coding_index":16.2,"agentic_index":2.9}},"reasoning":{"mandatory":false},"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Upstage | upstage/solar-pro-3","model_id":"upstage/solar-pro-3","model_name":"Upstage: Solar Pro 3","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015","discount":0},"provider_name":"Upstage","tag":"upstage","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","tool_choice","structured_outputs","response_format","top_p","frequency_penalty","presence_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Upstage","_cheapest_blended_per_m":2.8499999999999997e-07,"_priciest_blended_per_m":2.8499999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"minimax/minimax-m2-her","canonical_slug":"minimax/minimax-m2-her-20260123","hugging_face_id":"","name":"MiniMax: MiniMax M2-her","created":1769177239,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003"},"top_provider":{"context_length":65536,"max_completion_tokens":2048,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m2-her-20260123/endpoints"},"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Minimax | minimax/minimax-m2-her-20260123","model_id":"minimax/minimax-m2-her","model_name":"MiniMax: MiniMax M2-her","context_length":65536,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","discount":0},"provider_name":"Minimax","tag":"minimax","quantization":"unknown","max_completion_tokens":2048,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Minimax","_cheapest_blended_per_m":5.699999999999999e-07,"_priciest_blended_per_m":5.699999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"writer/palmyra-x5","canonical_slug":"writer/palmyra-x5-20250428","hugging_face_id":"","name":"Writer: Palmyra X5","created":1769003823,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...","context_length":1040000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.000006"},"top_provider":{"context_length":1040000,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/writer/palmyra-x5-20250428/endpoints"},"_prompt_per_m":6e-07,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Amazon Bedrock | writer/palmyra-x5-20250428","model_id":"writer/palmyra-x5","model_name":"Writer: Palmyra X5","context_length":1040000,"pricing":{"prompt":"0.0000006","completion":"0.000006","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":2.22e-06,"_priciest_blended_per_m":2.22e-06,"_provider_spread_multiplier":1.0},{"id":"stepfun/step-3.5-flash","canonical_slug":"stepfun/step-3.5-flash","hugging_face_id":"stepfun-ai/Step-3.5-Flash","name":"StepFun: Step 3.5 Flash","created":1769728337,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000003"},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/stepfun/step-3.5-flash/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"SiliconFlow | stepfun/step-3.5-flash","model_id":"stepfun/step-3.5-flash","model_name":"StepFun: Step 3.5 Flash","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.0000003","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"SiliconFlow","_cheapest_blended_per_m":1.6e-07,"_priciest_blended_per_m":1.6e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.2-codex","canonical_slug":"openai/gpt-5.2-codex-20260114","hugging_face_id":"","name":"OpenAI: GPT-5.2-Codex","created":1768409315,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.2-codex-20260114/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1176,"win_rate":47.5,"rank":23},{"arena":"agents","category":"fullstack","elo":1016,"win_rate":37.2,"rank":39},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":47.8,"rank":19},{"arena":"agents","category":"mobileapps","elo":1130,"win_rate":46.6,"rank":34},{"arena":"agents","category":"webapps","elo":1082,"win_rate":39.7,"rank":34}]},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-5.2-codex-20260114","model_id":"openai/gpt-5.2-codex","model_name":"OpenAI: GPT-5.2-Codex","context_length":400000,"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":5.425e-06,"_priciest_blended_per_m":5.425e-06,"_provider_spread_multiplier":1.0},{"id":"bytedance-seed/seed-1.6-flash","canonical_slug":"bytedance-seed/seed-1.6-flash-20250625","hugging_face_id":"","name":"ByteDance Seed: Seed 1.6 Flash","created":1766505011,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000075","completion":"0.0000003","overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000001","completion":"0.0000008"}]},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-1.6-flash-20250625/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":7.5e-08,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Seed | bytedance-seed/seed-1.6-flash-20250625","model_id":"bytedance-seed/seed-1.6-flash","model_name":"ByteDance Seed: Seed 1.6 Flash","context_length":262144,"pricing":{"prompt":"0.000000075","completion":"0.0000003","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000001","completion":"0.0000008"}]},"provider_name":"Seed","tag":"seed/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-08,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Seed","_cheapest_blended_per_m":1.4249999999999999e-07,"_priciest_blended_per_m":1.4249999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-audio","canonical_slug":"openai/gpt-audio","hugging_face_id":"","name":"OpenAI: GPT Audio","created":1768862569,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","audio":"0.000032","audio_output":"0.000064"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-audio/endpoints"},"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-audio","model_id":"openai/gpt-audio","model_name":"OpenAI: GPT Audio","context_length":128000,"pricing":{"prompt":"0.0000025","completion":"0.00001","audio":"0.000032","audio_output":"0.000064","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":4.75e-06,"_priciest_blended_per_m":4.75e-06,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-audio-mini","canonical_slug":"openai/gpt-audio-mini","hugging_face_id":"","name":"OpenAI: GPT Audio Mini","created":1768859419,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000024","audio":"0.0000006","audio_output":"0.0000024"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-audio-mini/endpoints"},"_prompt_per_m":6e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-audio-mini","model_id":"openai/gpt-audio-mini","model_name":"OpenAI: GPT Audio Mini","context_length":128000,"pricing":{"prompt":"0.0000006","completion":"0.0000024","audio":"0.0000006","audio_output":"0.0000024","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":1.1399999999999999e-06,"_priciest_blended_per_m":1.1399999999999999e-06,"_provider_spread_multiplier":1.0},{"id":"z-ai/glm-4.7-flash","canonical_slug":"z-ai/glm-4.7-flash-20260119","hugging_face_id":"zai-org/GLM-4.7-Flash","name":"Z.ai: GLM 4.7 Flash","created":1768833913,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000006","completion":"0.0000004","input_cache_read":"0.00000001"},"top_provider":{"context_length":202752,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.7-flash-20260119/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1165,"win_rate":51.2,"rank":63},{"arena":"models","category":"codecategories","elo":1202,"win_rate":53.1,"rank":52},{"arena":"models","category":"dataviz","elo":1144,"win_rate":45.3,"rank":77},{"arena":"models","category":"gamedev","elo":1171,"win_rate":49.7,"rank":63},{"arena":"models","category":"svg","elo":1078,"win_rate":44.2,"rank":62},{"arena":"models","category":"uicomponent","elo":1234,"win_rate":57.6,"rank":41},{"arena":"models","category":"website","elo":1214,"win_rate":54,"rank":48}]},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":6e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | z-ai/glm-4.7-flash-20260119","model_id":"z-ai/glm-4.7-flash","model_name":"Z.ai: GLM 4.7 Flash","context_length":202752,"pricing":{"prompt":"0.00000006","completion":"0.0000004","input_cache_read":"0.00000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.96982498491249,"uptime_last_5m":100,"uptime_last_1d":99.56564399925418,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null},{"name":"Venice | z-ai/glm-4.7-flash-20260119","model_id":"z-ai/glm-4.7-flash","model_name":"Z.ai: GLM 4.7 Flash","context_length":128000,"pricing":{"prompt":"0.00000006","completion":"0.0000004","input_cache_read":"0.00000001","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.3853834535996,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null},{"name":"Cloudflare | z-ai/glm-4.7-flash-20260119","model_id":"z-ai/glm-4.7-flash","model_name":"Z.ai: GLM 4.7 Flash","context_length":131072,"pricing":{"prompt":"0.0000000605","completion":"0.0000004","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","min_p","stop","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":95.26881720430107,"uptime_last_5m":97.82503624939585,"uptime_last_1d":97.0375434826708,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.05e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | z-ai/glm-4.7-flash-20260119","model_id":"z-ai/glm-4.7-flash","model_name":"Z.ai: GLM 4.7 Flash","context_length":200000,"pricing":{"prompt":"0.00000007","completion":"0.0000004","input_cache_read":"0.00000001","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":72.43629333261727,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.62e-07,"_priciest_blended_per_m":1.69e-07,"_provider_spread_multiplier":1.0432098765432098},{"id":"minimax/minimax-m2.1","canonical_slug":"minimax/minimax-m2.1","hugging_face_id":"MiniMaxAI/MiniMax-M2.1","name":"MiniMax: MiniMax M2.1","created":1766454997,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003"},"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.9,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m2.1/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1209,"win_rate":57.5,"rank":45},{"arena":"models","category":"codecategories","elo":1215,"win_rate":55.3,"rank":45},{"arena":"models","category":"dataviz","elo":1227,"win_rate":57,"rank":41},{"arena":"models","category":"gamedev","elo":1170,"win_rate":50.4,"rank":64},{"arena":"models","category":"svg","elo":1172,"win_rate":55.4,"rank":43},{"arena":"models","category":"uicomponent","elo":1249,"win_rate":60.9,"rank":37},{"arena":"models","category":"website","elo":1221,"win_rate":55.4,"rank":45}]},"reasoning":{"mandatory":true},"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | minimax/minimax-m2.1","model_id":"minimax/minimax-m2.1","model_name":"MiniMax: MiniMax M2.1","context_length":204800,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.70501474926253,"uptime_last_5m":99.24242424242425,"uptime_last_1d":99.68277819517489,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Minimax | minimax/minimax-m2.1","model_id":"minimax/minimax-m2.1","model_name":"MiniMax: MiniMax M2.1","context_length":204800,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","discount":0},"provider_name":"Minimax","tag":"minimax/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.44928866452501,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Minimax | minimax/minimax-m2.1","model_id":"minimax/minimax-m2.1","model_name":"MiniMax: MiniMax M2.1","context_length":204800,"pricing":{"prompt":"0.0000003","completion":"0.0000024","input_cache_read":"0.00000003","discount":0},"provider_name":"Minimax","tag":"minimax/highspeed","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.89293361884368,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":5.699999999999999e-07,"_priciest_blended_per_m":9.3e-07,"_provider_spread_multiplier":1.6315789473684212},{"id":"bytedance-seed/seed-1.6","canonical_slug":"bytedance-seed/seed-1.6-20250625","hugging_face_id":"","name":"ByteDance Seed: Seed 1.6","created":1766504997,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000002","overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000005","completion":"0.000004"}]},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-1.6-20250625/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Seed | bytedance-seed/seed-1.6-20250625","model_id":"bytedance-seed/seed-1.6","model_name":"ByteDance Seed: Seed 1.6","context_length":262144,"pricing":{"prompt":"0.00000025","completion":"0.000002","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000005","completion":"0.000004"}]},"provider_name":"Seed","tag":"seed/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Seed","_cheapest_blended_per_m":7.75e-07,"_priciest_blended_per_m":7.75e-07,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3-flash-preview","canonical_slug":"google/gemini-3-flash-preview-20251217","hugging_face_id":"","name":"Google: Gemini 3 Flash Preview","created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000003","image":"0.0000005","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.000003","input_cache_read":"0.00000005","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticslides","elo":1073,"win_rate":39.3,"rank":9},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1075,"win_rate":39.3,"rank":9},{"arena":"agents","category":"androidnative","elo":1076,"win_rate":48.1,"rank":32},{"arena":"agents","category":"fullstack","elo":1087,"win_rate":47.4,"rank":29},{"arena":"agents","category":"godotgamedev","elo":1161,"win_rate":50.6,"rank":14},{"arena":"agents","category":"mobileapps","elo":1130,"win_rate":46.6,"rank":33},{"arena":"agents","category":"python-pptxslides","elo":1036,"win_rate":38.3,"rank":22},{"arena":"agents","category":"webapps","elo":1142,"win_rate":48.5,"rank":30},{"arena":"models","category":"3d","elo":1228,"win_rate":62.7,"rank":41},{"arena":"models","category":"codecategories","elo":1214,"win_rate":57.6,"rank":46},{"arena":"models","category":"gamedev","elo":1202,"win_rate":58.3,"rank":51},{"arena":"models","category":"website","elo":1216,"win_rate":57,"rank":46}]},"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":5e-07,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":8.33333333333333e-08,"_endpoints":[{"name":"Google AI Studio | google/gemini-3-flash-preview-20251217","model_id":"google/gemini-3-flash-preview","model_name":"Google: Gemini 3 Flash Preview","context_length":1048576,"pricing":{"prompt":"0.0000005","completion":"0.000003","image":"0.0000005","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.000003","input_cache_read":"0.00000005","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.62858277465018,"uptime_last_5m":99.60822722820764,"uptime_last_1d":99.56260104405051,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":5e-07,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-3-flash-preview-20251217","model_id":"google/gemini-3-flash-preview","model_name":"Google: Gemini 3 Flash Preview","context_length":1048576,"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.62858277465018,"uptime_last_5m":99.60822722820764,"uptime_last_1d":99.56260104405051,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":2.5e-07,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-3-flash-preview-20251217","model_id":"google/gemini-3-flash-preview","model_name":"Google: Gemini 3 Flash Preview","context_length":1048576,"pricing":{"prompt":"0.0000009","completion":"0.0000054","image":"0.0000009","audio":"0.0000018","input_audio_cache":"0.00000018","web_search":"0.014","internal_reasoning":"0.0000054","input_cache_read":"0.00000009","input_cache_write":"0.00000015","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.62858277465018,"uptime_last_5m":99.60822722820764,"uptime_last_1d":99.56260104405051,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-07,"_completion_per_m":5.4e-06,"_image_per_m":9e-07,"_request_per_m":null,"_cached_read_per_m":9e-08,"_cached_write_per_m":1.5e-07},{"name":"Google | google/gemini-3-flash-preview-20251217","model_id":"google/gemini-3-flash-preview","model_name":"Google: Gemini 3 Flash Preview","context_length":1048576,"pricing":{"prompt":"0.0000005","completion":"0.000003","image":"0.0000005","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.000003","input_cache_read":"0.00000005","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tool_choice","tools","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.9292565250247,"uptime_last_5m":98.31475852752448,"uptime_last_1d":98.26434462358219,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":3e-06,"_image_per_m":5e-07,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google | google/gemini-3-flash-preview-20251217","model_id":"google/gemini-3-flash-preview","model_name":"Google: Gemini 3 Flash Preview","context_length":1048576,"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tool_choice","tools","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.9292565250247,"uptime_last_5m":98.31475852752448,"uptime_last_1d":98.26434462358219,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":2.5e-07,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google | google/gemini-3-flash-preview-20251217","model_id":"google/gemini-3-flash-preview","model_name":"Google: Gemini 3 Flash Preview","context_length":1048576,"pricing":{"prompt":"0.0000009","completion":"0.0000054","image":"0.0000009","audio":"0.0000018","input_audio_cache":"0.00000018","web_search":"0.014","internal_reasoning":"0.0000054","input_cache_read":"0.00000009","input_cache_write":"0.00000015","discount":0},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tool_choice","tools","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.9292565250247,"uptime_last_5m":98.31475852752448,"uptime_last_1d":98.26434462358219,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-07,"_completion_per_m":5.4e-06,"_image_per_m":9e-07,"_request_per_m":null,"_cached_read_per_m":9e-08,"_cached_write_per_m":1.5e-07}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":6.249999999999999e-07,"_priciest_blended_per_m":2.2499999999999996e-06,"_provider_spread_multiplier":3.5999999999999996},{"id":"google/gemini-3-flash-preview:batch","canonical_slug":"google/gemini-3-flash-preview-20251217","hugging_face_id":"","name":"Google: Gemini 3 Flash Preview (batch)","created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","web_search":"0.014","internal_reasoning":"0.0000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticslides","elo":1073,"win_rate":39.3,"rank":9},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1075,"win_rate":39.3,"rank":9},{"arena":"agents","category":"androidnative","elo":1076,"win_rate":48.1,"rank":32},{"arena":"agents","category":"fullstack","elo":1087,"win_rate":47.4,"rank":29},{"arena":"agents","category":"godotgamedev","elo":1161,"win_rate":50.6,"rank":14},{"arena":"agents","category":"mobileapps","elo":1130,"win_rate":46.6,"rank":33},{"arena":"agents","category":"python-pptxslides","elo":1036,"win_rate":38.3,"rank":22},{"arena":"agents","category":"webapps","elo":1142,"win_rate":48.5,"rank":30},{"arena":"models","category":"3d","elo":1228,"win_rate":62.7,"rank":41},{"arena":"models","category":"codecategories","elo":1214,"win_rate":57.6,"rank":46},{"arena":"models","category":"gamedev","elo":1202,"win_rate":58.3,"rank":51},{"arena":"models","category":"website","elo":1216,"win_rate":57,"rank":46}]},"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":2.5e-07,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | google/gemini-3-flash-preview-20251217:batch","model_id":"google/gemini-3-flash-preview:batch","model_name":"Google: Gemini 3 Flash Preview","context_length":1048576,"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","web_search":"0.014","internal_reasoning":"0.0000015","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tool_choice","tools","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":2.5e-07,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Google","_cheapest_blended_per_m":6.249999999999999e-07,"_priciest_blended_per_m":6.249999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"nvidia/nemotron-3-nano-30b-a3b","canonical_slug":"nvidia/nemotron-3-nano-30b-a3b","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","name":"NVIDIA: Nemotron 3 Nano 30B A3B","created":1765731275,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.0000002","input_cache_read":"0.000000025"},"top_provider":{"context_length":262144,"max_completion_tokens":228000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":14.5,"coding_index":14.4,"agentic_index":2}},"reasoning":{"mandatory":false},"_prompt_per_m":5e-08,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | nvidia/nemotron-3-nano-30b-a3b","model_id":"nvidia/nemotron-3-nano-30b-a3b","model_name":"NVIDIA: Nemotron 3 Nano 30B A3B","context_length":262144,"pricing":{"prompt":"0.00000005","completion":"0.0000002","input_cache_read":"0.000000025","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":228000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.81949458483754,"uptime_last_5m":100,"uptime_last_1d":99.95671828412041,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null},{"name":"Novita | nvidia/nemotron-3-nano-30b-a3b","model_id":"nvidia/nemotron-3-nano-30b-a3b","model_name":"NVIDIA: Nemotron 3 Nano 30B A3B","context_length":262144,"pricing":{"prompt":"0.00000005","completion":"0.0000002","discount":0},"provider_name":"Novita","tag":"novita/fp4","quantization":"fp4","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.76303317535546,"uptime_last_5m":100,"uptime_last_1d":99.66124359260084,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Crusoe | nvidia/nemotron-3-nano-30b-a3b","model_id":"nvidia/nemotron-3-nano-30b-a3b","model_name":"NVIDIA: Nemotron 3 Nano 30B A3B","context_length":262144,"pricing":{"prompt":"0.00000005","completion":"0.0000002","input_cache_read":"0.00000003","discount":0},"provider_name":"Crusoe","tag":"crusoe/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","structured_outputs","tools","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.56987755385202,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Nebius | nvidia/nemotron-3-nano-30b-a3b","model_id":"nvidia/nemotron-3-nano-30b-a3b","model_name":"NVIDIA: Nemotron 3 Nano 30B A3B","context_length":262144,"pricing":{"prompt":"0.00000006","completion":"0.00000024","discount":0},"provider_name":"Nebius","tag":"nebius/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.07764705882353,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-08,"_completion_per_m":2.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":9.499999999999999e-08,"_priciest_blended_per_m":1.1399999999999999e-07,"_provider_spread_multiplier":1.2},{"id":"openai/gpt-5.2-chat","canonical_slug":"openai/gpt-5.2-chat-20251211","hugging_face_id":"","name":"OpenAI: GPT-5.2 Chat","created":1765389783,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175"},"top_provider":{"context_length":128000,"max_completion_tokens":32000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.2-chat-20251211/endpoints"},"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-5.2-chat-20251211","model_id":"openai/gpt-5.2-chat","model_name":"OpenAI: GPT-5.2 Chat","context_length":128000,"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":96000,"supported_parameters":["max_completion_tokens","structured_outputs","response_format","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":5.425e-06,"_priciest_blended_per_m":5.425e-06,"_provider_spread_multiplier":1.0},{"id":"z-ai/glm-4.7","canonical_slug":"z-ai/glm-4.7-20251222","hugging_face_id":"zai-org/GLM-4.7","name":"Z.ai: GLM 4.7","created":1766378014,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.00000175","input_cache_read":"0.00000008"},"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.7-20251222/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1139,"win_rate":56.2,"rank":27},{"arena":"agents","category":"fullstack","elo":1073,"win_rate":45.1,"rank":34},{"arena":"agents","category":"godotgamedev","elo":1058,"win_rate":35.8,"rank":28},{"arena":"agents","category":"mobileapps","elo":1145,"win_rate":48.9,"rank":29},{"arena":"models","category":"3d","elo":1235,"win_rate":54.3,"rank":39},{"arena":"models","category":"asciiart","elo":1192,"win_rate":48.1,"rank":25},{"arena":"models","category":"codecategories","elo":1241,"win_rate":54.8,"rank":39},{"arena":"models","category":"dataviz","elo":1216,"win_rate":51.2,"rank":46},{"arena":"models","category":"gamedev","elo":1224,"win_rate":55.2,"rank":42},{"arena":"models","category":"svg","elo":1183,"win_rate":54.3,"rank":38},{"arena":"models","category":"uicomponent","elo":1226,"win_rate":51,"rank":43},{"arena":"models","category":"website","elo":1246,"win_rate":55.3,"rank":38}],"artificial_analysis":{"intelligence_index":34.5,"coding_index":45.3,"agentic_index":26.2}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":4e-07,"_completion_per_m":1.75e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | z-ai/glm-4.7-20251222","model_id":"z-ai/glm-4.7","model_name":"Z.ai: GLM 4.7","context_length":202752,"pricing":{"prompt":"0.0000004","completion":"0.00000175","input_cache_read":"0.00000008","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.76758599318252,"uptime_last_5m":100,"uptime_last_1d":96.4094476171095,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":1.75e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8e-08,"_cached_write_per_m":null},{"name":"StreamLake | z-ai/glm-4.7-20251222","model_id":"z-ai/glm-4.7","model_name":"Z.ai: GLM 4.7","context_length":200000,"pricing":{"prompt":"0.00000048","completion":"0.00000176","discount":0.2},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":-2,"uptime_last_30m":93.55531686358755,"uptime_last_5m":95.45454545454545,"uptime_last_1d":93.24740647595095,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.8e-07,"_completion_per_m":1.76e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"AtlasCloud | z-ai/glm-4.7-20251222","model_id":"z-ai/glm-4.7","model_name":"Z.ai: GLM 4.7","context_length":202752,"pricing":{"prompt":"0.00000052","completion":"0.00000185","input_cache_read":"0.00000012","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-2,"uptime_last_30m":90.87694483734087,"uptime_last_5m":86.66666666666667,"uptime_last_1d":92.64577065163576,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.2e-07,"_completion_per_m":1.85e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null},{"name":"Novita | z-ai/glm-4.7-20251222","model_id":"z-ai/glm-4.7","model_name":"Z.ai: GLM 4.7","context_length":204800,"pricing":{"prompt":"0.00000054","completion":"0.00000198","input_cache_read":"0.000000099","discount":0.1},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-2,"uptime_last_30m":91.83829138062548,"uptime_last_5m":94.73684210526315,"uptime_last_1d":92.87183442601878,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.4e-07,"_completion_per_m":1.98e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":9.9e-08,"_cached_write_per_m":null},{"name":"Venice | z-ai/glm-4.7-20251222","model_id":"z-ai/glm-4.7","model_name":"Z.ai: GLM 4.7","context_length":198000,"pricing":{"prompt":"0.00000055","completion":"0.00000265","input_cache_read":"0.00000011","discount":0},"provider_name":"Venice","tag":"venice/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.49622166246851,"uptime_last_5m":98.7012987012987,"uptime_last_1d":93.10799145881604,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-07,"_completion_per_m":2.65e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null},{"name":"Z.AI | z-ai/glm-4.7-20251222","model_id":"z-ai/glm-4.7","model_name":"Z.ai: GLM 4.7","context_length":202752,"pricing":{"prompt":"0.0000006","completion":"0.0000022","input_cache_read":"0.00000011","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp4","quantization":"fp4","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":-2,"uptime_last_30m":92.58160237388724,"uptime_last_5m":86.91588785046729,"uptime_last_1d":84.90723339315237,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null},{"name":"Google | z-ai/glm-4.7-20251222","model_id":"z-ai/glm-4.7","model_name":"Z.ai: GLM 4.7","context_length":200000,"pricing":{"prompt":"0.0000006","completion":"0.0000022","discount":0},"provider_name":"Google","tag":"google-vertex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.94107248084856,"uptime_last_5m":100,"uptime_last_1d":99.98043537805371,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Mancer 2 | z-ai/glm-4.7-20251222","model_id":"z-ai/glm-4.7","model_name":"Z.ai: GLM 4.7","context_length":131072,"pricing":{"prompt":"0.00000065","completion":"0.0000025","discount":0},"provider_name":"Mancer 2","tag":"mancer/fp4","quantization":"fp4","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a"],"supports_tool_choice":{"none":false,"auto":false,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.5e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":8.049999999999999e-07,"_priciest_blended_per_m":1.205e-06,"_provider_spread_multiplier":1.4968944099378882},{"id":"openai/gpt-5.2-pro","canonical_slug":"openai/gpt-5.2-pro-20251211","hugging_face_id":"","name":"OpenAI: GPT-5.2 Pro","created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000021","completion":"0.000168","web_search":"0.01"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"_prompt_per_m":2.1e-05,"_completion_per_m":0.000168,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.2-pro-20251211","model_id":"openai/gpt-5.2-pro","model_name":"OpenAI: GPT-5.2 Pro","context_length":400000,"pricing":{"prompt":"0.000021","completion":"0.000168","web_search":"0.01","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-05,"_completion_per_m":0.000168,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":6.51e-05,"_priciest_blended_per_m":6.51e-05,"_provider_spread_multiplier":1.0},{"id":"mistralai/devstral-2512","canonical_slug":"mistralai/devstral-2512","hugging_face_id":"mistralai/Devstral-2-123B-Instruct-2512","name":"Mistral: Devstral 2 2512","created":1765285419,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","context_length":262144,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000044","completion":"0.0000022","input_cache_read":"0.000000044"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/devstral-2512/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":19.2,"coding_index":31.3,"agentic_index":10.6}},"_prompt_per_m":4.4e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/devstral-2512","model_id":"mistralai/devstral-2512","model_name":"Mistral: Devstral 2 2512","context_length":262144,"pricing":{"prompt":"0.00000044","completion":"0.0000022","input_cache_read":"0.000000044","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.36390325737453,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":9.68e-07,"_priciest_blended_per_m":9.68e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.2","canonical_slug":"openai/gpt-5.2-20251211","hugging_face_id":"","name":"OpenAI: GPT-5.2","created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.2-20251211/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"website","elo":1214,"win_rate":54.4,"rank":47},{"arena":"agents","category":"androidnative","elo":1085,"win_rate":49.1,"rank":30},{"arena":"agents","category":"fullstack","elo":1067,"win_rate":44.3,"rank":35},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":48.1,"rank":18},{"arena":"agents","category":"mobileapps","elo":1134,"win_rate":46.8,"rank":31},{"arena":"agents","category":"webapps","elo":1117,"win_rate":45.5,"rank":31},{"arena":"models","category":"3d","elo":1123,"win_rate":41.5,"rank":80},{"arena":"models","category":"codecategories","elo":1194,"win_rate":49.6,"rank":58},{"arena":"models","category":"dataviz","elo":1222,"win_rate":56.1,"rank":43},{"arena":"models","category":"gamedev","elo":1231,"win_rate":56,"rank":41},{"arena":"models","category":"uicomponent","elo":1217,"win_rate":51.3,"rank":45},{"arena":"models","category":"asciiart","elo":1179,"win_rate":50.7,"rank":28},{"arena":"models","category":"svg","elo":1179,"win_rate":53.7,"rank":40}]},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.2-20251211","model_id":"openai/gpt-5.2","model_name":"OpenAI: GPT-5.2","context_length":400000,"pricing":{"prompt":"0.000000875","completion":"0.000007","web_search":"0.01","input_cache_read":"0.0000000875","discount":0},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.75e-07,"_completion_per_m":7e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8.75e-08,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.2-20251211","model_id":"openai/gpt-5.2","model_name":"OpenAI: GPT-5.2","context_length":400000,"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99776815605053,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.2-20251211","model_id":"openai/gpt-5.2","model_name":"OpenAI: GPT-5.2","context_length":400000,"pricing":{"prompt":"0.00000175","completion":"0.000014","web_search":"0.01","input_cache_read":"0.000000175","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.12363449428094,"uptime_last_5m":98.21059876118376,"uptime_last_1d":96.87474722730013,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.75e-06,"_completion_per_m":1.4e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-07,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.2-20251211","model_id":"openai/gpt-5.2","model_name":"OpenAI: GPT-5.2","context_length":400000,"pricing":{"prompt":"0.0000035","completion":"0.000028","web_search":"0.01","input_cache_read":"0.00000035","discount":0},"provider_name":"OpenAI","tag":"openai/fast","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-06,"_completion_per_m":2.8e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.7125e-06,"_priciest_blended_per_m":1.085e-05,"_provider_spread_multiplier":4.0},{"id":"relace/relace-search","canonical_slug":"relace/relace-search-20251208","hugging_face_id":null,"name":"Relace: Relace Search","created":1765213560,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000003"},"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/relace/relace-search-20251208/endpoints"},"_prompt_per_m":1e-06,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Relace | relace/relace-search-20251208","model_id":"relace/relace-search","model_name":"Relace: Relace Search","context_length":256000,"pricing":{"prompt":"0.000001","completion":"0.000003","discount":0},"provider_name":"Relace","tag":"relace/bf16","quantization":"bf16","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["tools","tool_choice","response_format","temperature","top_p","stop","seed","max_tokens"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Relace","_cheapest_blended_per_m":1.6e-06,"_priciest_blended_per_m":1.6e-06,"_provider_spread_multiplier":1.0},{"id":"z-ai/glm-4.6v","canonical_slug":"z-ai/glm-4.6-20251208","hugging_face_id":"zai-org/GLM-4.6V","name":"Z.ai: GLM 4.6V","created":1765207462,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","context_length":131072,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.000000055"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.8,"top_p":0.6,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.6-20251208/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":3e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | z-ai/glm-4.6-20251208","model_id":"z-ai/glm-4.6v","model_name":"Z.ai: GLM 4.6V","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.000000055","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.48717948717949,"uptime_last_5m":null,"uptime_last_1d":96.90494959133717,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-08,"_cached_write_per_m":null},{"name":"Z.AI | z-ai/glm-4.6-20251208","model_id":"z-ai/glm-4.6v","model_name":"Z.ai: GLM 4.6V","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000005","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tool_choice","tools","top_k"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.08952959028832,"uptime_last_5m":null,"uptime_last_1d":94.45192739400936,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":4.8e-07,"_priciest_blended_per_m":4.8e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.1-codex-max","canonical_slug":"openai/gpt-5.1-codex-max-20251204","hugging_face_id":"","name":"OpenAI: GPT-5.1-Codex-Max","created":1764878934,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.000000125"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.1-codex-max-20251204/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-5.1-codex-max-20251204","model_id":"openai/gpt-5.1-codex-max","model_name":"OpenAI: GPT-5.1-Codex-Max","context_length":400000,"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.000000125","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":3.875e-06,"_priciest_blended_per_m":3.875e-06,"_provider_spread_multiplier":1.0},{"id":"mistralai/ministral-14b-2512","canonical_slug":"mistralai/ministral-14b-2512","hugging_face_id":"mistralai/Ministral-3-14B-Instruct-2512","name":"Mistral: Ministral 3 14B 2512","created":1764681735,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000002","input_cache_read":"0.00000002"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/ministral-14b-2512/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1034,"win_rate":39.6,"rank":97},{"arena":"models","category":"codecategories","elo":1089,"win_rate":44,"rank":94},{"arena":"models","category":"gamedev","elo":1074,"win_rate":43.6,"rank":93},{"arena":"models","category":"website","elo":1101,"win_rate":44.8,"rank":95}],"artificial_analysis":{"intelligence_index":11.2,"coding_index":14.4,"agentic_index":2.2}},"_prompt_per_m":2e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/ministral-14b-2512","model_id":"mistralai/ministral-14b-2512","model_name":"Mistral: Ministral 3 14B 2512","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.0000002","input_cache_read":"0.00000002","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.44615384615385,"uptime_last_5m":100,"uptime_last_1d":98.03430051597,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/ministral-14b-2512","model_id":"mistralai/ministral-14b-2512","model_name":"Mistral: Ministral 3 14B 2512","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.0000002","input_cache_read":"0.00000002","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.9599358974359,"uptime_last_5m":100,"uptime_last_1d":98.06947050664925,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/ministral-14b-2512","model_id":"mistralai/ministral-14b-2512","model_name":"Mistral: Ministral 3 14B 2512","context_length":262144,"pricing":{"prompt":"0.00000022","completion":"0.00000022","input_cache_read":"0.000000022","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":2.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":2e-07,"_priciest_blended_per_m":2.2e-07,"_provider_spread_multiplier":1.1},{"id":"mistralai/ministral-8b-2512","canonical_slug":"mistralai/ministral-8b-2512","hugging_face_id":"mistralai/Ministral-3-8B-Instruct-2512","name":"Mistral: Ministral 3 8B 2512","created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/ministral-8b-2512/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1076,"win_rate":46.2,"rank":91},{"arena":"models","category":"codecategories","elo":1077,"win_rate":42.9,"rank":95},{"arena":"models","category":"gamedev","elo":1026,"win_rate":38.7,"rank":103},{"arena":"models","category":"website","elo":1085,"win_rate":42.9,"rank":97}],"artificial_analysis":{"intelligence_index":9,"coding_index":9.7,"agentic_index":1.2}},"_prompt_per_m":1.5e-07,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/ministral-8b-2512","model_id":"mistralai/ministral-8b-2512","model_name":"Mistral: Ministral 3 8B 2512","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.0538714037459,"uptime_last_5m":98.31932773109243,"uptime_last_1d":99.37575280706137,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/ministral-8b-2512","model_id":"mistralai/ministral-8b-2512","model_name":"Mistral: Ministral 3 8B 2512","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.1761071060762,"uptime_last_5m":97.90454016298021,"uptime_last_1d":99.28197280913425,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/ministral-8b-2512","model_id":"mistralai/ministral-8b-2512","model_name":"Mistral: Ministral 3 8B 2512","context_length":262144,"pricing":{"prompt":"0.000000165","completion":"0.000000165","input_cache_read":"0.0000000165","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.65e-07,"_completion_per_m":1.65e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.65e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":1.5e-07,"_priciest_blended_per_m":1.65e-07,"_provider_spread_multiplier":1.1},{"id":"amazon/nova-2-lite-v1","canonical_slug":"amazon/nova-2-lite-v1","hugging_face_id":"","name":"Amazon: Nova 2 Lite","created":1764696672,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","context_length":1000000,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":65535,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/amazon/nova-2-lite-v1/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":23,"agentic_index":null}},"reasoning":{"mandatory":false},"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Amazon Bedrock | amazon/nova-2-lite-v1","model_id":"amazon/nova-2-lite-v1","model_name":"Amazon: Nova 2 Lite","context_length":1000000,"pricing":{"prompt":"0.0000003","completion":"0.0000025","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.817547625436,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | amazon/nova-2-lite-v1","model_id":"amazon/nova-2-lite-v1","model_name":"Amazon: Nova 2 Lite","context_length":1000000,"pricing":{"prompt":"0.0000003","completion":"0.0000025","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.94973791914985,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":9.6e-07,"_priciest_blended_per_m":9.6e-07,"_provider_spread_multiplier":1.0},{"id":"mistralai/ministral-3b-2512","canonical_slug":"mistralai/ministral-3b-2512","hugging_face_id":"mistralai/Ministral-3-3B-Instruct-2512","name":"Mistral: Ministral 3 3B 2512","created":1764681560,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000001","input_cache_read":"0.00000001"},"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/ministral-3b-2512/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1007,"win_rate":35.9,"rank":103},{"arena":"models","category":"codecategories","elo":1034,"win_rate":37.3,"rank":104},{"arena":"models","category":"gamedev","elo":985,"win_rate":33,"rank":111},{"arena":"models","category":"website","elo":1047,"win_rate":38.2,"rank":106}],"artificial_analysis":{"intelligence_index":7.1,"coding_index":4.8,"agentic_index":1.6}},"_prompt_per_m":1e-07,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/ministral-3b-2512","model_id":"mistralai/ministral-3b-2512","model_name":"Mistral: Ministral 3 3B 2512","context_length":131072,"pricing":{"prompt":"0.0000001","completion":"0.0000001","input_cache_read":"0.00000001","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.78824775013234,"uptime_last_5m":99.53271028037383,"uptime_last_1d":99.64890843923102,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/ministral-3b-2512","model_id":"mistralai/ministral-3b-2512","model_name":"Mistral: Ministral 3 3B 2512","context_length":131072,"pricing":{"prompt":"0.0000001","completion":"0.0000001","input_cache_read":"0.00000001","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.77553310886644,"uptime_last_5m":99.76580796252928,"uptime_last_1d":99.44689244198246,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/ministral-3b-2512","model_id":"mistralai/ministral-3b-2512","model_name":"Mistral: Ministral 3 3B 2512","context_length":131072,"pricing":{"prompt":"0.00000011","completion":"0.00000011","input_cache_read":"0.000000011","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-07,"_completion_per_m":1.1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":1e-07,"_priciest_blended_per_m":1.1e-07,"_provider_spread_multiplier":1.1},{"id":"mistralai/ministral-8b-2512:batch","canonical_slug":"mistralai/ministral-8b-2512","hugging_face_id":"mistralai/Ministral-3-8B-Instruct-2512","name":"Mistral: Ministral 3 8B 2512 (batch)","created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/ministral-8b-2512/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1076,"win_rate":46.2,"rank":91},{"arena":"models","category":"codecategories","elo":1077,"win_rate":42.9,"rank":95},{"arena":"models","category":"gamedev","elo":1026,"win_rate":38.7,"rank":103},{"arena":"models","category":"website","elo":1085,"win_rate":42.9,"rank":97}],"artificial_analysis":{"intelligence_index":9,"coding_index":9.7,"agentic_index":1.2}},"_prompt_per_m":1.5e-07,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/ministral-8b-2512:batch","model_id":"mistralai/ministral-8b-2512:batch","model_name":"Mistral: Ministral 3 8B 2512","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":1.5e-07,"_priciest_blended_per_m":1.5e-07,"_provider_spread_multiplier":1.0},{"id":"deepseek/deepseek-v3.2","canonical_slug":"deepseek/deepseek-v3.2-20251201","hugging_face_id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek: DeepSeek V3.2","created":1764594642,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.000000269","completion":"0.0000004","input_cache_read":"0.0000001345"},"top_provider":{"context_length":163840,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v3.2-20251201/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1177,"win_rate":49.5,"rank":56},{"arena":"models","category":"asciiart","elo":1109,"win_rate":40.5,"rank":54},{"arena":"models","category":"codecategories","elo":1188,"win_rate":49.3,"rank":63},{"arena":"models","category":"dataviz","elo":1179,"win_rate":48.1,"rank":62},{"arena":"models","category":"gamedev","elo":1167,"win_rate":46.6,"rank":66},{"arena":"models","category":"svg","elo":1072,"win_rate":40.8,"rank":64},{"arena":"models","category":"uicomponent","elo":1175,"win_rate":46.8,"rank":63},{"arena":"models","category":"website","elo":1195,"win_rate":50.2,"rank":61}],"artificial_analysis":{"intelligence_index":null,"coding_index":44.2,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":false},"_prompt_per_m":2.69e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.345e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":163840,"pricing":{"prompt":"0.0000002088","completion":"0.0000003096","input_cache_read":"0.0000000216","discount":0.28},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":96.03326935380679,"uptime_last_5m":92.97597042513863,"uptime_last_1d":97.38145911807925,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.088e-07,"_completion_per_m":3.096e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.16e-08,"_cached_write_per_m":null},{"name":"StreamLake | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":128000,"pricing":{"prompt":"0.0000002145","completion":"0.00000032175","input_cache_read":"0.00000002145","discount":0.25},"provider_name":"StreamLake","tag":"streamlake/fp8","quantization":"fp8","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","max_tokens","temperature","top_p","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":97.24884399783006,"uptime_last_5m":94.74078513635001,"uptime_last_1d":95.00770610766082,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.145e-07,"_completion_per_m":3.2175e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.145e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":163840,"pricing":{"prompt":"0.000000259","completion":"0.00000042","input_cache_read":"0.000000135","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","response_format","tools","tool_choice","structured_outputs","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.72654690618762,"uptime_last_5m":93.47150259067357,"uptime_last_1d":94.77022876661214,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.59e-07,"_completion_per_m":4.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":null},{"name":"AtlasCloud | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":163840,"pricing":{"prompt":"0.00000026","completion":"0.00000038","input_cache_read":"0.00000013","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice","seed","logit_bias","stop","min_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.94444885326561,"uptime_last_5m":99.97886951928156,"uptime_last_1d":99.91167683623932,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-07,"_completion_per_m":3.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null},{"name":"DeepInfra | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":163840,"pricing":{"prompt":"0.00000026","completion":"0.00000038","input_cache_read":"0.00000013","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.76689976689977,"uptime_last_5m":100,"uptime_last_1d":99.67402759736281,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-07,"_completion_per_m":3.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null},{"name":"Novita | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":163840,"pricing":{"prompt":"0.000000269","completion":"0.0000004","input_cache_read":"0.0000001345","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":false,"required":true,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.89842202426951,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.69e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.345e-07,"_cached_write_per_m":null},{"name":"Baidu | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":131072,"pricing":{"prompt":"0.00000028","completion":"0.00000042","input_cache_read":"0.000000028","discount":0},"provider_name":"Baidu","tag":"baidu/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","seed","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97694437048463,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.8e-07,"_completion_per_m":4.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.8e-08,"_cached_write_per_m":null},{"name":"Venice | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":160000,"pricing":{"prompt":"0.00000033","completion":"0.00000048","input_cache_read":"0.00000016","discount":0},"provider_name":"Venice","tag":"venice","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","structured_outputs","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.32318104906938,"uptime_last_5m":100,"uptime_last_1d":99.27997495565063,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-07,"_completion_per_m":4.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.6e-07,"_cached_write_per_m":null},{"name":"Alibaba | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":131072,"pricing":{"prompt":"0.0000003705","completion":"0.0000011115","input_cache_read":"0.0000000741","input_cache_write":"0.00000046345","discount":0},"provider_name":"Alibaba","tag":"alibaba/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":98304,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":98.66805954557326,"uptime_last_5m":98.87459807073955,"uptime_last_1d":97.46733387082803,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.705e-07,"_completion_per_m":1.1115e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.41e-08,"_cached_write_per_m":4.6345e-07},{"name":"Friendli | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":163840,"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000025","discount":0},"provider_name":"Friendli","tag":"friendli","quantization":"unknown","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","tools","tool_choice","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.91137570442545,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":163840,"pricing":{"prompt":"0.0000005","completion":"0.0000016","input_cache_read":"0.00000015","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.86281010632216,"uptime_last_5m":99.95244888254874,"uptime_last_1d":96.00890464392849,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":1.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"Google | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":163840,"pricing":{"prompt":"0.00000056","completion":"0.00000168","discount":0},"provider_name":"Google","tag":"google-vertex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":98.47509847509848,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.6e-07,"_completion_per_m":1.68e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Phala | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":163840,"pricing":{"prompt":"0.000001","completion":"0.000001","input_cache_read":"0.0000005","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.41176470588235,"uptime_last_5m":null,"uptime_last_1d":98.17387852322351,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null},{"name":"SambaNova | deepseek/deepseek-v3.2-20251201","model_id":"deepseek/deepseek-v3.2","model_name":"DeepSeek: DeepSeek V3.2","context_length":32768,"pricing":{"prompt":"0.000003","completion":"0.0000045","discount":0},"provider_name":"SambaNova","tag":"sambanova","quantization":"unknown","max_completion_tokens":7168,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":96.20253164556962,"uptime_last_5m":null,"uptime_last_1d":96.9550798914682,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":4.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":2.3904e-07,"_priciest_blended_per_m":3.45e-06,"_provider_spread_multiplier":14.432730923694779},{"id":"mistralai/mistral-large-2512:batch","canonical_slug":"mistralai/mistral-large-2512","hugging_face_id":"","name":"Mistral: Mistral Large 3 2512 (batch)","created":1764624472,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000005"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.0645,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-large-2512/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1143,"win_rate":46.9,"rank":69},{"arena":"models","category":"asciiart","elo":1095,"win_rate":40.3,"rank":56},{"arena":"models","category":"codecategories","elo":1166,"win_rate":47.6,"rank":71},{"arena":"models","category":"dataviz","elo":1157,"win_rate":45.7,"rank":70},{"arena":"models","category":"gamedev","elo":1116,"win_rate":41.5,"rank":84},{"arena":"models","category":"svg","elo":1032,"win_rate":38,"rank":73},{"arena":"models","category":"uicomponent","elo":1128,"win_rate":43,"rank":76},{"arena":"models","category":"website","elo":1182,"win_rate":49.5,"rank":68}],"artificial_analysis":{"intelligence_index":15.9,"coding_index":20.1,"agentic_index":5.5}},"_prompt_per_m":5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-large-2512:batch","model_id":"mistralai/mistral-large-2512:batch","model_name":"Mistral: Mistral Large 3 2512","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000005","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":8e-07,"_priciest_blended_per_m":8e-07,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-large-2512","canonical_slug":"mistralai/mistral-large-2512","hugging_face_id":"","name":"Mistral: Mistral Large 3 2512","created":1764624472,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000005"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.0645,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-large-2512/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1143,"win_rate":46.9,"rank":69},{"arena":"models","category":"asciiart","elo":1095,"win_rate":40.3,"rank":56},{"arena":"models","category":"codecategories","elo":1166,"win_rate":47.6,"rank":71},{"arena":"models","category":"dataviz","elo":1157,"win_rate":45.7,"rank":70},{"arena":"models","category":"gamedev","elo":1116,"win_rate":41.5,"rank":84},{"arena":"models","category":"svg","elo":1032,"win_rate":38,"rank":73},{"arena":"models","category":"uicomponent","elo":1128,"win_rate":43,"rank":76},{"arena":"models","category":"website","elo":1182,"win_rate":49.5,"rank":68}],"artificial_analysis":{"intelligence_index":15.9,"coding_index":20.1,"agentic_index":5.5}},"_prompt_per_m":5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-large-2512","model_id":"mistralai/mistral-large-2512","model_name":"Mistral: Mistral Large 3 2512","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000005","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.85598377281947,"uptime_last_5m":100,"uptime_last_1d":81.92102947841775,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-large-2512","model_id":"mistralai/mistral-large-2512","model_name":"Mistral: Mistral Large 3 2512","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000005","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":90.57203389830508,"uptime_last_5m":80.37974683544303,"uptime_last_1d":84.46035479861533,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-large-2512","model_id":"mistralai/mistral-large-2512","model_name":"Mistral: Mistral Large 3 2512","context_length":262144,"pricing":{"prompt":"0.00000055","completion":"0.00000165","input_cache_read":"0.000000055","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":209715,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-07,"_completion_per_m":1.65e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":8e-07,"_priciest_blended_per_m":8.8e-07,"_provider_spread_multiplier":1.1},{"id":"openrouter/bodybuilder","canonical_slug":"openrouter/bodybuilder","hugging_face_id":"","name":"Body Builder (beta)","created":1764903653,"description":"Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openrouter/bodybuilder/endpoints"},"_prompt_per_m":-1.0,"_completion_per_m":-1.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":-1.0,"_priciest_blended_per_m":-1.0,"_provider_spread_multiplier":null},{"id":"anthropic/claude-opus-4.5:batch","canonical_slug":"anthropic/claude-4.5-opus-20251124","hugging_face_id":"","name":"Anthropic: Claude Opus 4.5 (batch)","created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1258,"win_rate":58.5,"rank":29},{"arena":"models","category":"asciiart","elo":1216,"win_rate":54.7,"rank":20},{"arena":"models","category":"codecategories","elo":1267,"win_rate":59.5,"rank":30},{"arena":"models","category":"dataviz","elo":1263,"win_rate":58.4,"rank":23},{"arena":"models","category":"gamedev","elo":1265,"win_rate":59.3,"rank":29},{"arena":"models","category":"svg","elo":1220,"win_rate":58.7,"rank":25},{"arena":"models","category":"uicomponent","elo":1264,"win_rate":58.1,"rank":31},{"arena":"models","category":"website","elo":1267,"win_rate":59.7,"rank":31},{"arena":"agents","category":"androidnative","elo":1201,"win_rate":65.5,"rank":15},{"arena":"agents","category":"fullstack","elo":1181,"win_rate":60.2,"rank":22},{"arena":"agents","category":"mobileapps","elo":1229,"win_rate":60.7,"rank":12},{"arena":"agents","category":"webapps","elo":1190,"win_rate":55.1,"rank":23}]},"reasoning":{"mandatory":false},"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.5-opus-20251124:batch","model_id":"anthropic/claude-opus-4.5:batch","model_name":"Anthropic: Claude Opus 4.5","context_length":200000,"pricing":{"prompt":"0.0000025","completion":"0.0000125","web_search":"0.01","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":3.125e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":5.5e-06,"_priciest_blended_per_m":5.5e-06,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-opus-4.5","canonical_slug":"anthropic/claude-4.5-opus-20251124","hugging_face_id":"","name":"Anthropic: Claude Opus 4.5","created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1258,"win_rate":58.5,"rank":29},{"arena":"models","category":"asciiart","elo":1216,"win_rate":54.7,"rank":20},{"arena":"models","category":"codecategories","elo":1267,"win_rate":59.5,"rank":30},{"arena":"models","category":"dataviz","elo":1263,"win_rate":58.4,"rank":23},{"arena":"models","category":"gamedev","elo":1265,"win_rate":59.3,"rank":29},{"arena":"models","category":"svg","elo":1220,"win_rate":58.7,"rank":25},{"arena":"models","category":"uicomponent","elo":1264,"win_rate":58.1,"rank":31},{"arena":"models","category":"website","elo":1267,"win_rate":59.7,"rank":31},{"arena":"agents","category":"androidnative","elo":1201,"win_rate":65.5,"rank":15},{"arena":"agents","category":"fullstack","elo":1181,"win_rate":60.2,"rank":22},{"arena":"agents","category":"mobileapps","elo":1229,"win_rate":60.7,"rank":12},{"arena":"agents","category":"webapps","elo":1190,"win_rate":55.1,"rank":23}]},"reasoning":{"mandatory":false},"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06,"_endpoints":[{"name":"Claude Platform on AWS | anthropic/claude-4.5-opus-20251124","model_id":"anthropic/claude-opus-4.5","model_name":"Anthropic: Claude Opus 4.5","context_length":200000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Claude Platform on AWS","tag":"claude-on-aws","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.84025559105432,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Azure | anthropic/claude-4.5-opus-20251124","model_id":"anthropic/claude-opus-4.5","model_name":"Anthropic: Claude Opus 4.5","context_length":200000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Azure","tag":"azure/global","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","max_completion_tokens","tools","tool_choice","response_format","verbosity"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Anthropic | anthropic/claude-4.5-opus-20251124","model_id":"anthropic/claude-opus-4.5","model_name":"Anthropic: Claude Opus 4.5","context_length":200000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.11504424778761,"uptime_last_5m":null,"uptime_last_1d":99.90326481257557,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Amazon Bedrock | anthropic/claude-4.5-opus-20251124","model_id":"anthropic/claude-opus-4.5","model_name":"Anthropic: Claude Opus 4.5","context_length":200000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_k","stop","tool_choice","tools","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.84235417761428,"uptime_last_5m":100,"uptime_last_1d":99.93651668233787,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Google | anthropic/claude-4.5-opus-20251124","model_id":"anthropic/claude-opus-4.5","model_name":"Anthropic: Claude Opus 4.5","context_length":200000,"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tool_choice","tools","verbosity"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.8306806637318,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":2.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":6.25e-06},{"name":"Amazon Bedrock | anthropic/claude-4.5-opus-20251124","model_id":"anthropic/claude-opus-4.5","model_name":"Anthropic: Claude Opus 4.5","context_length":200000,"pricing":{"prompt":"0.0000055","completion":"0.0000275","web_search":"0.01","input_cache_read":"0.00000055","input_cache_write":"0.000006875","input_cache_write_1h":"0.000011","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_k","stop","tool_choice","tools","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-06,"_completion_per_m":2.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":6.875e-06}],"_cheapest_provider":"Claude Platform on AWS","_cheapest_blended_per_m":1.1e-05,"_priciest_blended_per_m":1.21e-05,"_provider_spread_multiplier":1.0999999999999999},{"id":"allenai/olmo-3-32b-think","canonical_slug":"allenai/olmo-3-32b-think-20251121","hugging_face_id":"allenai/Olmo-3-32B-Think","name":"AllenAI: Olmo 3 32B Think","created":1763758276,"description":"Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000005"},"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/allenai/olmo-3-32b-think-20251121/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":1.5e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":2.55e-07,"_priciest_blended_per_m":2.55e-07,"_provider_spread_multiplier":null},{"id":"openai/gpt-5.1-codex","canonical_slug":"openai/gpt-5.1-codex-20251113","hugging_face_id":"","name":"OpenAI: GPT-5.1-Codex","created":1763060298,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.00000013"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.1-codex-20251113/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"fullstack","elo":1086,"win_rate":44.5,"rank":30},{"arena":"agents","category":"mobileapps","elo":1191,"win_rate":53.4,"rank":24},{"arena":"agents","category":"webapps","elo":1049,"win_rate":44,"rank":36},{"arena":"models","category":"codecategories","elo":1177,"win_rate":54.6,"rank":67},{"arena":"models","category":"dataviz","elo":1234,"win_rate":55.9,"rank":40},{"arena":"models","category":"gamedev","elo":1174,"win_rate":50.5,"rank":61},{"arena":"models","category":"uicomponent","elo":1263,"win_rate":60,"rank":32},{"arena":"models","category":"website","elo":1181,"win_rate":56.1,"rank":69}]},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-5.1-codex-20251113","model_id":"openai/gpt-5.1-codex","model_name":"OpenAI: GPT-5.1-Codex","context_length":400000,"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.00000013","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":3.875e-06,"_priciest_blended_per_m":3.875e-06,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5.1-codex-mini","canonical_slug":"openai/gpt-5.1-codex-mini-20251113","hugging_face_id":"","name":"OpenAI: GPT-5.1-Codex-Mini","created":1763057820,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000002","web_search":"0.01","input_cache_read":"0.00000003"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.1-codex-mini-20251113/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1032,"win_rate":32.8,"rank":99},{"arena":"models","category":"asciiart","elo":1131,"win_rate":43,"rank":50},{"arena":"models","category":"codecategories","elo":1118,"win_rate":41.5,"rank":88},{"arena":"models","category":"dataviz","elo":1118,"win_rate":40.6,"rank":85},{"arena":"models","category":"gamedev","elo":1129,"win_rate":43.4,"rank":81},{"arena":"models","category":"svg","elo":1018,"win_rate":35.3,"rank":77},{"arena":"models","category":"uicomponent","elo":1107,"win_rate":41,"rank":84},{"arena":"models","category":"website","elo":1130,"win_rate":42.8,"rank":88}]},"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-5.1-codex-mini-20251113","model_id":"openai/gpt-5.1-codex-mini","model_name":"OpenAI: GPT-5.1-Codex-Mini","context_length":400000,"pricing":{"prompt":"0.00000025","completion":"0.000002","web_search":"0.01","input_cache_read":"0.00000003","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":7.75e-07,"_priciest_blended_per_m":7.75e-07,"_provider_spread_multiplier":1.0},{"id":"moonshotai/kimi-k2-thinking","canonical_slug":"moonshotai/kimi-k2-thinking-20251106","hugging_face_id":"moonshotai/Kimi-K2-Thinking","name":"MoonshotAI: Kimi K2 Thinking","created":1762440622,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000025","input_cache_read":"0.00000015"},"top_provider":{"context_length":262144,"max_completion_tokens":100352,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2-thinking-20251106/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"website","elo":1133,"win_rate":48.8,"rank":87}],"artificial_analysis":{"intelligence_index":null,"coding_index":21,"agentic_index":null}},"reasoning":{"mandatory":true,"default_enabled":true},"_prompt_per_m":6e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | moonshotai/kimi-k2-thinking-20251106","model_id":"moonshotai/kimi-k2-thinking","model_name":"MoonshotAI: Kimi K2 Thinking","context_length":262144,"pricing":{"prompt":"0.0000006","completion":"0.0000025","input_cache_read":"0.00000015","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":100352,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.97986577181209,"uptime_last_5m":82.85714285714286,"uptime_last_1d":92.909100705857,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null},{"name":"Google | moonshotai/kimi-k2-thinking-20251106","model_id":"moonshotai/kimi-k2-thinking","model_name":"MoonshotAI: Kimi K2 Thinking","context_length":262144,"pricing":{"prompt":"0.0000006","completion":"0.0000025","discount":0},"provider_name":"Google","tag":"google-vertex","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.97807017543859,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":1.17e-06,"_priciest_blended_per_m":1.17e-06,"_provider_spread_multiplier":1.0},{"id":"google/gemini-3-pro-image-preview","canonical_slug":"google/gemini-3-pro-image-preview-20251120","hugging_face_id":"","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","created":1763653797,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","image_output":"0.00012","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375"},"top_provider":{"context_length":65536,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3-pro-image-preview-20251120/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1273,"win_rate":65.8,"rank":3},{"arena":"models","category":"image","elo":1262,"win_rate":62.1,"rank":3},{"arena":"models","category":"logo","elo":1251,"win_rate":61,"rank":4},{"arena":"models","category":"imageediting","elo":1273,"win_rate":66,"rank":2}]},"reasoning":{"mandatory":true},"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07,"_endpoints":[{"name":"Google AI Studio | google/gemini-3-pro-image-preview-20251120","model_id":"google/gemini-3-pro-image-preview","model_name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","context_length":65536,"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","image_output":"0.00012","audio":"0.000002","input_audio_cache":"0.0000002","web_search":"0.014","internal_reasoning":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000000375","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/global","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99802691290793,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":1.2e-05,"_image_per_m":2e-06,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":3.75e-07},{"name":"Google AI Studio | google/gemini-3-pro-image-preview-20251120","model_id":"google/gemini-3-pro-image-preview","model_name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","context_length":65536,"pricing":{"prompt":"0.000001","completion":"0.000006","image":"0.000001","image_output":"0.00006","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.000006","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/global/flex","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99802691290793,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":6e-06,"_image_per_m":1e-06,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.875e-07}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":2.4999999999999998e-06,"_priciest_blended_per_m":4.9999999999999996e-06,"_provider_spread_multiplier":2.0},{"id":"openai/gpt-5.1","canonical_slug":"openai/gpt-5.1-20251113","hugging_face_id":"","name":"OpenAI: GPT-5.1","created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.000000125"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.1-20251113/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1105,"win_rate":43.7,"rank":86},{"arena":"models","category":"asciiart","elo":1145,"win_rate":48.6,"rank":46},{"arena":"models","category":"codecategories","elo":1195,"win_rate":53,"rank":57},{"arena":"models","category":"dataviz","elo":1225,"win_rate":58,"rank":42},{"arena":"models","category":"gamedev","elo":1215,"win_rate":55.9,"rank":44},{"arena":"models","category":"svg","elo":1189,"win_rate":57.4,"rank":36},{"arena":"models","category":"uicomponent","elo":1193,"win_rate":52.9,"rank":56},{"arena":"models","category":"website","elo":1207,"win_rate":54,"rank":54}],"artificial_analysis":{"intelligence_index":37.5,"coding_index":49.4,"agentic_index":21.6}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"none"},"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5.1-20251113","model_id":"openai/gpt-5.1","model_name":"OpenAI: GPT-5.1","context_length":400000,"pricing":{"prompt":"0.000000625","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000000625","discount":0},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.25e-07,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6.25e-08,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.1-20251113","model_id":"openai/gpt-5.1","model_name":"OpenAI: GPT-5.1","context_length":400000,"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.000000125","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.0316169828365,"uptime_last_5m":94.51152579582876,"uptime_last_1d":96.10869933567434,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.1-20251113","model_id":"openai/gpt-5.1","model_name":"OpenAI: GPT-5.1","context_length":400000,"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.00000013","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5.1-20251113","model_id":"openai/gpt-5.1","model_name":"OpenAI: GPT-5.1","context_length":400000,"pricing":{"prompt":"0.000001375","completion":"0.000011","web_search":"0.01","input_cache_read":"0.000000143","discount":0},"provider_name":"Azure","tag":"azure/swedencentral","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.375e-06,"_completion_per_m":1.1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.43e-07,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5.1-20251113","model_id":"openai/gpt-5.1","model_name":"OpenAI: GPT-5.1","context_length":400000,"pricing":{"prompt":"0.0000025","completion":"0.00002","web_search":"0.01","input_cache_read":"0.00000025","discount":0},"provider_name":"OpenAI","tag":"openai/fast","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":2e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":1.9375e-06,"_priciest_blended_per_m":7.75e-06,"_provider_spread_multiplier":4.0},{"id":"perplexity/sonar-pro-search","canonical_slug":"perplexity/sonar-pro-search","hugging_face_id":"","name":"Perplexity: Sonar Pro Search","created":1761854366,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.018"},"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p","web_search_options"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/perplexity/sonar-pro-search/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Perplexity | perplexity/sonar-pro-search","model_id":"perplexity/sonar-pro-search","model_name":"Perplexity: Sonar Pro Search","context_length":200000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.018","discount":0},"provider_name":"Perplexity","tag":"perplexity","quantization":"unknown","max_completion_tokens":8000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97417522112467,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Perplexity","_cheapest_blended_per_m":6.5999999999999995e-06,"_priciest_blended_per_m":6.5999999999999995e-06,"_provider_spread_multiplier":1.0},{"id":"amazon/nova-premier-v1","canonical_slug":"amazon/nova-premier-v1","hugging_face_id":"","name":"Amazon: Nova Premier 1.0","created":1761950332,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.0000125","input_cache_read":"0.000000625"},"top_provider":{"context_length":1000000,"max_completion_tokens":32000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/amazon/nova-premier-v1/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"website","elo":855,"win_rate":26.2,"rank":123}]},"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6.25e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Amazon Bedrock | amazon/nova-premier-v1","model_id":"amazon/nova-premier-v1","model_name":"Amazon: Nova Premier 1.0","context_length":1000000,"pricing":{"prompt":"0.0000025","completion":"0.0000125","input_cache_read":"0.000000625","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1.25e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6.25e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":5.5e-06,"_priciest_blended_per_m":5.5e-06,"_provider_spread_multiplier":1.0},{"id":"mistralai/voxtral-small-24b-2507","canonical_slug":"mistralai/voxtral-small-24b-2507","hugging_face_id":"mistralai/Voxtral-Small-24B-2507","name":"Mistral: Voxtral Small 24B 2507","created":1761835144,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","context_length":32000,"architecture":{"modality":"text+file+audio->text","input_modalities":["text","audio","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000003","audio":"0.0001","input_cache_read":"0.00000001"},"top_provider":{"context_length":32000,"max_completion_tokens":25600,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.2,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/voxtral-small-24b-2507/endpoints"},"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/voxtral-small-24b-2507","model_id":"mistralai/voxtral-small-24b-2507","model_name":"Mistral: Voxtral Small 24B 2507","context_length":32000,"pricing":{"prompt":"0.0000001","completion":"0.0000003","audio":"0.0001","input_cache_read":"0.00000001","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":25600,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.54574951330305,"uptime_last_5m":99.19354838709677,"uptime_last_1d":99.41866724082247,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":1.6e-07,"_priciest_blended_per_m":1.6e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-oss-safeguard-20b","canonical_slug":"openai/gpt-oss-safeguard-20b","hugging_face_id":"openai/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","created":1761752836,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000000075","completion":"0.0000003","input_cache_read":"0.0000000375"},"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-oss-safeguard-20b/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":7.5e-08,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Groq | openai/gpt-oss-safeguard-20b","model_id":"openai/gpt-oss-safeguard-20b","model_name":"OpenAI: gpt-oss-safeguard-20b","context_length":131072,"pricing":{"prompt":"0.000000075","completion":"0.0000003","input_cache_read":"0.0000000375","discount":0},"provider_name":"Groq","tag":"groq","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-08,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Groq","_cheapest_blended_per_m":1.4249999999999999e-07,"_priciest_blended_per_m":1.4249999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-vl-32b-instruct","canonical_slug":"qwen/qwen3-vl-32b-instruct","hugging_face_id":"Qwen/Qwen3-VL-32B-Instruct","name":"Qwen: Qwen3 VL 32B Instruct","created":1761231332,"description":"Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000000104","completion":"0.000000416"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.7,"top_p":0.8,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-32b-instruct/endpoints"},"_prompt_per_m":1.04e-07,"_completion_per_m":4.16e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-vl-32b-instruct","model_id":"qwen/qwen3-vl-32b-instruct","model_name":"Qwen: Qwen3 VL 32B Instruct","context_length":131072,"pricing":{"prompt":"0.000000104","completion":"0.000000416","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":129024,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99919247124794,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.04e-07,"_completion_per_m":4.16e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":1.9760000000000002e-07,"_priciest_blended_per_m":1.9760000000000002e-07,"_provider_spread_multiplier":1.0},{"id":"ibm-granite/granite-4.0-h-micro","canonical_slug":"ibm-granite/granite-4.0-h-micro","hugging_face_id":"ibm-granite/granite-4.0-h-micro","name":"IBM: Granite 4.0 Micro","created":1760927695,"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...","context_length":131000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000017","completion":"0.000000112"},"top_provider":{"context_length":131000,"max_completion_tokens":117900,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/ibm-granite/granite-4.0-h-micro/endpoints"},"_prompt_per_m":1.7e-08,"_completion_per_m":1.12e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Cloudflare | ibm-granite/granite-4.0-h-micro","model_id":"ibm-granite/granite-4.0-h-micro","model_name":"IBM: Granite 4.0 Micro","context_length":131000,"pricing":{"prompt":"0.000000017","completion":"0.000000112","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":117900,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.7e-08,"_completion_per_m":1.12e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Cloudflare","_cheapest_blended_per_m":4.55e-08,"_priciest_blended_per_m":4.55e-08,"_provider_spread_multiplier":1.0},{"id":"minimax/minimax-m2","canonical_slug":"minimax/minimax-m2","hugging_face_id":"MiniMaxAI/MiniMax-M2","name":"MiniMax: MiniMax M2","created":1761252093,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000255","completion":"0.00000102"},"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m2/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1142,"win_rate":48.3,"rank":70},{"arena":"models","category":"codecategories","elo":1159,"win_rate":48.1,"rank":74},{"arena":"models","category":"dataviz","elo":1161,"win_rate":50,"rank":68},{"arena":"models","category":"gamedev","elo":1154,"win_rate":48.1,"rank":69},{"arena":"models","category":"svg","elo":1140,"win_rate":55.3,"rank":50},{"arena":"models","category":"uicomponent","elo":1163,"win_rate":49.2,"rank":68},{"arena":"models","category":"website","elo":1162,"win_rate":48,"rank":74}]},"reasoning":{"mandatory":true},"_prompt_per_m":2.55e-07,"_completion_per_m":1.02e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Minimax | minimax/minimax-m2","model_id":"minimax/minimax-m2","model_name":"MiniMax: MiniMax M2","context_length":204800,"pricing":{"prompt":"0.000000255","completion":"0.00000102","discount":0.15},"provider_name":"Minimax","tag":"minimax/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.73685784343041,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.55e-07,"_completion_per_m":1.02e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | minimax/minimax-m2","model_id":"minimax/minimax-m2","model_name":"MiniMax: MiniMax M2","context_length":204800,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.81290926099157,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Google | minimax/minimax-m2","model_id":"minimax/minimax-m2","model_name":"MiniMax: MiniMax M2","context_length":196608,"pricing":{"prompt":"0.0000003","completion":"0.0000012","discount":0},"provider_name":"Google","tag":"google-vertex","quantization":"unknown","max_completion_tokens":176947,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":97.8502080443828,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Minimax","_cheapest_blended_per_m":4.845e-07,"_priciest_blended_per_m":5.699999999999999e-07,"_provider_spread_multiplier":1.1764705882352942},{"id":"openai/gpt-5-image-mini","canonical_slug":"openai/gpt-5-image-mini","hugging_face_id":"","name":"OpenAI: GPT-5 Image Mini","created":1760624583,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["file","image","text"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.000002","image_output":"0.000008","web_search":"0.01","input_cache_read":"0.00000025"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5-image-mini/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1187,"win_rate":47.7,"rank":9},{"arena":"models","category":"image","elo":1202,"win_rate":51,"rank":9},{"arena":"models","category":"logo","elo":1219,"win_rate":51.4,"rank":6}]},"reasoning":{"mandatory":true},"_prompt_per_m":2.5e-06,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5-image-mini","model_id":"openai/gpt-5-image-mini","model_name":"OpenAI: GPT-5 Image Mini","context_length":400000,"pricing":{"prompt":"0.0000025","completion":"0.000002","image_output":"0.000008","web_search":"0.01","input_cache_read":"0.00000025","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.35e-06,"_priciest_blended_per_m":2.35e-06,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-haiku-4.5","canonical_slug":"anthropic/claude-4.5-haiku-20251001","hugging_face_id":"","name":"Anthropic: Claude Haiku 4.5","created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1116,"win_rate":41.1,"rank":83},{"arena":"models","category":"asciiart","elo":1166,"win_rate":49.3,"rank":38},{"arena":"models","category":"codecategories","elo":1139,"win_rate":44.9,"rank":81},{"arena":"models","category":"dataviz","elo":1145,"win_rate":45.7,"rank":76},{"arena":"models","category":"gamedev","elo":1133,"win_rate":44.7,"rank":75},{"arena":"models","category":"svg","elo":1065,"win_rate":39.1,"rank":66},{"arena":"models","category":"uicomponent","elo":1126,"win_rate":42.6,"rank":78},{"arena":"models","category":"website","elo":1142,"win_rate":45.1,"rank":82}],"artificial_analysis":{"intelligence_index":29.9,"coding_index":43.9,"agentic_index":16.5}},"reasoning":{"mandatory":false},"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.5-haiku-20251001","model_id":"anthropic/claude-haiku-4.5","model_name":"Anthropic: Claude Haiku 4.5","context_length":200000,"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.76660301294292,"uptime_last_5m":98.54651162790698,"uptime_last_1d":99.93377645875745,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06},{"name":"Google | anthropic/claude-4.5-haiku-20251001","model_id":"anthropic/claude-haiku-4.5","model_name":"Anthropic: Claude Haiku 4.5","context_length":200000,"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8876404494382,"uptime_last_5m":100,"uptime_last_1d":99.90717388258372,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06},{"name":"Azure | anthropic/claude-4.5-haiku-20251001","model_id":"anthropic/claude-haiku-4.5","model_name":"Anthropic: Claude Haiku 4.5","context_length":200000,"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002","discount":0},"provider_name":"Azure","tag":"azure/global","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","top_k","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.98405894647348,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06},{"name":"Amazon Bedrock | anthropic/claude-4.5-haiku-20251001","model_id":"anthropic/claude-haiku-4.5","model_name":"Anthropic: Claude Haiku 4.5","context_length":200000,"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/global","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.93592185930518,"uptime_last_5m":99.91910694062449,"uptime_last_1d":99.96723749599293,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":1.25e-06},{"name":"Amazon Bedrock | anthropic/claude-4.5-haiku-20251001","model_id":"anthropic/claude-haiku-4.5","model_name":"Anthropic: Claude Haiku 4.5","context_length":200000,"pricing":{"prompt":"0.0000011","completion":"0.0000055","web_search":"0.01","input_cache_read":"0.00000011","input_cache_write":"0.000001375","input_cache_write_1h":"0.0000022","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/us","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-06,"_completion_per_m":5.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":1.375e-06},{"name":"Amazon Bedrock | anthropic/claude-4.5-haiku-20251001","model_id":"anthropic/claude-haiku-4.5","model_name":"Anthropic: Claude Haiku 4.5","context_length":200000,"pricing":{"prompt":"0.0000011","completion":"0.0000055","web_search":"0.01","input_cache_read":"0.00000011","input_cache_write":"0.000001375","input_cache_write_1h":"0.0000022","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-06,"_completion_per_m":5.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":1.375e-06},{"name":"Google | anthropic/claude-4.5-haiku-20251001","model_id":"anthropic/claude-haiku-4.5","model_name":"Anthropic: Claude Haiku 4.5","context_length":200000,"pricing":{"prompt":"0.0000011","completion":"0.0000055","web_search":"0.01","input_cache_read":"0.00000011","input_cache_write":"0.000001375","input_cache_write_1h":"0.0000022","discount":0},"provider_name":"Google","tag":"google-vertex/us-east5","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-06,"_completion_per_m":5.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":1.375e-06},{"name":"Google | anthropic/claude-4.5-haiku-20251001","model_id":"anthropic/claude-haiku-4.5","model_name":"Anthropic: Claude Haiku 4.5","context_length":200000,"pricing":{"prompt":"0.0000011","completion":"0.0000055","web_search":"0.01","input_cache_read":"0.00000011","input_cache_write":"0.000001375","input_cache_write_1h":"0.0000022","discount":0},"provider_name":"Google","tag":"google-vertex/europe","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.78540772532189,"uptime_last_5m":100,"uptime_last_1d":99.88576176134593,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-06,"_completion_per_m":5.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":1.375e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":2.2e-06,"_priciest_blended_per_m":2.4199999999999997e-06,"_provider_spread_multiplier":1.0999999999999999},{"id":"qwen/qwen3-vl-8b-thinking","canonical_slug":"qwen/qwen3-vl-8b-thinking","hugging_face_id":"Qwen/Qwen3-VL-8B-Thinking","name":"Qwen: Qwen3 VL 8B Thinking","created":1760463746,"description":"Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000018","completion":"0.0000021"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-8b-thinking/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":1.8e-07,"_completion_per_m":2.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-vl-8b-thinking","model_id":"qwen/qwen3-vl-8b-thinking","model_name":"Qwen: Qwen3 VL 8B Thinking","context_length":131072,"pricing":{"prompt":"0.00000018","completion":"0.0000021","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":126976,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.8e-07,"_completion_per_m":2.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":7.559999999999998e-07,"_priciest_blended_per_m":7.559999999999998e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-vl-8b-instruct","canonical_slug":"qwen/qwen3-vl-8b-instruct","hugging_face_id":"Qwen/Qwen3-VL-8B-Instruct","name":"Qwen: Qwen3 VL 8B Instruct","created":1760463308,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.000000117","completion":"0.000000455"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.7,"top_p":0.8,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-8b-instruct/endpoints"},"_prompt_per_m":1.17e-07,"_completion_per_m":4.55e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-vl-8b-instruct","model_id":"qwen/qwen3-vl-8b-instruct","model_name":"Qwen: Qwen3 VL 8B Instruct","context_length":131072,"pricing":{"prompt":"0.000000117","completion":"0.000000455","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":129024,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98718824735224,"uptime_last_5m":99.97596153846153,"uptime_last_1d":99.97703684614399,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.17e-07,"_completion_per_m":4.55e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen3-vl-8b-instruct","model_id":"qwen/qwen3-vl-8b-instruct","model_name":"Qwen: Qwen3 VL 8B Instruct","context_length":262144,"pricing":{"prompt":"0.00000025","completion":"0.00000075","input_cache_read":"0.00000012","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.63135971437073,"uptime_last_5m":99.20760697305863,"uptime_last_1d":98.81706147884792,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":2.184e-07,"_priciest_blended_per_m":4e-07,"_provider_spread_multiplier":1.8315018315018314},{"id":"anthropic/claude-haiku-4.5:batch","canonical_slug":"anthropic/claude-4.5-haiku-20251001","hugging_face_id":"","name":"Anthropic: Claude Haiku 4.5 (batch)","created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000025","web_search":"0.01","input_cache_read":"0.00000005","input_cache_write":"0.000000625","input_cache_write_1h":"0.000001"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1116,"win_rate":41.1,"rank":83},{"arena":"models","category":"asciiart","elo":1166,"win_rate":49.3,"rank":38},{"arena":"models","category":"codecategories","elo":1139,"win_rate":44.9,"rank":81},{"arena":"models","category":"dataviz","elo":1145,"win_rate":45.7,"rank":76},{"arena":"models","category":"gamedev","elo":1133,"win_rate":44.7,"rank":75},{"arena":"models","category":"svg","elo":1065,"win_rate":39.1,"rank":66},{"arena":"models","category":"uicomponent","elo":1126,"win_rate":42.6,"rank":78},{"arena":"models","category":"website","elo":1142,"win_rate":45.1,"rank":82}],"artificial_analysis":{"intelligence_index":29.9,"coding_index":43.9,"agentic_index":16.5}},"reasoning":{"mandatory":false},"_prompt_per_m":5e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":6.25e-07,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.5-haiku-20251001:batch","model_id":"anthropic/claude-haiku-4.5:batch","model_name":"Anthropic: Claude Haiku 4.5","context_length":200000,"pricing":{"prompt":"0.0000005","completion":"0.0000025","web_search":"0.01","input_cache_read":"0.00000005","input_cache_write":"0.000000625","input_cache_write_1h":"0.000001","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":6.25e-07}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":1.1e-06,"_priciest_blended_per_m":1.1e-06,"_provider_spread_multiplier":1.0},{"id":"google/gemini-2.5-flash-image","canonical_slug":"google/gemini-2.5-flash-image","hugging_face_id":"","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","created":1759870431,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","context_length":32768,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","image_output":"0.00003","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-flash-image/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1190,"win_rate":56.9,"rank":8},{"arena":"models","category":"image","elo":1204,"win_rate":55.6,"rank":8},{"arena":"models","category":"logo","elo":1180,"win_rate":51.4,"rank":9}]},"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08,"_endpoints":[{"name":"Google AI Studio | google/gemini-2.5-flash-image","model_id":"google/gemini-2.5-flash-image","model_name":"Google: Nano Banana (Gemini 2.5 Flash Image)","context_length":32768,"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","image_output":"0.00003","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":29491,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.91380796414411,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-2.5-flash-image","model_id":"google/gemini-2.5-flash-image","model_name":"Google: Nano Banana (Gemini 2.5 Flash Image)","context_length":32768,"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","image_output":"0.000015","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.00000125","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":29491,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.91380796414411,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":1.5e-07,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-2.5-flash-image","model_id":"google/gemini-2.5-flash-image","model_name":"Google: Nano Banana (Gemini 2.5 Flash Image)","context_length":32768,"pricing":{"prompt":"0.00000054","completion":"0.0000045","image":"0.00000054","image_output":"0.000054","audio":"0.0000018","input_audio_cache":"0.00000018","web_search":"0.014","internal_reasoning":"0.0000045","input_cache_read":"0.000000054","input_cache_write":"0.00000015","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":29491,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.91380796414411,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.4e-07,"_completion_per_m":4.5e-06,"_image_per_m":5.4e-07,"_request_per_m":null,"_cached_read_per_m":5.4e-08,"_cached_write_per_m":1.5e-07},{"name":"Google | google/gemini-2.5-flash-image","model_id":"google/gemini-2.5-flash-image","model_name":"Google: Nano Banana (Gemini 2.5 Flash Image)","context_length":32768,"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","image_output":"0.00003","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.53825857519789,"uptime_last_5m":98.80952380952381,"uptime_last_1d":99.5227727284235,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google | google/gemini-2.5-flash-image","model_id":"google/gemini-2.5-flash-image","model_name":"Google: Nano Banana (Gemini 2.5 Flash Image)","context_length":32768,"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","image_output":"0.000015","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.00000125","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.53825857519789,"uptime_last_5m":98.80952380952381,"uptime_last_1d":99.5227727284235,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":1.5e-07,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":4.16666666666667e-08}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":4.8e-07,"_priciest_blended_per_m":1.728e-06,"_provider_spread_multiplier":3.6000000000000005},{"id":"qwen/qwen3-vl-30b-a3b-thinking","canonical_slug":"qwen/qwen3-vl-30b-a3b-thinking","hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","created":1759794479,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000024"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.8,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-30b-a3b-thinking/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":2e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-vl-30b-a3b-thinking","model_id":"qwen/qwen3-vl-30b-a3b-thinking","model_name":"Qwen: Qwen3 VL 30B A3B Thinking","context_length":131072,"pricing":{"prompt":"0.0000002","completion":"0.0000024","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":126976,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3-vl-30b-a3b-thinking","model_id":"qwen/qwen3-vl-30b-a3b-thinking","model_name":"Qwen: Qwen3 VL 30B A3B Thinking","context_length":262144,"pricing":{"prompt":"0.00000029","completion":"0.000001","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.19917334022217,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.9e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"SiliconFlow","_cheapest_blended_per_m":5.03e-07,"_priciest_blended_per_m":8.6e-07,"_provider_spread_multiplier":1.7097415506958251},{"id":"openai/gpt-5-image","canonical_slug":"openai/gpt-5-image","hugging_face_id":"","name":"OpenAI: GPT-5 Image","created":1760447986,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00001","image_output":"0.00004","web_search":"0.01","input_cache_read":"0.00000125"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5-image/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1194,"win_rate":48.9,"rank":7},{"arena":"models","category":"image","elo":1209,"win_rate":53.9,"rank":7},{"arena":"models","category":"logo","elo":1213,"win_rate":52.7,"rank":7}]},"reasoning":{"mandatory":true},"_prompt_per_m":1e-05,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5-image","model_id":"openai/gpt-5-image","model_name":"OpenAI: GPT-5 Image","context_length":400000,"pricing":{"prompt":"0.00001","completion":"0.00001","image_output":"0.00004","web_search":"0.01","input_cache_read":"0.00000125","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":9.999999999999999e-06,"_priciest_blended_per_m":9.999999999999999e-06,"_provider_spread_multiplier":1.0},{"id":"openrouter/pareto-code","canonical_slug":"openrouter/pareto-code","hugging_face_id":"","name":"Pareto Code Router","created":1776747900,"description":"The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...","context_length":2000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openrouter/pareto-code/endpoints"},"_prompt_per_m":-1.0,"_completion_per_m":-1.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":-1.0,"_priciest_blended_per_m":-1.0,"_provider_spread_multiplier":null},{"id":"qwen/qwen3-vl-30b-a3b-instruct","canonical_slug":"qwen/qwen3-vl-30b-a3b-instruct","hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","created":1759794476,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000013","completion":"0.00000052"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.7,"top_p":0.8,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-30b-a3b-instruct/endpoints"},"_prompt_per_m":1.3e-07,"_completion_per_m":5.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-vl-30b-a3b-instruct","model_id":"qwen/qwen3-vl-30b-a3b-instruct","model_name":"Qwen: Qwen3 VL 30B A3B Instruct","context_length":131072,"pricing":{"prompt":"0.00000013","completion":"0.00000052","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":129024,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.96510816468947,"uptime_last_5m":100,"uptime_last_1d":99.94732865466487,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":5.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3-vl-30b-a3b-instruct","model_id":"qwen/qwen3-vl-30b-a3b-instruct","model_name":"Qwen: Qwen3 VL 30B A3B Instruct","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.7106146544739,"uptime_last_5m":100,"uptime_last_1d":99.78333580666887,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3-vl-30b-a3b-instruct","model_id":"qwen/qwen3-vl-30b-a3b-instruct","model_name":"Qwen: Qwen3 VL 30B A3B Instruct","context_length":131072,"pricing":{"prompt":"0.0000002","completion":"0.0000007","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.98308392973325,"uptime_last_5m":98.72881355932203,"uptime_last_1d":96.7236374310969,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3-vl-30b-a3b-instruct","model_id":"qwen/qwen3-vl-30b-a3b-instruct","model_name":"Qwen: Qwen3 VL 30B A3B Instruct","context_length":262144,"pricing":{"prompt":"0.00000029","completion":"0.000001","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":0,"uptime_last_5m":null,"uptime_last_1d":72.38230242891804,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.9e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":2.47e-07,"_priciest_blended_per_m":5.03e-07,"_provider_spread_multiplier":2.0364372469635628},{"id":"z-ai/glm-4.6","canonical_slug":"z-ai/glm-4.6","hugging_face_id":"zai-org/GLM-4.6","name":"Z.ai: GLM 4.6","created":1759235576,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000043","completion":"0.00000175","input_cache_read":"0.00000008"},"top_provider":{"context_length":198000,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.6,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.6/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1110,"win_rate":52.6,"rank":29},{"arena":"agents","category":"fullstack","elo":1053,"win_rate":42.3,"rank":36},{"arena":"agents","category":"godotgamedev","elo":1180,"win_rate":53.2,"rank":13},{"arena":"agents","category":"mobileapps","elo":1136,"win_rate":47.2,"rank":30},{"arena":"models","category":"3d","elo":1173,"win_rate":54.2,"rank":58},{"arena":"models","category":"codecategories","elo":1190,"win_rate":54.3,"rank":61},{"arena":"models","category":"dataviz","elo":1182,"win_rate":52.6,"rank":60},{"arena":"models","category":"gamedev","elo":1187,"win_rate":54.8,"rank":56},{"arena":"models","category":"svg","elo":1149,"win_rate":52.1,"rank":47},{"arena":"models","category":"uicomponent","elo":1174,"win_rate":52.5,"rank":64},{"arena":"models","category":"website","elo":1194,"win_rate":54.3,"rank":62}],"artificial_analysis":{"intelligence_index":29.3,"coding_index":45.8,"agentic_index":18.6}},"reasoning":{"mandatory":false},"_prompt_per_m":4.3e-07,"_completion_per_m":1.75e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Venice | z-ai/glm-4.6","model_id":"z-ai/glm-4.6","model_name":"Z.ai: GLM 4.6","context_length":198000,"pricing":{"prompt":"0.00000043","completion":"0.00000175","input_cache_read":"0.00000008","discount":0},"provider_name":"Venice","tag":"venice/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.94669509594883,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.3e-07,"_completion_per_m":1.75e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8e-08,"_cached_write_per_m":null},{"name":"DeepInfra | z-ai/glm-4.6","model_id":"z-ai/glm-4.6","model_name":"Z.ai: GLM 4.6","context_length":202752,"pricing":{"prompt":"0.0000005","completion":"0.000002","input_cache_read":"0.0000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.94365475733127,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Novita | z-ai/glm-4.6","model_id":"z-ai/glm-4.6","model_name":"Z.ai: GLM 4.6","context_length":204800,"pricing":{"prompt":"0.00000055","completion":"0.0000022","input_cache_read":"0.00000011","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.6542750929368,"uptime_last_5m":96.15384615384616,"uptime_last_1d":95.96054628224583,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null},{"name":"AtlasCloud | z-ai/glm-4.6","model_id":"z-ai/glm-4.6","model_name":"Z.ai: GLM 4.6","context_length":202752,"pricing":{"prompt":"0.0000006","completion":"0.0000022","input_cache_read":"0.00000011","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":182476,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":98.47896288669443,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null},{"name":"Z.AI | z-ai/glm-4.6","model_id":"z-ai/glm-4.6","model_name":"Z.ai: GLM 4.6","context_length":202752,"pricing":{"prompt":"0.0000006","completion":"0.0000022","input_cache_read":"0.00000011","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp4","quantization":"fp4","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":93.53233830845771,"uptime_last_5m":81.81818181818183,"uptime_last_1d":96.22431570358282,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Venice","_cheapest_blended_per_m":8.26e-07,"_priciest_blended_per_m":1.08e-06,"_provider_spread_multiplier":1.3075060532687652},{"id":"deepseek/deepseek-v3.2-exp","canonical_slug":"deepseek/deepseek-v3.2-exp","hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Exp","name":"DeepSeek: DeepSeek V3.2 Exp","created":1759150481,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000027","completion":"0.00000041"},"top_provider":{"context_length":163840,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-07-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v3.2-exp/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1192,"win_rate":56.4,"rank":51},{"arena":"models","category":"codecategories","elo":1195,"win_rate":54.2,"rank":56},{"arena":"models","category":"dataviz","elo":1173,"win_rate":50.6,"rank":65},{"arena":"models","category":"gamedev","elo":1180,"win_rate":53,"rank":58},{"arena":"models","category":"svg","elo":1072,"win_rate":42,"rank":65},{"arena":"models","category":"uicomponent","elo":1193,"win_rate":53.3,"rank":55},{"arena":"models","category":"website","elo":1199,"win_rate":54.3,"rank":59}]},"reasoning":{"mandatory":false},"_prompt_per_m":2.7e-07,"_completion_per_m":4.1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | deepseek/deepseek-v3.2-exp","model_id":"deepseek/deepseek-v3.2-exp","model_name":"DeepSeek: DeepSeek V3.2 Exp","context_length":163840,"pricing":{"prompt":"0.00000027","completion":"0.00000041","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.69593310528316,"uptime_last_5m":100,"uptime_last_1d":99.65713484307184,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":4.1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-v3.2-exp","model_id":"deepseek/deepseek-v3.2-exp","model_name":"DeepSeek: DeepSeek V3.2 Exp","context_length":163840,"pricing":{"prompt":"0.00000027","completion":"0.00000041","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":94.53302961275627,"uptime_last_5m":96.7741935483871,"uptime_last_1d":90.16366668385855,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":4.1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"AtlasCloud | deepseek/deepseek-v3.2-exp","model_id":"deepseek/deepseek-v3.2-exp","model_name":"DeepSeek: DeepSeek V3.2 Exp","context_length":163840,"pricing":{"prompt":"0.00000027","completion":"0.00000041","input_cache_read":"0.00000027","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.00039086816162,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":4.1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.7e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":3.12e-07,"_priciest_blended_per_m":3.12e-07,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-sonnet-4.5:batch","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","hugging_face_id":"","name":"Anthropic: Claude Sonnet 4.5 (batch)","created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.0000075","web_search":"0.01","input_cache_read":"0.00000015","input_cache_write":"0.000001875","input_cache_write_1h":"0.000003","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000003","completion":"0.00001125","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1202,"win_rate":51,"rank":48},{"arena":"models","category":"asciiart","elo":1232,"win_rate":56.1,"rank":18},{"arena":"models","category":"codecategories","elo":1207,"win_rate":51.5,"rank":48},{"arena":"models","category":"dataviz","elo":1188,"win_rate":47.3,"rank":56},{"arena":"models","category":"gamedev","elo":1202,"win_rate":51.1,"rank":50},{"arena":"models","category":"svg","elo":1155,"win_rate":52.2,"rank":46},{"arena":"models","category":"uicomponent","elo":1199,"win_rate":49.4,"rank":52},{"arena":"models","category":"website","elo":1209,"win_rate":51.8,"rank":52},{"arena":"agents","category":"fullstack","elo":1074,"win_rate":43.7,"rank":33},{"arena":"agents","category":"mobileapps","elo":1177,"win_rate":52.9,"rank":26},{"arena":"agents","category":"webapps","elo":1091,"win_rate":43.2,"rank":32}],"artificial_analysis":{"intelligence_index":37.4,"coding_index":52.1,"agentic_index":26.4}},"reasoning":{"mandatory":false},"_prompt_per_m":1.5e-06,"_completion_per_m":7.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":1.875e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.5-sonnet-20250929:batch","model_id":"anthropic/claude-sonnet-4.5:batch","model_name":"Anthropic: Claude Sonnet 4.5","context_length":1000000,"pricing":{"prompt":"0.0000015","completion":"0.0000075","web_search":"0.01","input_cache_read":"0.00000015","input_cache_write":"0.000001875","input_cache_write_1h":"0.000003","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000003","completion":"0.00001125","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006"}]},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-06,"_completion_per_m":7.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":1.875e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":3.2999999999999997e-06,"_priciest_blended_per_m":3.2999999999999997e-06,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-sonnet-4.5","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","hugging_face_id":"","name":"Anthropic: Claude Sonnet 4.5","created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1202,"win_rate":51,"rank":48},{"arena":"models","category":"asciiart","elo":1232,"win_rate":56.1,"rank":18},{"arena":"models","category":"codecategories","elo":1207,"win_rate":51.5,"rank":48},{"arena":"models","category":"dataviz","elo":1188,"win_rate":47.3,"rank":56},{"arena":"models","category":"gamedev","elo":1202,"win_rate":51.1,"rank":50},{"arena":"models","category":"svg","elo":1155,"win_rate":52.2,"rank":46},{"arena":"models","category":"uicomponent","elo":1199,"win_rate":49.4,"rank":52},{"arena":"models","category":"website","elo":1209,"win_rate":51.8,"rank":52},{"arena":"agents","category":"fullstack","elo":1074,"win_rate":43.7,"rank":33},{"arena":"agents","category":"mobileapps","elo":1177,"win_rate":52.9,"rank":26},{"arena":"agents","category":"webapps","elo":1091,"win_rate":43.2,"rank":32}],"artificial_analysis":{"intelligence_index":37.4,"coding_index":52.1,"agentic_index":26.4}},"reasoning":{"mandatory":false},"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06,"_endpoints":[{"name":"Google | anthropic/claude-4.5-sonnet-20250929","model_id":"anthropic/claude-sonnet-4.5","model_name":"Anthropic: Claude Sonnet 4.5","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.92290196985468,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Azure | anthropic/claude-4.5-sonnet-20250929","model_id":"anthropic/claude-sonnet-4.5","model_name":"Anthropic: Claude Sonnet 4.5","context_length":200000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0},"provider_name":"Azure","tag":"azure/global","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","top_k","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.92207286187414,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Claude Platform on AWS | anthropic/claude-4.5-sonnet-20250929","model_id":"anthropic/claude-sonnet-4.5","model_name":"Anthropic: Claude Sonnet 4.5","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"provider_name":"Claude Platform on AWS","tag":"claude-on-aws","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","top_k","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.76851851851852,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Amazon Bedrock | anthropic/claude-4.5-sonnet-20250929","model_id":"anthropic/claude-sonnet-4.5","model_name":"Anthropic: Claude Sonnet 4.5","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.74816983894583,"uptime_last_5m":99.93136582017846,"uptime_last_1d":99.88550084652576,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Anthropic | anthropic/claude-4.5-sonnet-20250929","model_id":"anthropic/claude-sonnet-4.5","model_name":"Anthropic: Claude Sonnet 4.5","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.81651376146789,"uptime_last_5m":100,"uptime_last_1d":99.45272537264177,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Amazon Bedrock | anthropic/claude-4.5-sonnet-20250929","model_id":"anthropic/claude-sonnet-4.5","model_name":"Anthropic: Claude Sonnet 4.5","context_length":1000000,"pricing":{"prompt":"0.0000033","completion":"0.0000165","web_search":"0.01","input_cache_read":"0.00000033","input_cache_write":"0.000004125","input_cache_write_1h":"0.0000066","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000066","completion":"0.00002475","input_cache_read":"0.00000066","input_cache_write":"0.00000825","input_cache_write_1h":"0.0000132"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-07,"_cached_write_per_m":4.125e-06},{"name":"Google | anthropic/claude-4.5-sonnet-20250929","model_id":"anthropic/claude-sonnet-4.5","model_name":"Anthropic: Claude Sonnet 4.5","context_length":1000000,"pricing":{"prompt":"0.0000033","completion":"0.0000165","web_search":"0.01","input_cache_read":"0.00000033","input_cache_write":"0.000004125","input_cache_write_1h":"0.0000066","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000066","completion":"0.00002475","input_cache_read":"0.00000066","input_cache_write":"0.00000825","input_cache_write_1h":"0.0000132"}]},"provider_name":"Google","tag":"google-vertex/us-east5","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-06,"_completion_per_m":1.65e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-07,"_cached_write_per_m":4.125e-06}],"_cheapest_provider":"Google","_cheapest_blended_per_m":6.5999999999999995e-06,"_priciest_blended_per_m":7.26e-06,"_provider_spread_multiplier":1.1},{"id":"thedrummer/cydonia-24b-v4.1","canonical_slug":"thedrummer/cydonia-24b-v4.1","hugging_face_id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","created":1758931878,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000005","input_cache_read":"0.00000015"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-04-30","expiration_date":null,"links":{"details":"/api/v1/models/thedrummer/cydonia-24b-v4.1/endpoints"},"_prompt_per_m":3e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Parasail | thedrummer/cydonia-24b-v4.1","model_id":"thedrummer/cydonia-24b-v4.1","model_name":"TheDrummer: Cydonia 24B V4.1","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.0000005","input_cache_read":"0.00000015","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8798076923077,"uptime_last_5m":99.66216216216216,"uptime_last_1d":99.99052491946182,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Parasail","_cheapest_blended_per_m":3.5999999999999994e-07,"_priciest_blended_per_m":3.5999999999999994e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5-pro","canonical_slug":"openai/gpt-5-pro-2025-10-06","hugging_face_id":"","name":"OpenAI: GPT-5 Pro","created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0.00012","web_search":"0.01"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["high"],"default_effort":"high"},"_prompt_per_m":1.5e-05,"_completion_per_m":0.00012,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5-pro-2025-10-06","model_id":"openai/gpt-5-pro","model_name":"OpenAI: GPT-5 Pro","context_length":400000,"pricing":{"prompt":"0.000015","completion":"0.00012","web_search":"0.01","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-05,"_completion_per_m":0.00012,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":4.65e-05,"_priciest_blended_per_m":4.65e-05,"_provider_spread_multiplier":1.0},{"id":"relace/relace-apply-3","canonical_slug":"relace/relace-apply-3","hugging_face_id":"","name":"Relace: Relace Apply 3","created":1758891572,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000085","completion":"0.00000125"},"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","seed","stop"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/relace/relace-apply-3/endpoints"},"_prompt_per_m":8.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Relace | relace/relace-apply-3","model_id":"relace/relace-apply-3","model_name":"Relace: Relace Apply 3","context_length":256000,"pricing":{"prompt":"0.00000085","completion":"0.00000125","discount":0},"provider_name":"Relace","tag":"relace/fp8","quantization":"fp8","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["stop","seed","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Relace","_cheapest_blended_per_m":9.7e-07,"_priciest_blended_per_m":9.7e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-vl-235b-a22b-instruct","canonical_slug":"qwen/qwen3-vl-235b-a22b-instruct","hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","created":1758668687,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000021","completion":"0.0000019","input_cache_read":"0.0000001"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.7,"top_p":0.8,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-235b-a22b-instruct/endpoints"},"_prompt_per_m":2.1e-07,"_completion_per_m":1.9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | qwen/qwen3-vl-235b-a22b-instruct","model_id":"qwen/qwen3-vl-235b-a22b-instruct","model_name":"Qwen: Qwen3 VL 235B A22B Instruct","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.00000088","input_cache_read":"0.00000011","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":98.1549815498155,"uptime_last_5m":100,"uptime_last_1d":95.62613177322747,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":8.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3-vl-235b-a22b-instruct","model_id":"qwen/qwen3-vl-235b-a22b-instruct","model_name":"Qwen: Qwen3 VL 235B A22B Instruct","context_length":128000,"pricing":{"prompt":"0.00000021","completion":"0.0000019","input_cache_read":"0.0000001","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.16951915240423,"uptime_last_5m":93.18181818181817,"uptime_last_1d":96.74292900588897,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-07,"_completion_per_m":1.9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen3-vl-235b-a22b-instruct","model_id":"qwen/qwen3-vl-235b-a22b-instruct","model_name":"Qwen: Qwen3 VL 235B A22B Instruct","context_length":131072,"pricing":{"prompt":"0.00000021","completion":"0.0000019","input_cache_read":"0.0000001","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.99497487437185,"uptime_last_5m":99.6319018404908,"uptime_last_1d":99.04139395283377,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-07,"_completion_per_m":1.9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3-vl-235b-a22b-instruct","model_id":"qwen/qwen3-vl-235b-a22b-instruct","model_name":"Qwen: Qwen3 VL 235B A22B Instruct","context_length":131072,"pricing":{"prompt":"0.00000026","completion":"0.00000104","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":129024,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.68208484916589,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-07,"_completion_per_m":1.04e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3-vl-235b-a22b-instruct","model_id":"qwen/qwen3-vl-235b-a22b-instruct","model_name":"Qwen: Qwen3 VL 235B A22B Instruct","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.0000015","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.4059405940594,"uptime_last_5m":100,"uptime_last_1d":98.41722235053047,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":4.0399999999999996e-07,"_priciest_blended_per_m":7.169999999999999e-07,"_provider_spread_multiplier":1.7747524752475246},{"id":"qwen/qwen3-vl-235b-a22b-thinking","canonical_slug":"qwen/qwen3-vl-235b-a22b-thinking","hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","name":"Qwen: Qwen3 VL 235B A22B Thinking","created":1758668690,"description":"Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.000004"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.8,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-235b-a22b-thinking/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":4e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-vl-235b-a22b-thinking","model_id":"qwen/qwen3-vl-235b-a22b-thinking","model_name":"Qwen: Qwen3 VL 235B A22B Thinking","context_length":131072,"pricing":{"prompt":"0.0000004","completion":"0.000004","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":126976,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":-2,"uptime_last_30m":87.66519823788546,"uptime_last_5m":null,"uptime_last_1d":88.43120070113936,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3-vl-235b-a22b-thinking","model_id":"qwen/qwen3-vl-235b-a22b-thinking","model_name":"Qwen: Qwen3 VL 235B A22B Thinking","context_length":131072,"pricing":{"prompt":"0.00000098","completion":"0.00000395","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.63617463617463,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.8e-07,"_completion_per_m":3.95e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":1.4799999999999998e-06,"_priciest_blended_per_m":1.871e-06,"_provider_spread_multiplier":1.2641891891891894},{"id":"qwen/qwen3-max","canonical_slug":"qwen/qwen3-max","hugging_face_id":"","name":"Qwen: Qwen3 Max","created":1758662808,"description":"Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000078","completion":"0.0000039","input_cache_read":"0.000000156","input_cache_write":"0.000000975","overrides":[{"min_prompt_tokens":32000,"prompt":"0.00000156","completion":"0.0000078","input_cache_read":"0.000000312","input_cache_write":"0.00000195"},{"min_prompt_tokens":128000,"prompt":"0.00000195","completion":"0.00000975","input_cache_read":"0.00000039","input_cache_write":"0.0000024375"}]},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":1,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-max/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1118,"win_rate":43.5,"rank":82},{"arena":"models","category":"asciiart","elo":1154,"win_rate":47.2,"rank":44},{"arena":"models","category":"codecategories","elo":1134,"win_rate":44,"rank":84},{"arena":"models","category":"dataviz","elo":1121,"win_rate":41.2,"rank":82},{"arena":"models","category":"gamedev","elo":1130,"win_rate":43.9,"rank":80},{"arena":"models","category":"svg","elo":1051,"win_rate":37.3,"rank":70},{"arena":"models","category":"uicomponent","elo":1104,"win_rate":40.2,"rank":85},{"arena":"models","category":"website","elo":1139,"win_rate":44.5,"rank":85}]},"reasoning":{"mandatory":false},"_prompt_per_m":7.8e-07,"_completion_per_m":3.9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.56e-07,"_cached_write_per_m":9.75e-07,"_endpoints":[{"name":"Alibaba | qwen/qwen3-max","model_id":"qwen/qwen3-max","model_name":"Qwen: Qwen3 Max","context_length":262144,"pricing":{"prompt":"0.00000078","completion":"0.0000039","input_cache_read":"0.000000156","input_cache_write":"0.000000975","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.00000156","completion":"0.0000078","input_cache_read":"0.000000312","input_cache_write":"0.00000195"},{"min_prompt_tokens":128000,"prompt":"0.00000195","completion":"0.00000975","input_cache_read":"0.00000039","input_cache_write":"0.0000024375"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":258048,"supported_parameters":["response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.8e-07,"_completion_per_m":3.9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.56e-07,"_cached_write_per_m":9.75e-07}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":1.7160000000000002e-06,"_priciest_blended_per_m":1.7160000000000002e-06,"_provider_spread_multiplier":1.0},{"id":"kwaipilot/kat-coder-pro-v2","canonical_slug":"kwaipilot/kat-coder-pro-v2-20260327","hugging_face_id":"","name":"Kwaipilot: KAT-Coder-Pro V2","created":1774649310,"description":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006"},"top_provider":{"context_length":256000,"max_completion_tokens":80000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/kwaipilot/kat-coder-pro-v2-20260327/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":33.7,"coding_index":59.5,"agentic_index":15.1}},"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"StreamLake | kwaipilot/kat-coder-pro-v2-20260327","model_id":"kwaipilot/kat-coder-pro-v2","model_name":"Kwaipilot: KAT-Coder-Pro V2","context_length":256000,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":80000,"max_prompt_tokens":null,"supported_parameters":["tool_choice","tools","max_tokens","temperature","top_p","stop","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96909082880735,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null},{"name":"AtlasCloud | kwaipilot/kat-coder-pro-v2-20260327","model_id":"kwaipilot/kat-coder-pro-v2","model_name":"Kwaipilot: KAT-Coder-Pro V2","context_length":262144,"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":144000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.66777408637874,"uptime_last_5m":100,"uptime_last_1d":99.9076425767721,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":6e-08,"_cached_write_per_m":null}],"_cheapest_provider":"StreamLake","_cheapest_blended_per_m":5.699999999999999e-07,"_priciest_blended_per_m":5.699999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"deepseek/deepseek-v3.1-terminus","canonical_slug":"deepseek/deepseek-v3.1-terminus","hugging_face_id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","created":1758548275,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000027","completion":"0.000001","input_cache_read":"0.000000135"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v3.1-terminus/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1184,"win_rate":56,"rank":53},{"arena":"models","category":"codecategories","elo":1200,"win_rate":56,"rank":54},{"arena":"models","category":"dataviz","elo":1188,"win_rate":53.4,"rank":57},{"arena":"models","category":"gamedev","elo":1167,"win_rate":52.5,"rank":65},{"arena":"models","category":"svg","elo":1105,"win_rate":50.1,"rank":58},{"arena":"models","category":"uicomponent","elo":1209,"win_rate":59.5,"rank":46},{"arena":"models","category":"website","elo":1206,"win_rate":56.4,"rank":56}],"artificial_analysis":{"intelligence_index":31.4,"coding_index":43.5,"agentic_index":19.9}},"reasoning":{"mandatory":false},"_prompt_per_m":2.7e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | deepseek/deepseek-v3.1-terminus","model_id":"deepseek/deepseek-v3.1-terminus","model_name":"DeepSeek: DeepSeek V3.1 Terminus","context_length":131072,"pricing":{"prompt":"0.00000027","completion":"0.000001","input_cache_read":"0.000000135","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.80330373340972,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-v3.1-terminus","model_id":"deepseek/deepseek-v3.1-terminus","model_name":"DeepSeek: DeepSeek V3.1 Terminus","context_length":163840,"pricing":{"prompt":"0.00000027","completion":"0.000001","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.42147117296223,"uptime_last_5m":100,"uptime_last_1d":98.11525580321053,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"AtlasCloud | deepseek/deepseek-v3.1-terminus","model_id":"deepseek/deepseek-v3.1-terminus","model_name":"DeepSeek: DeepSeek V3.1 Terminus","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.00000095","input_cache_read":"0.00000013","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.24193548387098,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":9.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null},{"name":"StreamLake | deepseek/deepseek-v3.1-terminus","model_id":"deepseek/deepseek-v3.1-terminus","model_name":"DeepSeek: DeepSeek V3.1 Terminus","context_length":128000,"pricing":{"prompt":"0.0000003426","completion":"0.0000010284","discount":0.4},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.78978102189781,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.426e-07,"_completion_per_m":1.0284e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":4.89e-07,"_priciest_blended_per_m":5.483399999999999e-07,"_provider_spread_multiplier":1.1213496932515337},{"id":"qwen/qwen3-coder-plus","canonical_slug":"qwen/qwen3-coder-plus","hugging_face_id":"","name":"Qwen: Qwen3 Coder Plus","created":1758662707,"description":"Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000065","completion":"0.00000325","input_cache_read":"0.00000013","input_cache_write":"0.0000008125","overrides":[{"min_prompt_tokens":32000,"prompt":"0.00000117","completion":"0.00000585","input_cache_read":"0.000000234","input_cache_write":"0.0000014625"},{"min_prompt_tokens":128000,"prompt":"0.00000195","completion":"0.00000975","input_cache_read":"0.00000039","input_cache_write":"0.0000024375"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-plus/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":6.5e-07,"_completion_per_m":3.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":8.125e-07,"_endpoints":[{"name":"Alibaba | qwen/qwen3-coder-plus","model_id":"qwen/qwen3-coder-plus","model_name":"Qwen: Qwen3 Coder Plus","context_length":1000000,"pricing":{"prompt":"0.00000065","completion":"0.00000325","input_cache_read":"0.00000013","input_cache_write":"0.0000008125","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.00000117","completion":"0.00000585","input_cache_read":"0.000000234","input_cache_write":"0.0000014625"},{"min_prompt_tokens":128000,"prompt":"0.00000195","completion":"0.00000975","input_cache_read":"0.00000039","input_cache_write":"0.0000024375"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":997952,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.5e-07,"_completion_per_m":3.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":8.125e-07}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":1.4299999999999999e-06,"_priciest_blended_per_m":1.4299999999999999e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-coder-flash","canonical_slug":"qwen/qwen3-coder-flash","hugging_face_id":"","name":"Qwen: Qwen3 Coder Flash","created":1758115536,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.000000195","completion":"0.000000975","input_cache_read":"0.000000039","input_cache_write":"0.00000024375","overrides":[{"min_prompt_tokens":32000,"prompt":"0.000000325","completion":"0.000001625","input_cache_read":"0.000000065","input_cache_write":"0.00000040625"},{"min_prompt_tokens":128000,"prompt":"0.00000052","completion":"0.0000026","input_cache_read":"0.000000104","input_cache_write":"0.00000065"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-flash/endpoints"},"_prompt_per_m":1.95e-07,"_completion_per_m":9.75e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.9e-08,"_cached_write_per_m":2.4375e-07,"_endpoints":[{"name":"Alibaba | qwen/qwen3-coder-flash","model_id":"qwen/qwen3-coder-flash","model_name":"Qwen: Qwen3 Coder Flash","context_length":1000000,"pricing":{"prompt":"0.000000195","completion":"0.000000975","input_cache_read":"0.000000039","input_cache_write":"0.00000024375","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.000000325","completion":"0.000001625","input_cache_read":"0.000000065","input_cache_write":"0.00000040625"},{"min_prompt_tokens":128000,"prompt":"0.00000052","completion":"0.0000026","input_cache_read":"0.000000104","input_cache_write":"0.00000065"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":997952,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.95e-07,"_completion_per_m":9.75e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.9e-08,"_cached_write_per_m":2.4375e-07}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":4.2900000000000004e-07,"_priciest_blended_per_m":4.2900000000000004e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-next-80b-a3b-thinking","canonical_slug":"qwen/qwen3-next-80b-a3b-thinking-2509","hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","created":1757612284,"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000012"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-09-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-next-80b-a3b-thinking-2509/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":16.9,"coding_index":17.4,"agentic_index":2.1}},"reasoning":{"mandatory":true},"_prompt_per_m":1.5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-next-80b-a3b-thinking-2509","model_id":"qwen/qwen3-next-80b-a3b-thinking","model_name":"Qwen: Qwen3 Next 80B A3B Thinking","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000012","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":126976,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.93211133740665,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google | qwen/qwen3-next-80b-a3b-thinking-2509","model_id":"qwen/qwen3-next-80b-a3b-thinking","model_name":"Qwen: Qwen3 Next 80B A3B Thinking","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000012","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":4.65e-07,"_priciest_blended_per_m":4.65e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-next-80b-a3b-instruct","canonical_slug":"qwen/qwen3-next-80b-a3b-instruct-2509","hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","created":1757612213,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000011","input_cache_read":"0.00000007"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-09-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-next-80b-a3b-instruct-2509/endpoints"},"_prompt_per_m":1e-07,"_completion_per_m":1.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | qwen/qwen3-next-80b-a3b-instruct-2509","model_id":"qwen/qwen3-next-80b-a3b-instruct","model_name":"Qwen: Qwen3 Next 80B A3B Instruct","context_length":262144,"pricing":{"prompt":"0.00000009","completion":"0.0000011","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.90632318501171,"uptime_last_5m":100,"uptime_last_1d":99.84888135343334,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":1.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3-next-80b-a3b-instruct-2509","model_id":"qwen/qwen3-next-80b-a3b-instruct","model_name":"Qwen: Qwen3 Next 80B A3B Instruct","context_length":131072,"pricing":{"prompt":"0.0000000975","completion":"0.00000078","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":129024,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9916553086145,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.75e-08,"_completion_per_m":7.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen3-next-80b-a3b-instruct-2509","model_id":"qwen/qwen3-next-80b-a3b-instruct","model_name":"Qwen: Qwen3 Next 80B A3B Instruct","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.0000011","input_cache_read":"0.00000007","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97686215181987,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":1.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7e-08,"_cached_write_per_m":null},{"name":"Google | qwen/qwen3-next-80b-a3b-instruct-2509","model_id":"qwen/qwen3-next-80b-a3b-instruct","model_name":"Qwen: Qwen3 Next 80B A3B Instruct","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000012","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.96579247434435,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3-next-80b-a3b-instruct-2509","model_id":"qwen/qwen3-next-80b-a3b-instruct","model_name":"Qwen: Qwen3 Next 80B A3B Instruct","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000015","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.2248062015504,"uptime_last_5m":null,"uptime_last_1d":99.31208053691275,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":3.0225e-07,"_priciest_blended_per_m":5.55e-07,"_provider_spread_multiplier":1.836228287841191},{"id":"qwen/qwen-plus-2025-07-28","canonical_slug":"qwen/qwen-plus-2025-07-28","hugging_face_id":"","name":"Qwen: Qwen Plus 0728","created":1757347599,"description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000026","completion":"0.00000078","overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000078","completion":"0.00000234"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":2.6e-07,"_completion_per_m":7.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen-plus-2025-07-28","model_id":"qwen/qwen-plus-2025-07-28","model_name":"Qwen: Qwen Plus 0728","context_length":1000000,"pricing":{"prompt":"0.00000026","completion":"0.00000078","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000078","completion":"0.00000234"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":995904,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-07,"_completion_per_m":7.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":4.16e-07,"_priciest_blended_per_m":4.16e-07,"_provider_spread_multiplier":1.0},{"id":"moonshotai/kimi-k2-0905","canonical_slug":"moonshotai/kimi-k2-0905","hugging_face_id":"moonshotai/Kimi-K2-Instruct-0905","name":"MoonshotAI: Kimi K2 0905","created":1757021147,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000025"},"top_provider":{"context_length":262144,"max_completion_tokens":100352,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-12-31","expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2-0905/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1122,"win_rate":48.5,"rank":87},{"arena":"models","category":"website","elo":1127,"win_rate":48.3,"rank":89}]},"_prompt_per_m":6e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | moonshotai/kimi-k2-0905","model_id":"moonshotai/kimi-k2-0905","model_name":"MoonshotAI: Kimi K2 0905","context_length":262144,"pricing":{"prompt":"0.0000006","completion":"0.0000025","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":100352,"max_prompt_tokens":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99830074155639,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":1.17e-06,"_priciest_blended_per_m":1.17e-06,"_provider_spread_multiplier":1.0},{"id":"nousresearch/hermes-4-70b","canonical_slug":"nousresearch/hermes-4-70b","hugging_face_id":"NousResearch/Hermes-4-70B","name":"Nous: Hermes 4 70B","created":1756236182,"description":"Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":null},"pricing":{"prompt":"0.00000013","completion":"0.0000004"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/nousresearch/hermes-4-70b/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1.3e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Nebius | nousresearch/hermes-4-70b","model_id":"nousresearch/hermes-4-70b","model_name":"Nous: Hermes 4 70B","context_length":131072,"pricing":{"prompt":"0.00000013","completion":"0.0000004","discount":0},"provider_name":"Nebius","tag":"nebius/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","top_k","repetition_penalty","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99930360177164,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Nebius","_cheapest_blended_per_m":2.1099999999999997e-07,"_priciest_blended_per_m":2.1099999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-30b-a3b-thinking-2507","canonical_slug":"qwen/qwen3-30b-a3b-thinking-2507","hugging_face_id":"Qwen/Qwen3-30B-A3B-Thinking-2507","name":"Qwen: Qwen3 30B A3B Thinking 2507","created":1756399192,"description":"Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...","context_length":81920,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000024"},"top_provider":{"context_length":81920,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-30b-a3b-thinking-2507/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"dataviz","elo":945,"win_rate":33.3,"rank":110},{"arena":"models","category":"website","elo":950,"win_rate":35.5,"rank":118}],"artificial_analysis":{"intelligence_index":14.6,"coding_index":12.1,"agentic_index":1.8}},"reasoning":{"mandatory":true},"_prompt_per_m":2e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-30b-a3b-thinking-2507","model_id":"qwen/qwen3-30b-a3b-thinking-2507","model_name":"Qwen: Qwen3 30B A3B Thinking 2507","context_length":81920,"pricing":{"prompt":"0.0000002","completion":"0.0000024","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":126976,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":2.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":8.6e-07,"_priciest_blended_per_m":8.6e-07,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-medium-3.1:batch","canonical_slug":"mistralai/mistral-medium-3.1","hugging_face_id":"","name":"Mistral: Mistral Medium 3.1 (batch)","created":1755095639,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004"},"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-medium-3.1/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1125,"win_rate":44.6,"rank":78},{"arena":"models","category":"asciiart","elo":1024,"win_rate":30.8,"rank":60},{"arena":"models","category":"codecategories","elo":1145,"win_rate":45.1,"rank":78},{"arena":"models","category":"dataviz","elo":1165,"win_rate":47.2,"rank":67},{"arena":"models","category":"gamedev","elo":1110,"win_rate":40.7,"rank":86},{"arena":"models","category":"svg","elo":1032,"win_rate":38.2,"rank":74},{"arena":"models","category":"uicomponent","elo":1126,"win_rate":43.6,"rank":79},{"arena":"models","category":"website","elo":1152,"win_rate":46,"rank":78}],"artificial_analysis":{"intelligence_index":14.7,"coding_index":20.5,"agentic_index":6.1}},"_prompt_per_m":4e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-medium-3.1:batch","model_id":"mistralai/mistral-medium-3.1:batch","model_name":"Mistral: Mistral Medium 3.1","context_length":131072,"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":8.799999999999999e-07,"_priciest_blended_per_m":8.799999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-medium-3.1","canonical_slug":"mistralai/mistral-medium-3.1","hugging_face_id":"","name":"Mistral: Mistral Medium 3.1","created":1755095639,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004"},"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-medium-3.1/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1125,"win_rate":44.6,"rank":78},{"arena":"models","category":"asciiart","elo":1024,"win_rate":30.8,"rank":60},{"arena":"models","category":"codecategories","elo":1145,"win_rate":45.1,"rank":78},{"arena":"models","category":"dataviz","elo":1165,"win_rate":47.2,"rank":67},{"arena":"models","category":"gamedev","elo":1110,"win_rate":40.7,"rank":86},{"arena":"models","category":"svg","elo":1032,"win_rate":38.2,"rank":74},{"arena":"models","category":"uicomponent","elo":1126,"win_rate":43.6,"rank":79},{"arena":"models","category":"website","elo":1152,"win_rate":46,"rank":78}],"artificial_analysis":{"intelligence_index":14.7,"coding_index":20.5,"agentic_index":6.1}},"_prompt_per_m":4e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-medium-3.1","model_id":"mistralai/mistral-medium-3.1","model_name":"Mistral: Mistral Medium 3.1","context_length":131072,"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.14409108755399,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-medium-3.1","model_id":"mistralai/mistral-medium-3.1","model_name":"Mistral: Mistral Medium 3.1","context_length":131072,"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.31739443625013,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-medium-3.1","model_id":"mistralai/mistral-medium-3.1","model_name":"Mistral: Mistral Medium 3.1","context_length":131072,"pricing":{"prompt":"0.00000044","completion":"0.0000022","input_cache_read":"0.000000044","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":8.799999999999999e-07,"_priciest_blended_per_m":9.68e-07,"_provider_spread_multiplier":1.1},{"id":"nousresearch/hermes-4-405b","canonical_slug":"nousresearch/hermes-4-405b","hugging_face_id":"NousResearch/Hermes-4-405B","name":"Nous: Hermes 4 405B","created":1756235463,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000003"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/nousresearch/hermes-4-405b/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1e-06,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Nebius | nousresearch/hermes-4-405b","model_id":"nousresearch/hermes-4-405b","model_name":"Nous: Hermes 4 405B","context_length":131072,"pricing":{"prompt":"0.000001","completion":"0.000003","discount":0},"provider_name":"Nebius","tag":"nebius/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","top_k","repetition_penalty","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Nebius","_cheapest_blended_per_m":1.6e-06,"_priciest_blended_per_m":1.6e-06,"_provider_spread_multiplier":1.0},{"id":"deepseek/deepseek-chat-v3.1","canonical_slug":"deepseek/deepseek-chat-v3.1","hugging_face_id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek: DeepSeek V3.1","created":1755779628,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000055","completion":"0.00000165","input_cache_read":"0.00000055"},"top_provider":{"context_length":161000,"max_completion_tokens":144900,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-chat-v3.1/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1121,"win_rate":47.9,"rank":81},{"arena":"models","category":"codecategories","elo":1136,"win_rate":47.8,"rank":83},{"arena":"models","category":"dataviz","elo":1116,"win_rate":46.2,"rank":86},{"arena":"models","category":"gamedev","elo":1120,"win_rate":47.1,"rank":82},{"arena":"models","category":"svg","elo":1007,"win_rate":38.2,"rank":79},{"arena":"models","category":"uicomponent","elo":1111,"win_rate":47.1,"rank":82},{"arena":"models","category":"website","elo":1142,"win_rate":48,"rank":83}]},"reasoning":{"mandatory":false},"_prompt_per_m":5.5e-07,"_completion_per_m":1.65e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | deepseek/deepseek-chat-v3.1","model_id":"deepseek/deepseek-chat-v3.1","model_name":"DeepSeek: DeepSeek V3.1","context_length":163840,"pricing":{"prompt":"0.00000025","completion":"0.00000095","input_cache_read":"0.00000013","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98505678421996,"uptime_last_5m":100,"uptime_last_1d":99.90826569477889,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":9.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-chat-v3.1","model_id":"deepseek/deepseek-chat-v3.1","model_name":"DeepSeek: DeepSeek V3.1","context_length":163840,"pricing":{"prompt":"0.00000027","completion":"0.000001","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":false,"auto":false,"required":false,"function":true},"status":0,"uptime_last_30m":96.54545454545455,"uptime_last_5m":99.3421052631579,"uptime_last_1d":97.86264340719785,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | deepseek/deepseek-chat-v3.1","model_id":"deepseek/deepseek-chat-v3.1","model_name":"DeepSeek: DeepSeek V3.1","context_length":131072,"pricing":{"prompt":"0.00000027","completion":"0.000001","input_cache_read":"0.000000135","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.73581582589006,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":null},{"name":"AtlasCloud | deepseek/deepseek-chat-v3.1","model_id":"deepseek/deepseek-chat-v3.1","model_name":"DeepSeek: DeepSeek V3.1","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.00000095","input_cache_read":"0.00000013","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.92429977289932,"uptime_last_5m":100,"uptime_last_1d":99.7740832400571,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":9.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null},{"name":"CoreWeave | deepseek/deepseek-chat-v3.1","model_id":"deepseek/deepseek-chat-v3.1","model_name":"DeepSeek: DeepSeek V3.1","context_length":161000,"pricing":{"prompt":"0.00000055","completion":"0.00000165","input_cache_read":"0.00000055","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp8","quantization":"fp8","max_completion_tokens":144900,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98517997073044,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-07,"_completion_per_m":1.65e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null},{"name":"Mara | deepseek/deepseek-chat-v3.1","model_id":"deepseek/deepseek-chat-v3.1","model_name":"DeepSeek: DeepSeek V3.1","context_length":131072,"pricing":{"prompt":"0.0000006","completion":"0.0000017","discount":0},"provider_name":"Mara","tag":"mara","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_k","top_p","response_format","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":95.78030810448762,"uptime_last_5m":100,"uptime_last_1d":95.94517133956386,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":1.7e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google | deepseek/deepseek-chat-v3.1","model_id":"deepseek/deepseek-chat-v3.1","model_name":"DeepSeek: DeepSeek V3.1","context_length":163840,"pricing":{"prompt":"0.0000006","completion":"0.0000017","discount":0},"provider_name":"Google","tag":"google-vertex/us-west2","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":96.89404197698036,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":1.7e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SambaNova | deepseek/deepseek-chat-v3.1","model_id":"deepseek/deepseek-chat-v3.1","model_name":"DeepSeek: DeepSeek V3.1","context_length":131072,"pricing":{"prompt":"0.00000065","completion":"0.0000015","discount":0},"provider_name":"SambaNova","tag":"sambanova/fp8","quantization":"fp8","max_completion_tokens":7168,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.55072463768117,"uptime_last_5m":null,"uptime_last_1d":99.08163538515088,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":4.5999999999999994e-07,"_priciest_blended_per_m":9.3e-07,"_provider_spread_multiplier":2.0217391304347827},{"id":"z-ai/glm-4.5v","canonical_slug":"z-ai/glm-4.5v","hugging_face_id":"zai-org/GLM-4.5V","name":"Z.ai: GLM 4.5V","created":1754922288,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","context_length":65536,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000018","input_cache_read":"0.00000011"},"top_provider":{"context_length":65536,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.75,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-12-31","expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.5v/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":6e-07,"_completion_per_m":1.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | z-ai/glm-4.5v","model_id":"z-ai/glm-4.5v","model_name":"Z.ai: GLM 4.5V","context_length":65536,"pricing":{"prompt":"0.0000006","completion":"0.0000018","input_cache_read":"0.00000011","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":97.86960985626283,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":1.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null},{"name":"Z.AI | z-ai/glm-4.5v","model_id":"z-ai/glm-4.5v","model_name":"Z.ai: GLM 4.5V","context_length":65536,"pricing":{"prompt":"0.0000006","completion":"0.0000018","input_cache_read":"0.00000011","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":98.0721251984577,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":1.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":9.6e-07,"_priciest_blended_per_m":9.6e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-5","canonical_slug":"openai/gpt-5-2025-08-07","hugging_face_id":"","name":"OpenAI: GPT-5","created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.000000125"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5-2025-08-07/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1100,"win_rate":41.3,"rank":87},{"arena":"models","category":"asciiart","elo":1167,"win_rate":49,"rank":37},{"arena":"models","category":"codecategories","elo":1192,"win_rate":54.5,"rank":59},{"arena":"models","category":"dataviz","elo":1242,"win_rate":60.5,"rank":35},{"arena":"models","category":"gamedev","elo":1221,"win_rate":59.3,"rank":43},{"arena":"models","category":"svg","elo":1229,"win_rate":64.1,"rank":21},{"arena":"models","category":"uicomponent","elo":1206,"win_rate":57.4,"rank":48},{"arena":"models","category":"website","elo":1204,"win_rate":53.7,"rank":57}],"artificial_analysis":{"intelligence_index":35.3,"coding_index":37.8,"agentic_index":26.5}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5-2025-08-07","model_id":"openai/gpt-5","model_name":"OpenAI: GPT-5","context_length":400000,"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.000000125","discount":0},"provider_name":"OpenAI","tag":"openai/default","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.75598935226265,"uptime_last_5m":99.2603550295858,"uptime_last_1d":99.53081189209236,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5-2025-08-07","model_id":"openai/gpt-5","model_name":"OpenAI: GPT-5","context_length":400000,"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.000000125","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5-2025-08-07","model_id":"openai/gpt-5","model_name":"OpenAI: GPT-5","context_length":400000,"pricing":{"prompt":"0.000001375","completion":"0.000011","web_search":"0.01","input_cache_read":"0.0000001375","discount":0},"provider_name":"Azure","tag":"azure/swedencentral","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.375e-06,"_completion_per_m":1.1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.375e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":3.875e-06,"_priciest_blended_per_m":4.262499999999999e-06,"_provider_spread_multiplier":1.0999999999999999},{"id":"openai/gpt-oss-120b","canonical_slug":"openai/gpt-oss-120b","hugging_face_id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000000037","completion":"0.00000017"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-oss-120b/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":945,"win_rate":29.4,"rank":105},{"arena":"models","category":"codecategories","elo":987,"win_rate":33.4,"rank":112},{"arena":"models","category":"dataviz","elo":1007,"win_rate":43.6,"rank":103},{"arena":"models","category":"gamedev","elo":1028,"win_rate":40.5,"rank":102},{"arena":"models","category":"uicomponent","elo":953,"win_rate":35.7,"rank":107},{"arena":"models","category":"website","elo":987,"win_rate":32.5,"rank":114}],"artificial_analysis":{"intelligence_index":24.1,"coding_index":30.4,"agentic_index":13.4}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":3.7e-08,"_completion_per_m":1.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"AkashML | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000003","completion":"0.00000017","input_cache_read":"0.00000003","discount":0},"provider_name":"AkashML","tag":"akashml/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","seed","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.68207945470267,"uptime_last_5m":99.24054812613505,"uptime_last_1d":98.96058150077965,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":1.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"CoreWeave | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000003","completion":"0.00000017","input_cache_read":"0.00000003","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp4","quantization":"fp4","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.93532234508659,"uptime_last_5m":99.75651675737612,"uptime_last_1d":99.87580622652851,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":1.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"DeepInfra | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.000000037","completion":"0.00000017","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.07474568774879,"uptime_last_5m":99.76607304557803,"uptime_last_1d":99.31957807348456,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.7e-08,"_completion_per_m":1.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000005","completion":"0.00000025","discount":0},"provider_name":"Novita","tag":"novita/fp4","quantization":"fp4","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":27.739086121963645,"uptime_last_5m":39.473684210526315,"uptime_last_1d":92.41372907994958,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000005","completion":"0.00000045","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","max_tokens","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":62.20451289398281,"uptime_last_5m":10.189418680600914,"uptime_last_1d":61.92621349949425,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":4.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Mancer 2 | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.000000085","completion":"0.0000005","discount":0},"provider_name":"Mancer 2","tag":"mancer/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","response_format","logprobs","top_logprobs","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.88026819923371,"uptime_last_5m":100,"uptime_last_1d":99.55132652534647,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.5e-08,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000009","completion":"0.00000036","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","repetition_penalty","top_k","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":81.30423349986853,"uptime_last_5m":77.59146341463415,"uptime_last_1d":88.14444890405947,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":3.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"BaseTen | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":128072,"pricing":{"prompt":"0.0000001","completion":"0.0000005","input_cache_read":"0.0000001","discount":0},"provider_name":"BaseTen","tag":"baseten/fp4","quantization":"fp4","max_completion_tokens":115264,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99445934626804,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"DigitalOcean | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":128000,"pricing":{"prompt":"0.0000001","completion":"0.0000007","input_cache_read":"0.00000002","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":115200,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.93192648059905,"uptime_last_5m":100,"uptime_last_1d":99.87095190705469,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null},{"name":"Parasail | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.0000001","completion":"0.00000075","input_cache_read":"0.000000055","discount":0},"provider_name":"Parasail","tag":"parasail/fp4","quantization":"fp4","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.99183606825048,"uptime_last_5m":100,"uptime_last_1d":99.97914931841876,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-08,"_cached_write_per_m":null},{"name":"SambaNova | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000014","completion":"0.00000095","discount":0},"provider_name":"SambaNova","tag":"sambanova","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.70414201183432,"uptime_last_5m":100,"uptime_last_1d":99.75912679251215,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":9.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/turbo","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","structured_outputs","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.96611318197222,"uptime_last_5m":100,"uptime_last_1d":99.86801895566677,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Groq | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075","discount":0},"provider_name":"Groq","tag":"groq","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.99631166436146,"uptime_last_5m":100,"uptime_last_1d":99.98859022364277,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null},{"name":"Phala | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.73718791064388,"uptime_last_5m":100,"uptime_last_1d":99.61285327138985,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.86099230111206,"uptime_last_5m":100,"uptime_last_1d":90.03869560903499,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Together | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":87.62057877813506,"uptime_last_5m":93.4002869440459,"uptime_last_1d":66.57383913561144,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Nebius | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"Nebius","tag":"nebius/fp4","quantization":"fp4","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","repetition_penalty","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.84538739048273,"uptime_last_5m":99.75816203143893,"uptime_last_1d":99.09909577607284,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Mara | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000015","completion":"0.00000075","discount":0},"provider_name":"Mara","tag":"mara","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_k","top_p","tool_choice","tools","structured_outputs","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.05479452054794,"uptime_last_5m":94.6372239747634,"uptime_last_1d":81.43640884632083,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Cerebras | openai/gpt-oss-120b","model_id":"openai/gpt-oss-120b","model_name":"OpenAI: gpt-oss-120b","context_length":131072,"pricing":{"prompt":"0.00000035","completion":"0.00000075","input_cache_read":"0.00000035","discount":0},"provider_name":"Cerebras","tag":"cerebras/fp16","quantization":"fp16","max_completion_tokens":40960,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","logprobs","top_logprobs","tools","tool_choice","response_format","structured_outputs","frequency_penalty","presence_penalty","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.99558537877449,"uptime_last_5m":100,"uptime_last_1d":99.9869065878568,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"AkashML","_cheapest_blended_per_m":7.199999999999998e-08,"_priciest_blended_per_m":4.6999999999999995e-07,"_provider_spread_multiplier":6.527777777777779},{"id":"openai/gpt-5-mini","canonical_slug":"openai/gpt-5-mini-2025-08-07","hugging_face_id":"","name":"OpenAI: GPT-5 Mini","created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000002","web_search":"0.01","input_cache_read":"0.000000025"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-05-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1081,"win_rate":36.9,"rank":89},{"arena":"models","category":"asciiart","elo":1149,"win_rate":44.5,"rank":45},{"arena":"models","category":"codecategories","elo":1139,"win_rate":43.5,"rank":82},{"arena":"models","category":"dataviz","elo":1151,"win_rate":43.7,"rank":73},{"arena":"models","category":"gamedev","elo":1165,"win_rate":46.5,"rank":67},{"arena":"models","category":"svg","elo":1131,"win_rate":45.8,"rank":52},{"arena":"models","category":"uicomponent","elo":1132,"win_rate":41.9,"rank":73},{"arena":"models","category":"website","elo":1145,"win_rate":44.3,"rank":81}],"artificial_analysis":{"intelligence_index":25.8,"coding_index":15.6,"agentic_index":19.6}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5-mini-2025-08-07","model_id":"openai/gpt-5-mini","model_name":"OpenAI: GPT-5 Mini","context_length":400000,"pricing":{"prompt":"0.000000125","completion":"0.000001","web_search":"0.01","input_cache_read":"0.0000000125","discount":0},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-08,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5-mini-2025-08-07","model_id":"openai/gpt-5-mini","model_name":"OpenAI: GPT-5 Mini","context_length":400000,"pricing":{"prompt":"0.00000025","completion":"0.000002","web_search":"0.01","input_cache_read":"0.00000003","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":360000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9942900647126,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5-mini-2025-08-07","model_id":"openai/gpt-5-mini","model_name":"OpenAI: GPT-5 Mini","context_length":400000,"pricing":{"prompt":"0.00000025","completion":"0.000002","web_search":"0.01","input_cache_read":"0.000000025","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.80747884001666,"uptime_last_5m":99.22556853103872,"uptime_last_1d":99.57151022077635,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5-mini-2025-08-07","model_id":"openai/gpt-5-mini","model_name":"OpenAI: GPT-5 Mini","context_length":400000,"pricing":{"prompt":"0.000000275","completion":"0.0000022","web_search":"0.01","input_cache_read":"0.000000033","discount":0},"provider_name":"Azure","tag":"azure/swedencentral","quantization":"unknown","max_completion_tokens":360000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.75e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":3.875e-07,"_priciest_blended_per_m":8.525000000000001e-07,"_provider_spread_multiplier":2.2},{"id":"openai/gpt-5-nano","canonical_slug":"openai/gpt-5-nano-2025-08-07","hugging_face_id":"","name":"OpenAI: GPT-5 Nano","created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.0000004","web_search":"0.01","input_cache_read":"0.000000005"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-05-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1009,"win_rate":36.3,"rank":102},{"arena":"models","category":"codecategories","elo":1109,"win_rate":48,"rank":89},{"arena":"models","category":"dataviz","elo":1076,"win_rate":46.2,"rank":92},{"arena":"models","category":"gamedev","elo":1081,"win_rate":46.5,"rank":92},{"arena":"models","category":"uicomponent","elo":1093,"win_rate":51.9,"rank":87},{"arena":"models","category":"website","elo":1121,"win_rate":48.9,"rank":90}]},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"_prompt_per_m":5e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-09,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-5-nano-2025-08-07","model_id":"openai/gpt-5-nano","model_name":"OpenAI: GPT-5 Nano","context_length":400000,"pricing":{"prompt":"0.000000025","completion":"0.0000002","web_search":"0.01","input_cache_read":"0.0000000025","discount":0},"provider_name":"OpenAI","tag":"openai/flex","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-08,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-09,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5-nano-2025-08-07","model_id":"openai/gpt-5-nano","model_name":"OpenAI: GPT-5 Nano","context_length":400000,"pricing":{"prompt":"0.00000005","completion":"0.0000004","web_search":"0.01","input_cache_read":"0.00000001","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":360000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96194583624025,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-5-nano-2025-08-07","model_id":"openai/gpt-5-nano","model_name":"OpenAI: GPT-5 Nano","context_length":400000,"pricing":{"prompt":"0.00000005","completion":"0.0000004","web_search":"0.01","input_cache_read":"0.000000005","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":128000,"max_prompt_tokens":272000,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.57602862254025,"uptime_last_5m":98.54028317253477,"uptime_last_1d":97.75794476352098,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-09,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-5-nano-2025-08-07","model_id":"openai/gpt-5-nano","model_name":"OpenAI: GPT-5 Nano","context_length":400000,"pricing":{"prompt":"0.000000055","completion":"0.00000044","web_search":"0.01","input_cache_read":"0.000000011","discount":0},"provider_name":"Azure","tag":"azure/swedencentral","quantization":"unknown","max_completion_tokens":360000,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-08,"_completion_per_m":4.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-08,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":7.75e-08,"_priciest_blended_per_m":1.705e-07,"_provider_spread_multiplier":2.2},{"id":"mistralai/codestral-2508","canonical_slug":"mistralai/codestral-2508","hugging_face_id":"","name":"Mistral: Codestral 2508","created":1754079630,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","context_length":256000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000003"},"top_provider":{"context_length":256000,"max_completion_tokens":204800,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/codestral-2508/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1031,"win_rate":38.5,"rank":105},{"arena":"models","category":"dataviz","elo":1037,"win_rate":41.1,"rank":98},{"arena":"models","category":"gamedev","elo":1004,"win_rate":36.3,"rank":108},{"arena":"models","category":"uicomponent","elo":1043,"win_rate":46.7,"rank":95},{"arena":"models","category":"website","elo":1033,"win_rate":37.8,"rank":109},{"arena":"models","category":"3d","elo":1064,"win_rate":45.4,"rank":92}]},"_prompt_per_m":3e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/codestral-2508","model_id":"mistralai/codestral-2508","model_name":"Mistral: Codestral 2508","context_length":256000,"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000003","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":204800,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","prediction","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.6742671009772,"uptime_last_5m":99.61832061068702,"uptime_last_1d":99.90386114431222,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/codestral-2508","model_id":"mistralai/codestral-2508","model_name":"Mistral: Codestral 2508","context_length":256000,"pricing":{"prompt":"0.00000033","completion":"0.00000099","input_cache_read":"0.000000033","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":204800,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","prediction","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.3e-07,"_completion_per_m":9.9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":4.8e-07,"_priciest_blended_per_m":5.280000000000001e-07,"_provider_spread_multiplier":1.1000000000000003},{"id":"anthropic/claude-opus-4.1","canonical_slug":"anthropic/claude-4.1-opus-20250805","hugging_face_id":"","name":"Anthropic: Claude Opus 4.1","created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0.000075","web_search":"0.01","input_cache_read":"0.0000015","input_cache_write":"0.00001875","input_cache_write_1h":"0.00003"},"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.1-opus-20250805/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1197,"win_rate":51.9,"rank":49},{"arena":"models","category":"asciiart","elo":1194,"win_rate":51.5,"rank":23},{"arena":"models","category":"codecategories","elo":1195,"win_rate":55.8,"rank":55},{"arena":"models","category":"dataviz","elo":1187,"win_rate":56.4,"rank":58},{"arena":"models","category":"gamedev","elo":1207,"win_rate":58.4,"rank":47},{"arena":"models","category":"svg","elo":1192,"win_rate":60.8,"rank":33},{"arena":"models","category":"uicomponent","elo":1191,"win_rate":57.8,"rank":57},{"arena":"models","category":"website","elo":1196,"win_rate":55.3,"rank":60}]},"reasoning":{"mandatory":false},"_prompt_per_m":1.5e-05,"_completion_per_m":7.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-06,"_cached_write_per_m":1.875e-05,"_endpoints":[{"name":"Amazon Bedrock | anthropic/claude-4.1-opus-20250805","model_id":"anthropic/claude-opus-4.1","model_name":"Anthropic: Claude Opus 4.1","context_length":200000,"pricing":{"prompt":"0.000015","completion":"0.000075","web_search":"0.01","input_cache_read":"0.0000015","input_cache_write":"0.00001875","input_cache_write_1h":"0.00003","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.85355648535564,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-05,"_completion_per_m":7.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-06,"_cached_write_per_m":1.875e-05},{"name":"Google | anthropic/claude-4.1-opus-20250805","model_id":"anthropic/claude-opus-4.1","model_name":"Anthropic: Claude Opus 4.1","context_length":200000,"pricing":{"prompt":"0.000015","completion":"0.000075","web_search":"0.01","input_cache_read":"0.0000015","input_cache_write":"0.00001875","input_cache_write_1h":"0.00003","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-05,"_completion_per_m":7.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-06,"_cached_write_per_m":1.875e-05}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":3.2999999999999996e-05,"_priciest_blended_per_m":3.2999999999999996e-05,"_provider_spread_multiplier":1.0},{"id":"mistralai/codestral-2508:batch","canonical_slug":"mistralai/codestral-2508","hugging_face_id":"","name":"Mistral: Codestral 2508 (batch)","created":1754079630,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","context_length":256000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000003"},"top_provider":{"context_length":256000,"max_completion_tokens":204800,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/codestral-2508/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1031,"win_rate":38.5,"rank":105},{"arena":"models","category":"dataviz","elo":1037,"win_rate":41.1,"rank":98},{"arena":"models","category":"gamedev","elo":1004,"win_rate":36.3,"rank":108},{"arena":"models","category":"uicomponent","elo":1043,"win_rate":46.7,"rank":95},{"arena":"models","category":"website","elo":1033,"win_rate":37.8,"rank":109},{"arena":"models","category":"3d","elo":1064,"win_rate":45.4,"rank":92}]},"_prompt_per_m":3e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/codestral-2508:batch","model_id":"mistralai/codestral-2508:batch","model_name":"Mistral: Codestral 2508","context_length":256000,"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000003","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":204800,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","prediction","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":4.8e-07,"_priciest_blended_per_m":4.8e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-coder-30b-a3b-instruct","canonical_slug":"qwen/qwen3-coder-30b-a3b-instruct","hugging_face_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","created":1753972379,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000007","completion":"0.00000028"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-30b-a3b-instruct/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"dataviz","elo":1103,"win_rate":54.7,"rank":88},{"arena":"models","category":"uicomponent","elo":1072,"win_rate":54.1,"rank":89},{"arena":"models","category":"website","elo":1107,"win_rate":57.1,"rank":92}]},"_prompt_per_m":7e-08,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | qwen/qwen3-coder-30b-a3b-instruct","model_id":"qwen/qwen3-coder-30b-a3b-instruct","model_name":"Qwen: Qwen3 Coder 30B A3B Instruct","context_length":160000,"pricing":{"prompt":"0.00000007","completion":"0.00000027","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.27329192546584,"uptime_last_5m":100,"uptime_last_1d":97.5044972633674,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":2.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3-coder-30b-a3b-instruct","model_id":"qwen/qwen3-coder-30b-a3b-instruct","model_name":"Qwen: Qwen3 Coder 30B A3B Instruct","context_length":262144,"pricing":{"prompt":"0.00000007","completion":"0.00000028","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.11504424778761,"uptime_last_5m":99.31972789115646,"uptime_last_1d":99.06942854168835,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | qwen/qwen3-coder-30b-a3b-instruct","model_id":"qwen/qwen3-coder-30b-a3b-instruct","model_name":"Qwen: Qwen3 Coder 30B A3B Instruct","context_length":0,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":0,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tool_choice","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3-coder-30b-a3b-instruct","model_id":"qwen/qwen3-coder-30b-a3b-instruct","model_name":"Qwen: Qwen3 Coder 30B A3B Instruct","context_length":262144,"pricing":{"prompt":"0.0000002925","completion":"0.0000014625","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.0000004875","completion":"0.0000024375"},{"min_prompt_tokens":128000,"prompt":"0.00000078","completion":"0.0000039"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":204800,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.9670075882547,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.925e-07,"_completion_per_m":1.4625e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":1.3e-07,"_priciest_blended_per_m":6.435e-07,"_provider_spread_multiplier":4.949999999999999},{"id":"qwen/qwen3-30b-a3b-instruct-2507","canonical_slug":"qwen/qwen3-30b-a3b-instruct-2507","hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","created":1753806965,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000004815","completion":"0.00000019305"},"top_provider":{"context_length":128000,"max_completion_tokens":32000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-30b-a3b-instruct-2507/endpoints"},"_prompt_per_m":4.815e-08,"_completion_per_m":1.9305e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"StreamLake | qwen/qwen3-30b-a3b-instruct-2507","model_id":"qwen/qwen3-30b-a3b-instruct-2507","model_name":"Qwen: Qwen3 30B A3B Instruct 2507","context_length":128000,"pricing":{"prompt":"0.00000004815","completion":"0.00000019305","discount":0.55},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.29028774203502,"uptime_last_5m":99.28097345132744,"uptime_last_1d":99.77051956418961,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.815e-08,"_completion_per_m":1.9305e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3-30b-a3b-instruct-2507","model_id":"qwen/qwen3-30b-a3b-instruct-2507","model_name":"Qwen: Qwen3 30B A3B Instruct 2507","context_length":262144,"pricing":{"prompt":"0.00000009","completion":"0.0000003","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.71310222794176,"uptime_last_5m":99.56389010030527,"uptime_last_1d":97.98378339874527,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"CoreWeave | qwen/qwen3-30b-a3b-instruct-2507","model_id":"qwen/qwen3-30b-a3b-instruct-2507","model_name":"Qwen: Qwen3 30B A3B Instruct 2507","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.0000003","input_cache_read":"0.0000001","discount":0},"provider_name":"CoreWeave","tag":"coreweave/bf16","quantization":"bf16","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.5316440494776,"uptime_last_5m":97.50367107195301,"uptime_last_1d":99.65555400936988,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Nebius | qwen/qwen3-30b-a3b-instruct-2507","model_id":"qwen/qwen3-30b-a3b-instruct-2507","model_name":"Qwen: Qwen3 30B A3B Instruct 2507","context_length":262144,"pricing":{"prompt":"0.0000001","completion":"0.0000003","discount":0},"provider_name":"Nebius","tag":"nebius/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.73799126637554,"uptime_last_5m":99.65307892454467,"uptime_last_1d":94.07092938541656,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3-30b-a3b-instruct-2507","model_id":"qwen/qwen3-30b-a3b-instruct-2507","model_name":"Qwen: Qwen3 30B A3B Instruct 2507","context_length":131072,"pricing":{"prompt":"0.00000013","completion":"0.00000052","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":129024,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.96714848883047,"uptime_last_5m":99.9054820415879,"uptime_last_1d":99.9695773254123,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":5.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"StreamLake","_cheapest_blended_per_m":9.162e-08,"_priciest_blended_per_m":2.47e-07,"_provider_spread_multiplier":2.695917921851124},{"id":"z-ai/glm-4.5","canonical_slug":"z-ai/glm-4.5","hugging_face_id":"zai-org/GLM-4.5","name":"Z.ai: GLM 4.5","created":1753471347,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000022","input_cache_read":"0.00000011"},"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.75,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-12-31","expiration_date":"2026-12-31","links":{"details":"/api/v1/models/z-ai/glm-4.5/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1214,"win_rate":59.7,"rank":44},{"arena":"models","category":"codecategories","elo":1189,"win_rate":54.4,"rank":62},{"arena":"models","category":"dataviz","elo":1180,"win_rate":53.3,"rank":61},{"arena":"models","category":"gamedev","elo":1181,"win_rate":54.4,"rank":57},{"arena":"models","category":"svg","elo":1136,"win_rate":50.8,"rank":51},{"arena":"models","category":"uicomponent","elo":1170,"win_rate":55,"rank":65},{"arena":"models","category":"website","elo":1189,"win_rate":53.7,"rank":63}]},"reasoning":{"mandatory":false},"_prompt_per_m":6e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Z.AI | z-ai/glm-4.5","model_id":"z-ai/glm-4.5","model_name":"Z.ai: GLM 4.5","context_length":131072,"pricing":{"prompt":"0.0000006","completion":"0.0000022","input_cache_read":"0.00000011","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":98304,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","tools","tool_choice","top_k"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Z.AI","_cheapest_blended_per_m":1.08e-06,"_priciest_blended_per_m":1.08e-06,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-opus-4.1:batch","canonical_slug":"anthropic/claude-4.1-opus-20250805","hugging_face_id":"","name":"Anthropic: Claude Opus 4.1 (batch)","created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000075","completion":"0.0000375","web_search":"0.01","input_cache_read":"0.00000075","input_cache_write":"0.000009375","input_cache_write_1h":"0.000015"},"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.1-opus-20250805/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1197,"win_rate":51.9,"rank":49},{"arena":"models","category":"asciiart","elo":1194,"win_rate":51.5,"rank":23},{"arena":"models","category":"codecategories","elo":1195,"win_rate":55.8,"rank":55},{"arena":"models","category":"dataviz","elo":1187,"win_rate":56.4,"rank":58},{"arena":"models","category":"gamedev","elo":1207,"win_rate":58.4,"rank":47},{"arena":"models","category":"svg","elo":1192,"win_rate":60.8,"rank":33},{"arena":"models","category":"uicomponent","elo":1191,"win_rate":57.8,"rank":57},{"arena":"models","category":"website","elo":1196,"win_rate":55.3,"rank":60}]},"reasoning":{"mandatory":false},"_prompt_per_m":7.5e-06,"_completion_per_m":3.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-07,"_cached_write_per_m":9.375e-06,"_endpoints":[{"name":"Anthropic | anthropic/claude-4.1-opus-20250805:batch","model_id":"anthropic/claude-opus-4.1:batch","model_name":"Anthropic: Claude Opus 4.1","context_length":200000,"pricing":{"prompt":"0.0000075","completion":"0.0000375","web_search":"0.01","input_cache_read":"0.00000075","input_cache_write":"0.000009375","input_cache_write_1h":"0.000015","discount":0},"provider_name":"Anthropic","tag":"anthropic","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-06,"_completion_per_m":3.75e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-07,"_cached_write_per_m":9.375e-06}],"_cheapest_provider":"Anthropic","_cheapest_blended_per_m":1.6499999999999998e-05,"_priciest_blended_per_m":1.6499999999999998e-05,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-oss-20b","canonical_slug":"openai/gpt-oss-20b","hugging_face_id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000003","completion":"0.00000013","input_cache_read":"0.00000003"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-oss-20b/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"dataviz","elo":952,"win_rate":39.7,"rank":107},{"arena":"models","category":"website","elo":872,"win_rate":27.9,"rank":122}],"artificial_analysis":{"intelligence_index":15.2,"coding_index":20.7,"agentic_index":3.1}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"_prompt_per_m":3e-08,"_completion_per_m":1.3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Darkbloom | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000002","completion":"0.0000001","discount":0},"provider_name":"Darkbloom","tag":"darkbloom/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.95938261575954,"uptime_last_5m":100,"uptime_last_1d":99.00741814551672,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-08,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"CoreWeave | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000003","completion":"0.00000013","input_cache_read":"0.00000003","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp4","quantization":"fp4","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98132080938078,"uptime_last_5m":99.97656707674282,"uptime_last_1d":99.55529449863853,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":1.3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"DeepInfra | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000003","completion":"0.00000014","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8900293255132,"uptime_last_5m":100,"uptime_last_1d":99.91921774224944,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":1.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000003","completion":"0.00000015","input_cache_read":"0.00000002","discount":0},"provider_name":"Parasail","tag":"parasail/fp4","quantization":"fp4","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.71316177675791,"uptime_last_5m":99.8406374501992,"uptime_last_1d":98.62072635241871,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null},{"name":"Phala | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000004","completion":"0.00000015","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.27745664739885,"uptime_last_5m":100,"uptime_last_1d":99.87357774968395,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-08,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000004","completion":"0.00000015","discount":0},"provider_name":"Novita","tag":"novita/fp4","quantization":"fp4","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8217468805704,"uptime_last_5m":100,"uptime_last_1d":97.38225924077841,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-08,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000004","completion":"0.00000018","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","max_tokens","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":96.953523950569,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-08,"_completion_per_m":1.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Together | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000005","completion":"0.0000002","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.29328621908127,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000007","completion":"0.00000015","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.13790112749349,"uptime_last_5m":100,"uptime_last_1d":96.44387204428523,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000007","completion":"0.00000015","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000007","completion":"0.00000025","discount":0},"provider_name":"Google","tag":"google-vertex/us-central1","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","repetition_penalty","top_k","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.24748095355125,"uptime_last_5m":97.23374827109267,"uptime_last_1d":90.16633064516128,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":2.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Fireworks | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.00000007","completion":"0.0000003","input_cache_read":"0.000000035","discount":0},"provider_name":"Fireworks","tag":"fireworks","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":0,"uptime_last_5m":0,"uptime_last_1d":32.11892378475695,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-08,"_cached_write_per_m":null},{"name":"Groq | openai/gpt-oss-20b","model_id":"openai/gpt-oss-20b","model_name":"OpenAI: gpt-oss-20b","context_length":131072,"pricing":{"prompt":"0.000000075","completion":"0.0000003","input_cache_read":"0.0000000375","discount":0},"provider_name":"Groq","tag":"groq","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.14084276110839,"uptime_last_5m":99.4418910045962,"uptime_last_1d":98.85348335665412,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-08,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.75e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Darkbloom","_cheapest_blended_per_m":4.4e-08,"_priciest_blended_per_m":1.4249999999999999e-07,"_provider_spread_multiplier":3.2386363636363633},{"id":"z-ai/glm-4.5-air","canonical_slug":"z-ai/glm-4.5-air","hugging_face_id":"zai-org/GLM-4.5-Air","name":"Z.ai: GLM 4.5 Air","created":1753471258,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000013","completion":"0.00000085","input_cache_read":"0.000000025"},"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.75,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-12-31","expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.5-air/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1166,"win_rate":54.1,"rank":62},{"arena":"models","category":"codecategories","elo":1162,"win_rate":51.4,"rank":73},{"arena":"models","category":"dataviz","elo":1207,"win_rate":58.5,"rank":47},{"arena":"models","category":"gamedev","elo":1130,"win_rate":48.4,"rank":79},{"arena":"models","category":"svg","elo":1111,"win_rate":50.8,"rank":57},{"arena":"models","category":"uicomponent","elo":1149,"win_rate":54.4,"rank":71},{"arena":"models","category":"website","elo":1166,"win_rate":51.3,"rank":73}]},"reasoning":{"mandatory":false},"_prompt_per_m":1.3e-07,"_completion_per_m":8.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | z-ai/glm-4.5-air","model_id":"z-ai/glm-4.5-air","model_name":"Z.ai: GLM 4.5 Air","context_length":131072,"pricing":{"prompt":"0.00000013","completion":"0.00000085","input_cache_read":"0.000000025","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":98304,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.18509895227008,"uptime_last_5m":98.78048780487805,"uptime_last_1d":98.9413193975741,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":8.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null},{"name":"SiliconFlow | z-ai/glm-4.5-air","model_id":"z-ai/glm-4.5-air","model_name":"Z.ai: GLM 4.5 Air","context_length":131072,"pricing":{"prompt":"0.00000014","completion":"0.00000086","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":83.97435897435898,"uptime_last_5m":null,"uptime_last_1d":97.23521040861965,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":8.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Z.AI | z-ai/glm-4.5-air","model_id":"z-ai/glm-4.5-air","model_name":"Z.ai: GLM 4.5 Air","context_length":131072,"pricing":{"prompt":"0.0000002","completion":"0.0000011","input_cache_read":"0.00000003","discount":0},"provider_name":"Z.AI","tag":"z-ai/fp8","quantization":"fp8","max_completion_tokens":98304,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":95.75289575289575,"uptime_last_5m":100,"uptime_last_1d":98.04229195088676,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":3.46e-07,"_priciest_blended_per_m":4.7e-07,"_provider_spread_multiplier":1.3583815028901733},{"id":"qwen/qwen3-235b-a22b-thinking-2507","canonical_slug":"qwen/qwen3-235b-a22b-thinking-2507","hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","created":1753449557,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000023","completion":"0.0000023"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-235b-a22b-thinking-2507/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1042,"win_rate":40.4,"rank":95},{"arena":"models","category":"codecategories","elo":1057,"win_rate":40.8,"rank":100},{"arena":"models","category":"dataviz","elo":969,"win_rate":32.6,"rank":106},{"arena":"models","category":"gamedev","elo":993,"win_rate":34.2,"rank":109},{"arena":"models","category":"uicomponent","elo":971,"win_rate":34,"rank":106},{"arena":"models","category":"website","elo":1072,"win_rate":42,"rank":99}],"artificial_analysis":{"intelligence_index":19.9,"coding_index":22.1,"agentic_index":3.8}},"reasoning":{"mandatory":true},"_prompt_per_m":2.3e-07,"_completion_per_m":2.3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-235b-a22b-thinking-2507","model_id":"qwen/qwen3-235b-a22b-thinking-2507","model_name":"Qwen: Qwen3 235B A22B Thinking 2507","context_length":131072,"pricing":{"prompt":"0.00000023","completion":"0.0000023","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.81247069854665,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.3e-07,"_completion_per_m":2.3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3-235b-a22b-thinking-2507","model_id":"qwen/qwen3-235b-a22b-thinking-2507","model_name":"Qwen: Qwen3 235B A22B Thinking 2507","context_length":131072,"pricing":{"prompt":"0.0000003","completion":"0.000003","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":90.76348104644954,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3-235b-a22b-thinking-2507","model_id":"qwen/qwen3-235b-a22b-thinking-2507","model_name":"Qwen: Qwen3 235B A22B Thinking 2507","context_length":128000,"pricing":{"prompt":"0.00000045","completion":"0.0000035","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":93.42105263157895,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":3.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":8.51e-07,"_priciest_blended_per_m":1.3649999999999998e-06,"_provider_spread_multiplier":1.6039952996474733},{"id":"qwen/qwen3-coder","canonical_slug":"qwen/qwen3-coder-480b-a35b-07-25","hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen: Qwen3 Coder 480B A35B","created":1753230546,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.000001","input_cache_read":"0.0000001"},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-480b-a35b-07-25/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1167,"win_rate":61.2,"rank":69},{"arena":"models","category":"dataviz","elo":1102,"win_rate":54.9,"rank":89},{"arena":"models","category":"gamedev","elo":1135,"win_rate":58.7,"rank":74},{"arena":"models","category":"uicomponent","elo":1139,"win_rate":61.4,"rank":72},{"arena":"models","category":"website","elo":1178,"win_rate":61.7,"rank":70}]},"_prompt_per_m":3e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | qwen/qwen3-coder-480b-a35b-07-25","model_id":"qwen/qwen3-coder","model_name":"Qwen: Qwen3 Coder 480B A35B","context_length":262144,"pricing":{"prompt":"0.00000022","completion":"0.0000018","discount":0},"provider_name":"Google","tag":"google-vertex/us-south1","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.94205250043461,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":1.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3-coder-480b-a35b-07-25","model_id":"qwen/qwen3-coder","model_name":"Qwen: Qwen3 Coder 480B A35B","context_length":262144,"pricing":{"prompt":"0.0000003","completion":"0.000001","input_cache_read":"0.0000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/turbo","quantization":"fp4","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":97.12007972097658,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3-coder-480b-a35b-07-25","model_id":"qwen/qwen3-coder","model_name":"Qwen: Qwen3 Coder 480B A35B","context_length":256000,"pricing":{"prompt":"0.00000035","completion":"0.0000015","input_cache_read":"0.00000004","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":90.090548377251,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3-coder-480b-a35b-07-25","model_id":"qwen/qwen3-coder","model_name":"Qwen: Qwen3 Coder 480B A35B","context_length":262144,"pricing":{"prompt":"0.00000038","completion":"0.00000155","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":91.81818181818183,"uptime_last_5m":null,"uptime_last_1d":93.70431893687707,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.8e-07,"_completion_per_m":1.55e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3-coder-480b-a35b-07-25","model_id":"qwen/qwen3-coder","model_name":"Qwen: Qwen3 Coder 480B A35B","context_length":262144,"pricing":{"prompt":"0.000000975","completion":"0.000004875","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.000001755","completion":"0.000008775"},{"min_prompt_tokens":128000,"prompt":"0.000002925","completion":"0.000014625"}]},"provider_name":"Alibaba","tag":"alibaba/opensource","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":204800,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9.75e-07,"_completion_per_m":4.875e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":5.1e-07,"_priciest_blended_per_m":2.145e-06,"_provider_spread_multiplier":4.205882352941176},{"id":"google/gemini-2.5-flash-lite","canonical_slug":"google/gemini-2.5-flash-lite","hugging_face_id":"","name":"Google: Gemini 2.5 Flash Lite","created":1753200276,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000004","image":"0.0000001","audio":"0.0000003","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000004","input_cache_read":"0.00000001","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-flash-lite/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":1e-07,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":8.33333333333333e-08,"_endpoints":[{"name":"Google | google/gemini-2.5-flash-lite","model_id":"google/gemini-2.5-flash-lite","model_name":"Google: Gemini 2.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.0000001","completion":"0.0000004","image":"0.0000001","audio":"0.0000003","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000004","input_cache_read":"0.00000001","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/eu","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.89949347168606,"uptime_last_5m":99.8592409184954,"uptime_last_1d":99.71573852255227,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":1e-07,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google | google/gemini-2.5-flash-lite","model_id":"google/gemini-2.5-flash-lite","model_name":"Google: Gemini 2.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.0000001","completion":"0.0000004","image":"0.0000001","audio":"0.0000003","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000004","input_cache_read":"0.00000001","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.79763359567335,"uptime_last_5m":99.49547775795237,"uptime_last_1d":99.712219055407,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":1e-07,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-2.5-flash-lite","model_id":"google/gemini-2.5-flash-lite","model_name":"Google: Gemini 2.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.0000001","completion":"0.0000004","image":"0.0000001","audio":"0.0000003","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000004","input_cache_read":"0.00000001","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.64610022319381,"uptime_last_5m":99.64360493607164,"uptime_last_1d":99.70798136734524,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":1e-07,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-2.5-flash-lite","model_id":"google/gemini-2.5-flash-lite","model_name":"Google: Gemini 2.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000005","completion":"0.0000002","image":"0.00000005","audio":"0.00000015","input_audio_cache":"0.000000015","web_search":"0.014","internal_reasoning":"0.0000002","input_cache_read":"0.000000005","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.64610022319381,"uptime_last_5m":99.64360493607164,"uptime_last_1d":99.70798136734524,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":2e-07,"_image_per_m":5e-08,"_request_per_m":null,"_cached_read_per_m":5e-09,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-2.5-flash-lite","model_id":"google/gemini-2.5-flash-lite","model_name":"Google: Gemini 2.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000018","completion":"0.00000072","image":"0.00000018","audio":"0.00000054","input_audio_cache":"0.000000054","web_search":"0.014","internal_reasoning":"0.00000072","input_cache_read":"0.000000018","input_cache_write":"0.00000015","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.64610022319381,"uptime_last_5m":99.64360493607164,"uptime_last_1d":99.70798136734524,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.8e-07,"_completion_per_m":7.2e-07,"_image_per_m":1.8e-07,"_request_per_m":null,"_cached_read_per_m":1.8e-08,"_cached_write_per_m":1.5e-07}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":9.499999999999999e-08,"_priciest_blended_per_m":3.4199999999999997e-07,"_provider_spread_multiplier":3.6},{"id":"moonshotai/kimi-k2","canonical_slug":"moonshotai/kimi-k2","hugging_face_id":"moonshotai/Kimi-K2-Instruct","name":"MoonshotAI: Kimi K2 0711","created":1752263252,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000057","completion":"0.0000023"},"top_provider":{"context_length":131072,"max_completion_tokens":100352,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-12-31","expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1058,"win_rate":51.7,"rank":99},{"arena":"models","category":"dataviz","elo":1037,"win_rate":49.4,"rank":99},{"arena":"models","category":"gamedev","elo":1010,"win_rate":46.4,"rank":105},{"arena":"models","category":"uicomponent","elo":1056,"win_rate":55.1,"rank":91},{"arena":"models","category":"website","elo":1070,"win_rate":53.1,"rank":100}]},"_prompt_per_m":5.7e-07,"_completion_per_m":2.3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | moonshotai/kimi-k2","model_id":"moonshotai/kimi-k2","model_name":"MoonshotAI: Kimi K2 0711","context_length":131072,"pricing":{"prompt":"0.00000057","completion":"0.0000023","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":100352,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99461434200724,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.7e-07,"_completion_per_m":2.3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":1.089e-06,"_priciest_blended_per_m":1.089e-06,"_provider_spread_multiplier":1.0},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","canonical_slug":"venice/uncensored","hugging_face_id":"cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition","name":"Venice: Uncensored","created":1752094966,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000009"},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-04-30","expiration_date":null,"links":{"details":"/api/v1/models/venice/uncensored/endpoints"},"_prompt_per_m":2e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Venice | venice/uncensored","model_id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","model_name":"Venice: Uncensored","context_length":128000,"pricing":{"prompt":"0.0000002","completion":"0.0000009","discount":0},"provider_name":"Venice","tag":"venice/fp16","quantization":"fp16","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98453927025356,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Venice","_cheapest_blended_per_m":4.0999999999999994e-07,"_priciest_blended_per_m":4.0999999999999994e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-235b-a22b-2507","canonical_slug":"qwen/qwen3-235b-a22b-07-25","hugging_face_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","created":1753119555,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000000875","completion":"0.00000035","input_cache_read":"0.0000000175"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-235b-a22b-07-25/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1038,"win_rate":41.1,"rank":96},{"arena":"models","category":"codecategories","elo":1063,"win_rate":42.6,"rank":97},{"arena":"models","category":"dataviz","elo":1090,"win_rate":49,"rank":91},{"arena":"models","category":"gamedev","elo":988,"win_rate":35,"rank":110},{"arena":"models","category":"uicomponent","elo":991,"win_rate":38.4,"rank":102},{"arena":"models","category":"website","elo":1078,"win_rate":43.6,"rank":98}]},"_prompt_per_m":8.75e-08,"_completion_per_m":3.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"GMICloud | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":262144,"pricing":{"prompt":"0.0000000875","completion":"0.00000035","input_cache_read":"0.0000000175","discount":0.75},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":84.8817114593886,"uptime_last_5m":80.96139288417865,"uptime_last_1d":86.90255058382313,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.75e-08,"_completion_per_m":3.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.75e-08,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":262144,"pricing":{"prompt":"0.00000009","completion":"0.00000055","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":98.26319305277221,"uptime_last_5m":98.0225988700565,"uptime_last_1d":98.87037801747532,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":5.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":131072,"pricing":{"prompt":"0.00000009","completion":"0.00000058","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.19307511737088,"uptime_last_5m":99.91158267020336,"uptime_last_1d":98.79698172585202,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":5.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":131072,"pricing":{"prompt":"0.00000014","completion":"0.0000008","input_cache_read":"0.00000005","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.87577639751552,"uptime_last_5m":99.58563535911603,"uptime_last_1d":99.83058795695837,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":131072,"pricing":{"prompt":"0.0000001495","completion":"0.000000598","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":129024,"supported_parameters":["response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99019439609737,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.495e-07,"_completion_per_m":5.98e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Venice | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":128000,"pricing":{"prompt":"0.00000015","completion":"0.00000075","discount":0},"provider_name":"Venice","tag":"venice/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":98.38913455464309,"uptime_last_5m":96.17834394904459,"uptime_last_1d":98.09024745269286,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Nebius | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":262144,"pricing":{"prompt":"0.0000002","completion":"0.0000006","discount":0},"provider_name":"Nebius","tag":"nebius/fp8","quantization":"fp8","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":96.59275283937264,"uptime_last_5m":96.49122807017544,"uptime_last_1d":90.65345165379739,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"AtlasCloud | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":131072,"pricing":{"prompt":"0.0000002","completion":"0.00000088","input_cache_read":"0.0000002","discount":0},"provider_name":"AtlasCloud","tag":"atlas-cloud/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.62235649546828,"uptime_last_5m":99.51690821256038,"uptime_last_1d":99.04961340206185,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":8.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"StreamLake | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":128000,"pricing":{"prompt":"0.00000021","completion":"0.00000084","discount":0.4},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.67768595041322,"uptime_last_5m":100,"uptime_last_1d":99.03543069741806,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.1e-07,"_completion_per_m":8.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":262144,"pricing":{"prompt":"0.00000022","completion":"0.00000088","discount":0},"provider_name":"Google","tag":"google-vertex/us-south1","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.94368598085323,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":8.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google | qwen/qwen3-235b-a22b-07-25","model_id":"qwen/qwen3-235b-a22b-2507","model_name":"Qwen: Qwen3 235B A22B Instruct 2507","context_length":262144,"pricing":{"prompt":"0.00000025","completion":"0.000001","discount":0},"provider_name":"Google","tag":"google-vertex/us-south1","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.20405043943447,"uptime_last_5m":97.81818181818181,"uptime_last_1d":98.27176608797808,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"GMICloud","_cheapest_blended_per_m":1.6625e-07,"_priciest_blended_per_m":4.75e-07,"_provider_spread_multiplier":2.857142857142857},{"id":"tencent/hunyuan-a13b-instruct","canonical_slug":"tencent/hunyuan-a13b-instruct","hugging_face_id":"tencent/Hunyuan-A13B-Instruct","name":"Tencent: Hunyuan A13B Instruct","created":1751987664,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.00000057"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/tencent/hunyuan-a13b-instruct/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1.4e-07,"_completion_per_m":5.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"SiliconFlow | tencent/hunyuan-a13b-instruct","model_id":"tencent/hunyuan-a13b-instruct","model_name":"Tencent: Hunyuan A13B Instruct","context_length":131072,"pricing":{"prompt":"0.00000014","completion":"0.00000057","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":5.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"SiliconFlow","_cheapest_blended_per_m":2.69e-07,"_priciest_blended_per_m":2.69e-07,"_provider_spread_multiplier":1.0},{"id":"morph/morph-v3-large","canonical_slug":"morph/morph-v3-large","hugging_face_id":"","name":"Morph: Morph V3 Large","created":1751910858,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000009","completion":"0.0000019"},"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/morph/morph-v3-large/endpoints"},"_prompt_per_m":9e-07,"_completion_per_m":1.9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Morph | morph/morph-v3-large","model_id":"morph/morph-v3-large","model_name":"Morph: Morph V3 Large","context_length":262144,"pricing":{"prompt":"0.0000009","completion":"0.0000019","discount":0},"provider_name":"Morph","tag":"morph/fp8","quantization":"fp8","max_completion_tokens":131072,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-07,"_completion_per_m":1.9e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Morph","_cheapest_blended_per_m":1.2e-06,"_priciest_blended_per_m":1.2e-06,"_provider_spread_multiplier":1.0},{"id":"bytedance/ui-tars-1.5-7b","canonical_slug":"bytedance/ui-tars-1.5-7b","hugging_face_id":"ByteDance-Seed/UI-TARS-1.5-7B","name":"ByteDance: UI-TARS 7B ","created":1753205056,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000002","input_cache_read":"0.0000001"},"top_provider":{"context_length":128000,"max_completion_tokens":2048,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/bytedance/ui-tars-1.5-7b/endpoints"},"_prompt_per_m":1e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Parasail | bytedance/ui-tars-1.5-7b","model_id":"bytedance/ui-tars-1.5-7b","model_name":"ByteDance: UI-TARS 7B ","context_length":128000,"pricing":{"prompt":"0.0000001","completion":"0.0000002","input_cache_read":"0.0000001","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":2048,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Parasail","_cheapest_blended_per_m":1.2999999999999997e-07,"_priciest_blended_per_m":1.2999999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"baidu/ernie-4.5-vl-424b-a47b","canonical_slug":"baidu/ernie-4.5-vl-424b-a47b","hugging_face_id":"baidu/ERNIE-4.5-VL-424B-A47B-PT","name":"Baidu: ERNIE 4.5 VL 424B A47B ","created":1751300903,"description":"ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...","context_length":123000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000042","completion":"0.00000125"},"top_provider":{"context_length":123000,"max_completion_tokens":16000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/baidu/ernie-4.5-vl-424b-a47b/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":4.2e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | baidu/ernie-4.5-vl-424b-a47b","model_id":"baidu/ernie-4.5-vl-424b-a47b","model_name":"Baidu: ERNIE 4.5 VL 424B A47B ","context_length":123000,"pricing":{"prompt":"0.00000042","completion":"0.00000125","discount":0},"provider_name":"Novita","tag":"novita/fp16","quantization":"fp16","max_completion_tokens":16000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.2e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":6.69e-07,"_priciest_blended_per_m":6.69e-07,"_provider_spread_multiplier":1.0},{"id":"morph/morph-v3-fast","canonical_slug":"morph/morph-v3-fast","hugging_face_id":"","name":"Morph: Morph V3 Fast","created":1751910002,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...","context_length":81920,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000008","completion":"0.0000012"},"top_provider":{"context_length":81920,"max_completion_tokens":38000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/morph/morph-v3-fast/endpoints"},"_prompt_per_m":8e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Morph | morph/morph-v3-fast","model_id":"morph/morph-v3-fast","model_name":"Morph: Morph V3 Fast","context_length":81920,"pricing":{"prompt":"0.0000008","completion":"0.0000012","discount":0},"provider_name":"Morph","tag":"morph","quantization":"unknown","max_completion_tokens":38000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Morph","_cheapest_blended_per_m":9.199999999999999e-07,"_priciest_blended_per_m":9.199999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-small-3.2-24b-instruct","canonical_slug":"mistralai/mistral-small-3.2-24b-instruct-2506","hugging_face_id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"Mistral: Mistral Small 3.2 24B","created":1750443016,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000000075","completion":"0.0000002"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-3.2-24b-instruct-2506/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":931,"win_rate":39.8,"rank":116},{"arena":"models","category":"dataviz","elo":948,"win_rate":43.3,"rank":108},{"arena":"models","category":"gamedev","elo":925,"win_rate":39.4,"rank":117},{"arena":"models","category":"uicomponent","elo":933,"win_rate":40.5,"rank":110},{"arena":"models","category":"website","elo":915,"win_rate":38.3,"rank":119}]},"_prompt_per_m":7.5e-08,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | mistralai/mistral-small-3.2-24b-instruct-2506","model_id":"mistralai/mistral-small-3.2-24b-instruct","model_name":"Mistral: Mistral Small 3.2 24B","context_length":128000,"pricing":{"prompt":"0.000000075","completion":"0.0000002","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.96516650411034,"uptime_last_5m":99.92537313432835,"uptime_last_1d":99.91147320641144,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-08,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | mistralai/mistral-small-3.2-24b-instruct-2506","model_id":"mistralai/mistral-small-3.2-24b-instruct","model_name":"Mistral: Mistral Small 3.2 24B","context_length":131072,"pricing":{"prompt":"0.00000009","completion":"0.0000003","input_cache_read":"0.00000005","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.29742388758783,"uptime_last_5m":100,"uptime_last_1d":99.38606847697756,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":9e-08,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-small-3.2-24b-instruct-2506","model_id":"mistralai/mistral-small-3.2-24b-instruct","model_name":"Mistral: Mistral Small 3.2 24B","context_length":131072,"pricing":{"prompt":"0.00000011","completion":"0.00000033","input_cache_read":"0.000000011","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.94285714285715,"uptime_last_5m":100,"uptime_last_1d":99.71231222265948,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-07,"_completion_per_m":3.3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-08,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.1249999999999998e-07,"_priciest_blended_per_m":1.76e-07,"_provider_spread_multiplier":1.5644444444444445},{"id":"google/gemini-2.5-flash-lite:batch","canonical_slug":"google/gemini-2.5-flash-lite","hugging_face_id":"","name":"Google: Gemini 2.5 Flash Lite (batch)","created":1753200276,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.0000002","image":"0.00000005","audio":"0.00000015","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000002","input_cache_read":"0.00000001"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-flash-lite/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":5e-08,"_completion_per_m":2e-07,"_image_per_m":5e-08,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | google/gemini-2.5-flash-lite:batch","model_id":"google/gemini-2.5-flash-lite:batch","model_name":"Google: Gemini 2.5 Flash Lite","context_length":1048576,"pricing":{"prompt":"0.00000005","completion":"0.0000002","image":"0.00000005","audio":"0.00000015","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000002","input_cache_read":"0.00000001","discount":0},"provider_name":"Google","tag":"google-vertex/eu","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":2e-07,"_image_per_m":5e-08,"_request_per_m":null,"_cached_read_per_m":1e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Google","_cheapest_blended_per_m":9.499999999999999e-08,"_priciest_blended_per_m":9.499999999999999e-08,"_provider_spread_multiplier":1.0},{"id":"minimax/minimax-m1","canonical_slug":"minimax/minimax-m1","hugging_face_id":"","name":"MiniMax: MiniMax M1","created":1750200414,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000055","completion":"0.0000022"},"top_provider":{"context_length":1000000,"max_completion_tokens":40000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m1/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":5.5e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Minimax | minimax/minimax-m1","model_id":"minimax/minimax-m1","model_name":"MiniMax: MiniMax M1","context_length":1000000,"pricing":{"prompt":"0.0000004","completion":"0.0000022","discount":0},"provider_name":"Minimax","tag":"minimax","quantization":"unknown","max_completion_tokens":40000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | minimax/minimax-m1","model_id":"minimax/minimax-m1","model_name":"MiniMax: MiniMax M1","context_length":1000000,"pricing":{"prompt":"0.00000055","completion":"0.0000022","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":40000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.62962962962963,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Minimax","_cheapest_blended_per_m":9.4e-07,"_priciest_blended_per_m":1.0450000000000002e-06,"_provider_spread_multiplier":1.1117021276595747},{"id":"google/gemini-2.5-flash:batch","canonical_slug":"google/gemini-2.5-flash","hugging_face_id":"","name":"Google: Gemini 2.5 Flash (batch)","created":1750172488,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","audio":"0.0000005","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.00000125","input_cache_read":"0.00000003"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-flash/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1115,"win_rate":47.4,"rank":84},{"arena":"models","category":"codecategories","elo":1128,"win_rate":46.9,"rank":86},{"arena":"models","category":"dataviz","elo":1154,"win_rate":49.1,"rank":72},{"arena":"models","category":"gamedev","elo":1102,"win_rate":44.3,"rank":88},{"arena":"models","category":"uicomponent","elo":1119,"win_rate":48.9,"rank":81},{"arena":"models","category":"website","elo":1135,"win_rate":47.1,"rank":86},{"arena":"models","category":"svg","elo":1060,"win_rate":43.1,"rank":68}]},"reasoning":{"mandatory":false},"_prompt_per_m":1.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":1.5e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | google/gemini-2.5-flash:batch","model_id":"google/gemini-2.5-flash:batch","model_name":"Google: Gemini 2.5 Flash","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","audio":"0.0000005","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.00000125","input_cache_read":"0.00000003","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":1.5e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Google","_cheapest_blended_per_m":4.8e-07,"_priciest_blended_per_m":4.8e-07,"_provider_spread_multiplier":1.0},{"id":"google/gemini-2.5-flash","canonical_slug":"google/gemini-2.5-flash","hugging_face_id":"","name":"Google: Gemini 2.5 Flash","created":1750172488,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-flash/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1115,"win_rate":47.4,"rank":84},{"arena":"models","category":"codecategories","elo":1128,"win_rate":46.9,"rank":86},{"arena":"models","category":"dataviz","elo":1154,"win_rate":49.1,"rank":72},{"arena":"models","category":"gamedev","elo":1102,"win_rate":44.3,"rank":88},{"arena":"models","category":"uicomponent","elo":1119,"win_rate":48.9,"rank":81},{"arena":"models","category":"website","elo":1135,"win_rate":47.1,"rank":86},{"arena":"models","category":"svg","elo":1060,"win_rate":43.1,"rank":68}]},"reasoning":{"mandatory":false},"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08,"_endpoints":[{"name":"Google | google/gemini-2.5-flash","model_id":"google/gemini-2.5-flash","model_name":"Google: Gemini 2.5 Flash","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.67474006160172,"uptime_last_5m":99.86377431369844,"uptime_last_1d":99.66908762191339,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google | google/gemini-2.5-flash","model_id":"google/gemini-2.5-flash","model_name":"Google: Gemini 2.5 Flash","context_length":1048576,"pricing":{"prompt":"0.00000054","completion":"0.0000045","image":"0.00000054","audio":"0.0000018","input_audio_cache":"0.00000018","web_search":"0.014","internal_reasoning":"0.0000045","input_cache_read":"0.000000054","input_cache_write":"0.00000015","discount":0},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.67474006160172,"uptime_last_5m":99.86377431369844,"uptime_last_1d":99.66908762191339,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.4e-07,"_completion_per_m":4.5e-06,"_image_per_m":5.4e-07,"_request_per_m":null,"_cached_read_per_m":5.4e-08,"_cached_write_per_m":1.5e-07},{"name":"Google | google/gemini-2.5-flash","model_id":"google/gemini-2.5-flash","model_name":"Google: Gemini 2.5 Flash","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex/eu","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.58349688539978,"uptime_last_5m":99.22196796338673,"uptime_last_1d":98.5109690953223,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-2.5-flash","model_id":"google/gemini-2.5-flash","model_name":"Google: Gemini 2.5 Flash","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.94286544064859,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08},{"name":"Google AI Studio | google/gemini-2.5-flash","model_id":"google/gemini-2.5-flash","model_name":"Google: Gemini 2.5 Flash","context_length":1048576,"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.00000125","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.94286544064859,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":1.5e-07,"_request_per_m":null,"_cached_read_per_m":1.5e-08,"_cached_write_per_m":4.16666666666667e-08},{"name":"Google AI Studio | google/gemini-2.5-flash","model_id":"google/gemini-2.5-flash","model_name":"Google: Gemini 2.5 Flash","context_length":1048576,"pricing":{"prompt":"0.00000054","completion":"0.0000045","image":"0.00000054","audio":"0.0000018","input_audio_cache":"0.00000018","web_search":"0.014","internal_reasoning":"0.0000045","input_cache_read":"0.000000054","input_cache_write":"0.00000015","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.94286544064859,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.4e-07,"_completion_per_m":4.5e-06,"_image_per_m":5.4e-07,"_request_per_m":null,"_cached_read_per_m":5.4e-08,"_cached_write_per_m":1.5e-07},{"name":"Google | google/gemini-2.5-flash","model_id":"google/gemini-2.5-flash","model_name":"Google: Gemini 2.5 Flash","context_length":1048576,"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","discount":0},"provider_name":"Google","tag":"google-vertex","quantization":"unknown","max_completion_tokens":65535,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":65.56818181818181,"uptime_last_5m":35.8974358974359,"uptime_last_1d":65.92417373020567,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-07,"_completion_per_m":2.5e-06,"_image_per_m":3e-07,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":8.33333333333333e-08}],"_cheapest_provider":"Google AI Studio","_cheapest_blended_per_m":4.8e-07,"_priciest_blended_per_m":1.728e-06,"_provider_spread_multiplier":3.6000000000000005},{"id":"google/gemini-2.5-pro","canonical_slug":"google/gemini-2.5-pro","hugging_face_id":"","name":"Google: Gemini 2.5 Pro","created":1750169544,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-pro/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1124,"win_rate":50.6,"rank":79},{"arena":"models","category":"codecategories","elo":1177,"win_rate":57.5,"rank":66},{"arena":"models","category":"dataviz","elo":1242,"win_rate":68.2,"rank":34},{"arena":"models","category":"gamedev","elo":1147,"win_rate":54.2,"rank":71},{"arena":"models","category":"uicomponent","elo":1166,"win_rate":57.5,"rank":66},{"arena":"models","category":"website","elo":1187,"win_rate":58.4,"rank":64}],"artificial_analysis":{"intelligence_index":25.9,"coding_index":33.3,"agentic_index":7.2}},"reasoning":{"mandatory":true},"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07,"_endpoints":[{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.56505645012031,"uptime_last_5m":99.77912755383765,"uptime_last_1d":99.50885187737619,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","audio":"0.000000625","input_audio_cache":"0.0000000625","web_search":"0.014","internal_reasoning":"0.000005","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.00000125","completion":"0.0000075","audio":"0.00000125","input_audio_cache":"0.000000125","input_cache_read":"0.000000125"}]},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.56505645012031,"uptime_last_5m":99.77912755383765,"uptime_last_1d":99.50885187737619,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.25e-07,"_completion_per_m":5e-06,"_image_per_m":6.25e-07,"_request_per_m":null,"_cached_read_per_m":6.25e-08,"_cached_write_per_m":1.875e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000225","completion":"0.000018","image":"0.00000225","audio":"0.00000225","input_audio_cache":"0.000000225","web_search":"0.014","internal_reasoning":"0.000018","input_cache_read":"0.000000225","input_cache_write":"0.000000675","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000045","completion":"0.000027","audio":"0.0000045","input_audio_cache":"0.00000045","input_cache_read":"0.00000045"}]},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.56505645012031,"uptime_last_5m":99.77912755383765,"uptime_last_1d":99.50885187737619,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.25e-06,"_completion_per_m":1.8e-05,"_image_per_m":2.25e-06,"_request_per_m":null,"_cached_read_per_m":2.25e-07,"_cached_write_per_m":6.75e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":63.67713004484305,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/eu","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":65.45632973503434,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google AI Studio | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":92.8709055876686,"uptime_last_5m":91.17647058823529,"uptime_last_1d":96.29248621512633,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google AI Studio | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","audio":"0.000000625","input_audio_cache":"0.0000000625","web_search":"0.014","internal_reasoning":"0.000005","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.00000125","completion":"0.0000075","audio":"0.00000125","input_audio_cache":"0.000000125","input_cache_read":"0.000000125"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":92.8709055876686,"uptime_last_5m":91.17647058823529,"uptime_last_1d":96.29248621512633,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.25e-07,"_completion_per_m":5e-06,"_image_per_m":6.25e-07,"_request_per_m":null,"_cached_read_per_m":6.25e-08,"_cached_write_per_m":1.875e-07},{"name":"Google AI Studio | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000225","completion":"0.000018","image":"0.00000225","audio":"0.00000225","input_audio_cache":"0.000000225","web_search":"0.014","internal_reasoning":"0.000018","input_cache_read":"0.000000225","input_cache_write":"0.000000675","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000045","completion":"0.000027","audio":"0.0000045","input_audio_cache":"0.00000045","input_cache_read":"0.00000045"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":92.8709055876686,"uptime_last_5m":91.17647058823529,"uptime_last_1d":96.29248621512633,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.25e-06,"_completion_per_m":1.8e-05,"_image_per_m":2.25e-06,"_request_per_m":null,"_cached_read_per_m":2.25e-07,"_cached_write_per_m":6.75e-07}],"_cheapest_provider":"Google","_cheapest_blended_per_m":1.9375e-06,"_priciest_blended_per_m":6.975e-06,"_provider_spread_multiplier":3.6},{"id":"openai/o3-pro","canonical_slug":"openai/o3-pro-2025-06-10","hugging_face_id":"","name":"OpenAI: o3 Pro","created":1749598352,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","file","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00002","completion":"0.00008","web_search":"0.01"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/o3-pro-2025-06-10/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":2e-05,"_completion_per_m":8e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/o3-pro-2025-06-10","model_id":"openai/o3-pro","model_name":"OpenAI: o3 Pro","context_length":200000,"pricing":{"prompt":"0.00002","completion":"0.00008","web_search":"0.01","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":100000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-05,"_completion_per_m":8e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":3.8e-05,"_priciest_blended_per_m":3.8e-05,"_provider_spread_multiplier":1.0},{"id":"google/gemini-2.5-pro-preview","canonical_slug":"google/gemini-2.5-pro-preview-06-05","hugging_face_id":"","name":"Google: Gemini 2.5 Pro Preview 06-05","created":1749137257,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio->text","input_modalities":["file","image","text","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-pro-preview-06-05/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07,"_endpoints":[{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.54703832752612,"uptime_last_5m":99.14187643020595,"uptime_last_1d":99.50672690231771,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","audio":"0.000000625","input_audio_cache":"0.0000000625","web_search":"0.014","internal_reasoning":"0.000005","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.00000125","completion":"0.0000075","audio":"0.00000125","input_audio_cache":"0.000000125","input_cache_read":"0.000000125"}]},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.54703832752612,"uptime_last_5m":99.14187643020595,"uptime_last_1d":99.50672690231771,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.25e-07,"_completion_per_m":5e-06,"_image_per_m":6.25e-07,"_request_per_m":null,"_cached_read_per_m":6.25e-08,"_cached_write_per_m":1.875e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000225","completion":"0.000018","image":"0.00000225","audio":"0.00000225","input_audio_cache":"0.000000225","web_search":"0.014","internal_reasoning":"0.000018","input_cache_read":"0.000000225","input_cache_write":"0.000000675","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000045","completion":"0.000027","audio":"0.0000045","input_audio_cache":"0.00000045","input_cache_read":"0.00000045"}]},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.54703832752612,"uptime_last_5m":99.14187643020595,"uptime_last_1d":99.50672690231771,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.25e-06,"_completion_per_m":1.8e-05,"_image_per_m":2.25e-06,"_request_per_m":null,"_cached_read_per_m":2.25e-07,"_cached_write_per_m":6.75e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":63.6001989060169,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/eu","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":65.49192364170338,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google AI Studio | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":93.22033898305084,"uptime_last_5m":90.76923076923077,"uptime_last_1d":96.24758538489992,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google AI Studio | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","audio":"0.000000625","input_audio_cache":"0.0000000625","web_search":"0.014","internal_reasoning":"0.000005","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.00000125","completion":"0.0000075","audio":"0.00000125","input_audio_cache":"0.000000125","input_cache_read":"0.000000125"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":93.22033898305084,"uptime_last_5m":90.76923076923077,"uptime_last_1d":96.24758538489992,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.25e-07,"_completion_per_m":5e-06,"_image_per_m":6.25e-07,"_request_per_m":null,"_cached_read_per_m":6.25e-08,"_cached_write_per_m":1.875e-07},{"name":"Google AI Studio | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000225","completion":"0.000018","image":"0.00000225","audio":"0.00000225","input_audio_cache":"0.000000225","web_search":"0.014","internal_reasoning":"0.000018","input_cache_read":"0.000000225","input_cache_write":"0.000000675","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000045","completion":"0.000027","audio":"0.0000045","input_audio_cache":"0.00000045","input_cache_read":"0.00000045"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":93.22033898305084,"uptime_last_5m":90.76923076923077,"uptime_last_1d":96.24758538489992,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.25e-06,"_completion_per_m":1.8e-05,"_image_per_m":2.25e-06,"_request_per_m":null,"_cached_read_per_m":2.25e-07,"_cached_write_per_m":6.75e-07}],"_cheapest_provider":"Google","_cheapest_blended_per_m":1.9375e-06,"_priciest_blended_per_m":6.975e-06,"_provider_spread_multiplier":3.6},{"id":"deepseek/deepseek-r1-0528","canonical_slug":"deepseek/deepseek-r1-0528","hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek: R1 0528","created":1748455170,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.0000005","completion":"0.00000215","input_cache_read":"0.00000035"},"top_provider":{"context_length":163840,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-r1-0528/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1155,"win_rate":53.3,"rank":66},{"arena":"models","category":"codecategories","elo":1163,"win_rate":52.6,"rank":72},{"arena":"models","category":"dataviz","elo":1202,"win_rate":60.9,"rank":49},{"arena":"models","category":"gamedev","elo":1133,"win_rate":49.3,"rank":76},{"arena":"models","category":"svg","elo":1078,"win_rate":48.7,"rank":61},{"arena":"models","category":"uicomponent","elo":1129,"win_rate":54.9,"rank":75},{"arena":"models","category":"website","elo":1169,"win_rate":52.7,"rank":71}]},"reasoning":{"mandatory":true},"_prompt_per_m":5e-07,"_completion_per_m":2.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | deepseek/deepseek-r1-0528","model_id":"deepseek/deepseek-r1-0528","model_name":"DeepSeek: R1 0528","context_length":163840,"pricing":{"prompt":"0.0000005","completion":"0.00000215","input_cache_read":"0.00000035","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.91638795986621,"uptime_last_5m":100,"uptime_last_1d":99.96836587129428,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":2.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-r1-0528","model_id":"deepseek/deepseek-r1-0528","model_name":"DeepSeek: R1 0528","context_length":163840,"pricing":{"prompt":"0.0000005","completion":"0.00000218","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.66582064297799,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":2.18e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"StreamLake | deepseek/deepseek-r1-0528","model_id":"deepseek/deepseek-r1-0528","model_name":"DeepSeek: R1 0528","context_length":128000,"pricing":{"prompt":"0.000000571","completion":"0.000002286","discount":0},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9744408945687,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.71e-07,"_completion_per_m":2.286e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | deepseek/deepseek-r1-0528","model_id":"deepseek/deepseek-r1-0528","model_name":"DeepSeek: R1 0528","context_length":163840,"pricing":{"prompt":"0.0000007","completion":"0.0000025","input_cache_read":"0.00000035","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":97.79735682819384,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":9.95e-07,"_priciest_blended_per_m":1.24e-06,"_provider_spread_multiplier":1.2462311557788945},{"id":"anthropic/claude-opus-4","canonical_slug":"anthropic/claude-4-opus-20250522","hugging_face_id":"","name":"Anthropic: Claude Opus 4","created":1747931245,"description":"Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0.000075","web_search":"0.01","input_cache_read":"0.0000015","input_cache_write":"0.00001875","input_cache_write_1h":"0.00003"},"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4-opus-20250522/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1183,"win_rate":57.7,"rank":54},{"arena":"models","category":"codecategories","elo":1185,"win_rate":55.6,"rank":64},{"arena":"models","category":"dataviz","elo":1166,"win_rate":57.9,"rank":66},{"arena":"models","category":"gamedev","elo":1206,"win_rate":59.9,"rank":48},{"arena":"models","category":"svg","elo":1167,"win_rate":57.7,"rank":45},{"arena":"models","category":"uicomponent","elo":1179,"win_rate":59.2,"rank":62},{"arena":"models","category":"website","elo":1185,"win_rate":54.6,"rank":65}]},"reasoning":{"mandatory":false},"_prompt_per_m":1.5e-05,"_completion_per_m":7.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-06,"_cached_write_per_m":1.875e-05,"_endpoints":[{"name":"Google | anthropic/claude-4-opus-20250522","model_id":"anthropic/claude-opus-4","model_name":"Anthropic: Claude Opus 4","context_length":200000,"pricing":{"prompt":"0.000015","completion":"0.000075","web_search":"0.01","input_cache_read":"0.0000015","input_cache_write":"0.00001875","input_cache_write_1h":"0.00003","discount":0},"provider_name":"Google","tag":"google-vertex","quantization":"unknown","max_completion_tokens":32000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-05,"_completion_per_m":7.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.5e-06,"_cached_write_per_m":1.875e-05}],"_cheapest_provider":"Google","_cheapest_blended_per_m":3.2999999999999996e-05,"_priciest_blended_per_m":3.2999999999999996e-05,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-sonnet-4","canonical_slug":"anthropic/claude-4-sonnet-20250522","hugging_face_id":"","name":"Anthropic: Claude Sonnet 4","created":1747930371,"description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4-sonnet-20250522/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1183,"win_rate":57.8,"rank":55},{"arena":"models","category":"codecategories","elo":1166,"win_rate":53.4,"rank":70},{"arena":"models","category":"dataviz","elo":1178,"win_rate":56.5,"rank":63},{"arena":"models","category":"gamedev","elo":1175,"win_rate":54.8,"rank":60},{"arena":"models","category":"svg","elo":1118,"win_rate":51.1,"rank":55},{"arena":"models","category":"uicomponent","elo":1155,"win_rate":57.9,"rank":70},{"arena":"models","category":"website","elo":1166,"win_rate":52.4,"rank":72}],"artificial_analysis":{"intelligence_index":29.8,"coding_index":37.6,"agentic_index":17.6}},"reasoning":{"mandatory":false},"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06,"_endpoints":[{"name":"Google | anthropic/claude-4-sonnet-20250522","model_id":"anthropic/claude-sonnet-4","model_name":"Anthropic: Claude Sonnet 4","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99640869096785,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Google | anthropic/claude-4-sonnet-20250522","model_id":"anthropic/claude-sonnet-4","model_name":"Anthropic: Claude Sonnet 4","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"provider_name":"Google","tag":"google-vertex","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Amazon Bedrock | anthropic/claude-4-sonnet-20250522","model_id":"anthropic/claude-sonnet-4","model_name":"Anthropic: Claude Sonnet 4","context_length":200000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Google | anthropic/claude-4-sonnet-20250522","model_id":"anthropic/claude-sonnet-4","model_name":"Anthropic: Claude Sonnet 4","context_length":1000000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"provider_name":"Google","tag":"google-vertex/europe","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06},{"name":"Amazon Bedrock | anthropic/claude-4-sonnet-20250522","model_id":"anthropic/claude-sonnet-4","model_name":"Anthropic: Claude Sonnet 4","context_length":200000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}]},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.94542974079127,"uptime_last_5m":99.77116704805492,"uptime_last_1d":99.96234827473086,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-07,"_cached_write_per_m":3.75e-06}],"_cheapest_provider":"Google","_cheapest_blended_per_m":6.5999999999999995e-06,"_priciest_blended_per_m":6.5999999999999995e-06,"_provider_spread_multiplier":1.0},{"id":"google/gemini-2.5-pro:batch","canonical_slug":"google/gemini-2.5-pro","hugging_face_id":"","name":"Google: Gemini 2.5 Pro (batch)","created":1750169544,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","audio":"0.000000625","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.000005","input_cache_read":"0.000000125","overrides":[{"min_prompt_tokens":200000,"prompt":"0.00000125","completion":"0.0000075","audio":"0.00000125","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-pro/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1124,"win_rate":50.6,"rank":79},{"arena":"models","category":"codecategories","elo":1177,"win_rate":57.5,"rank":66},{"arena":"models","category":"dataviz","elo":1242,"win_rate":68.2,"rank":34},{"arena":"models","category":"gamedev","elo":1147,"win_rate":54.2,"rank":71},{"arena":"models","category":"uicomponent","elo":1166,"win_rate":57.5,"rank":66},{"arena":"models","category":"website","elo":1187,"win_rate":58.4,"rank":64}],"artificial_analysis":{"intelligence_index":25.9,"coding_index":33.3,"agentic_index":7.2}},"reasoning":{"mandatory":true},"_prompt_per_m":6.25e-07,"_completion_per_m":5e-06,"_image_per_m":6.25e-07,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Google | google/gemini-2.5-pro:batch","model_id":"google/gemini-2.5-pro:batch","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","audio":"0.000000625","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.000005","input_cache_read":"0.000000125","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.00000125","completion":"0.0000075","audio":"0.00000125","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.25e-07,"_completion_per_m":5e-06,"_image_per_m":6.25e-07,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Google","_cheapest_blended_per_m":1.9375e-06,"_priciest_blended_per_m":1.9375e-06,"_provider_spread_multiplier":1.0},{"id":"meta-llama/llama-guard-4-12b","canonical_slug":"meta-llama/llama-guard-4-12b","hugging_face_id":"meta-llama/Llama-Guard-4-12B","name":"Meta: Llama Guard 4 12B","created":1745975193,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","context_length":163840,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000018","completion":"0.00000018"},"top_provider":{"context_length":163840,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-guard-4-12b/endpoints"},"_prompt_per_m":1.8e-07,"_completion_per_m":1.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | meta-llama/llama-guard-4-12b","model_id":"meta-llama/llama-guard-4-12b","model_name":"Meta: Llama Guard 4 12B","context_length":163840,"pricing":{"prompt":"0.00000018","completion":"0.00000018","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.8e-07,"_completion_per_m":1.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.7999999999999997e-07,"_priciest_blended_per_m":1.7999999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-medium-3","canonical_slug":"mistralai/mistral-medium-3","hugging_face_id":"","name":"Mistral: Mistral Medium 3","created":1746627341,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004"},"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-medium-3/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1127,"win_rate":54.7,"rank":76},{"arena":"models","category":"codecategories","elo":1093,"win_rate":48.1,"rank":93},{"arena":"models","category":"dataviz","elo":1054,"win_rate":46,"rank":96},{"arena":"models","category":"gamedev","elo":1054,"win_rate":45.2,"rank":98},{"arena":"models","category":"uicomponent","elo":1051,"win_rate":49.6,"rank":93},{"arena":"models","category":"website","elo":1099,"win_rate":47.6,"rank":96}]},"_prompt_per_m":4e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-medium-3","model_id":"mistralai/mistral-medium-3","model_name":"Mistral: Mistral Medium 3","context_length":131072,"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":98.57514418183875,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-medium-3","model_id":"mistralai/mistral-medium-3","model_name":"Mistral: Mistral Medium 3","context_length":131072,"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":98.6493860845839,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-medium-3","model_id":"mistralai/mistral-medium-3","model_name":"Mistral: Mistral Medium 3","context_length":131072,"pricing":{"prompt":"0.00000044","completion":"0.0000022","input_cache_read":"0.000000044","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":2.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4.4e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":8.799999999999999e-07,"_priciest_blended_per_m":9.68e-07,"_provider_spread_multiplier":1.1},{"id":"qwen/qwen3-8b","canonical_slug":"qwen/qwen3-8b-04-28","hugging_face_id":"Qwen/Qwen3-8B","name":"Qwen: Qwen3 8B","created":1745876632,"description":"Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.000000117","completion":"0.000000455"},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-8b-04-28/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":8.3,"coding_index":9,"agentic_index":1.6}},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":1.17e-07,"_completion_per_m":4.55e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-8b-04-28","model_id":"qwen/qwen3-8b","model_name":"Qwen: Qwen3 8B","context_length":131072,"pricing":{"prompt":"0.000000117","completion":"0.000000455","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":98304,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.70045474272129,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.17e-07,"_completion_per_m":4.55e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":2.184e-07,"_priciest_blended_per_m":2.184e-07,"_provider_spread_multiplier":1.0},{"id":"arcee-ai/virtuoso-large","canonical_slug":"arcee-ai/virtuoso-large","hugging_face_id":"","name":"Arcee AI: Virtuoso Large","created":1746478885,"description":"Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.0000012"},"top_provider":{"context_length":131072,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/arcee-ai/virtuoso-large/endpoints"},"_prompt_per_m":7.5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Together | arcee-ai/virtuoso-large","model_id":"arcee-ai/virtuoso-large","model_name":"Arcee AI: Virtuoso Large","context_length":131072,"pricing":{"prompt":"0.00000075","completion":"0.0000012","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.5e-07,"_completion_per_m":1.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Together","_cheapest_blended_per_m":8.85e-07,"_priciest_blended_per_m":8.85e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-30b-a3b","canonical_slug":"qwen/qwen3-30b-a3b-04-28","hugging_face_id":"Qwen/Qwen3-30B-A3B","name":"Qwen: Qwen3 30B A3B","created":1745878604,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000012","completion":"0.0000005"},"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-30b-a3b-04-28/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":966,"win_rate":37.5,"rank":115},{"arena":"models","category":"dataviz","elo":985,"win_rate":39,"rank":105},{"arena":"models","category":"gamedev","elo":935,"win_rate":33.9,"rank":116},{"arena":"models","category":"uicomponent","elo":972,"win_rate":42.4,"rank":105},{"arena":"models","category":"website","elo":974,"win_rate":37.7,"rank":116}]},"reasoning":{"mandatory":false,"default_enabled":true},"_prompt_per_m":1.2e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | qwen/qwen3-30b-a3b-04-28","model_id":"qwen/qwen3-30b-a3b","model_name":"Qwen: Qwen3 30B A3B","context_length":40960,"pricing":{"prompt":"0.00000012","completion":"0.0000005","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.95840698762608,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.2e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3-30b-a3b-04-28","model_id":"qwen/qwen3-30b-a3b","model_name":"Qwen: Qwen3 30B A3B","context_length":131072,"pricing":{"prompt":"0.00000013","completion":"0.00000052","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":98304,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99652978600348,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":5.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":2.3399999999999998e-07,"_priciest_blended_per_m":2.47e-07,"_provider_spread_multiplier":1.0555555555555556},{"id":"qwen/qwen3-14b","canonical_slug":"qwen/qwen3-14b-04-28","hugging_face_id":"Qwen/Qwen3-14B","name":"Qwen: Qwen3 14B","created":1745876478,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000012","completion":"0.00000024"},"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-14b-04-28/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":10.4,"coding_index":13.8,"agentic_index":1.9}},"reasoning":{"mandatory":false},"_prompt_per_m":1.2e-07,"_completion_per_m":2.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"NextBit | qwen/qwen3-14b-04-28","model_id":"qwen/qwen3-14b","model_name":"Qwen: Qwen3 14B","context_length":40960,"pricing":{"prompt":"0.0000001","completion":"0.00000022","discount":0},"provider_name":"NextBit","tag":"nextbit/int4","quantization":"int4","max_completion_tokens":36864,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.53666204083945,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":2.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | qwen/qwen3-14b-04-28","model_id":"qwen/qwen3-14b","model_name":"Qwen: Qwen3 14B","context_length":40960,"pricing":{"prompt":"0.00000012","completion":"0.00000024","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.23896499238964,"uptime_last_5m":95.16728624535315,"uptime_last_1d":98.1259097525473,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.2e-07,"_completion_per_m":2.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Alibaba | qwen/qwen3-14b-04-28","model_id":"qwen/qwen3-14b","model_name":"Qwen: Qwen3 14B","context_length":131072,"pricing":{"prompt":"0.0000002275","completion":"0.00000091","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":98304,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99780514036128,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.275e-07,"_completion_per_m":9.1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"NextBit","_cheapest_blended_per_m":1.36e-07,"_priciest_blended_per_m":4.3224999999999997e-07,"_provider_spread_multiplier":3.1783088235294117},{"id":"google/gemini-2.5-pro-preview-05-06","canonical_slug":"google/gemini-2.5-pro-preview-03-25","hugging_face_id":"","name":"Google: Gemini 2.5 Pro Preview 05-06","created":1746578513,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-pro-preview-03-25/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07,"_endpoints":[{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/global","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.56505645012031,"uptime_last_5m":99.77912755383765,"uptime_last_1d":99.50885187737619,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","audio":"0.000000625","input_audio_cache":"0.0000000625","web_search":"0.014","internal_reasoning":"0.000005","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.00000125","completion":"0.0000075","audio":"0.00000125","input_audio_cache":"0.000000125","input_cache_read":"0.000000125"}]},"provider_name":"Google","tag":"google-vertex/global/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.56505645012031,"uptime_last_5m":99.77912755383765,"uptime_last_1d":99.50885187737619,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.25e-07,"_completion_per_m":5e-06,"_image_per_m":6.25e-07,"_request_per_m":null,"_cached_read_per_m":6.25e-08,"_cached_write_per_m":1.875e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000225","completion":"0.000018","image":"0.00000225","audio":"0.00000225","input_audio_cache":"0.000000225","web_search":"0.014","internal_reasoning":"0.000018","input_cache_read":"0.000000225","input_cache_write":"0.000000675","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000045","completion":"0.000027","audio":"0.0000045","input_audio_cache":"0.00000045","input_cache_read":"0.00000045"}]},"provider_name":"Google","tag":"google-vertex/global/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.56505645012031,"uptime_last_5m":99.77912755383765,"uptime_last_1d":99.50885187737619,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.25e-06,"_completion_per_m":1.8e-05,"_image_per_m":2.25e-06,"_request_per_m":null,"_cached_read_per_m":2.25e-07,"_cached_write_per_m":6.75e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/us","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":63.67713004484305,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google","tag":"google-vertex/eu","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":65.45632973503434,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google AI Studio | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.000000125","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":92.8709055876686,"uptime_last_5m":91.17647058823529,"uptime_last_1d":96.29248621512633,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.25e-06,"_completion_per_m":1e-05,"_image_per_m":1.25e-06,"_request_per_m":null,"_cached_read_per_m":1.25e-07,"_cached_write_per_m":3.75e-07},{"name":"Google AI Studio | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","audio":"0.000000625","input_audio_cache":"0.0000000625","web_search":"0.014","internal_reasoning":"0.000005","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.00000125","completion":"0.0000075","audio":"0.00000125","input_audio_cache":"0.000000125","input_cache_read":"0.000000125"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio/flex","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":92.8709055876686,"uptime_last_5m":91.17647058823529,"uptime_last_1d":96.29248621512633,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.25e-07,"_completion_per_m":5e-06,"_image_per_m":6.25e-07,"_request_per_m":null,"_cached_read_per_m":6.25e-08,"_cached_write_per_m":1.875e-07},{"name":"Google AI Studio | google/gemini-2.5-pro","model_id":"google/gemini-2.5-pro","model_name":"Google: Gemini 2.5 Pro","context_length":1048576,"pricing":{"prompt":"0.00000225","completion":"0.000018","image":"0.00000225","audio":"0.00000225","input_audio_cache":"0.000000225","web_search":"0.014","internal_reasoning":"0.000018","input_cache_read":"0.000000225","input_cache_write":"0.000000675","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000045","completion":"0.000027","audio":"0.0000045","input_audio_cache":"0.00000045","input_cache_read":"0.00000045"}]},"provider_name":"Google AI Studio","tag":"google-ai-studio/priority","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":92.8709055876686,"uptime_last_5m":91.17647058823529,"uptime_last_1d":96.29248621512633,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.25e-06,"_completion_per_m":1.8e-05,"_image_per_m":2.25e-06,"_request_per_m":null,"_cached_read_per_m":2.25e-07,"_cached_write_per_m":6.75e-07}],"_cheapest_provider":"Google","_cheapest_blended_per_m":1.9375e-06,"_priciest_blended_per_m":6.975e-06,"_provider_spread_multiplier":3.6},{"id":"qwen/qwen3-235b-a22b","canonical_slug":"qwen/qwen3-235b-a22b-04-28","hugging_face_id":"Qwen/Qwen3-235B-A22B","name":"Qwen: Qwen3 235B A22B","created":1745875757,"description":"Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.000000455","completion":"0.00000182"},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-235b-a22b-04-28/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":902,"win_rate":24.5,"rank":108},{"arena":"models","category":"codecategories","elo":1026,"win_rate":38.2,"rank":107},{"arena":"models","category":"dataviz","elo":1016,"win_rate":40,"rank":101},{"arena":"models","category":"gamedev","elo":964,"win_rate":32.9,"rank":112},{"arena":"models","category":"uicomponent","elo":985,"win_rate":38.6,"rank":104},{"arena":"models","category":"website","elo":1050,"win_rate":40.4,"rank":105}]},"reasoning":{"mandatory":false},"_prompt_per_m":4.55e-07,"_completion_per_m":1.82e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Alibaba | qwen/qwen3-235b-a22b-04-28","model_id":"qwen/qwen3-235b-a22b","model_name":"Qwen: Qwen3 235B A22B","context_length":131072,"pricing":{"prompt":"0.000000455","completion":"0.00000182","discount":0},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":98304,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.55e-07,"_completion_per_m":1.82e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":8.644999999999999e-07,"_priciest_blended_per_m":8.644999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-4.1","canonical_slug":"openai/gpt-4.1-2025-04-14","hugging_face_id":"","name":"OpenAI: GPT-4.1","created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.01","input_cache_read":"0.0000005"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":893,"win_rate":30.9,"rank":110},{"arena":"models","category":"codecategories","elo":1050,"win_rate":50.9,"rank":101},{"arena":"models","category":"dataviz","elo":1123,"win_rate":59.5,"rank":81},{"arena":"models","category":"gamedev","elo":1116,"win_rate":59.1,"rank":83},{"arena":"models","category":"uicomponent","elo":1026,"win_rate":49.7,"rank":99},{"arena":"models","category":"website","elo":1058,"win_rate":52.3,"rank":102}]},"_prompt_per_m":2e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-4.1-2025-04-14","model_id":"openai/gpt-4.1","model_name":"OpenAI: GPT-4.1","context_length":1047576,"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.01","input_cache_read":"0.0000005","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.83484723369116,"uptime_last_5m":99.72200158856235,"uptime_last_1d":99.84492036069923,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-4.1-2025-04-14","model_id":"openai/gpt-4.1","model_name":"OpenAI: GPT-4.1","context_length":1047576,"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.01","input_cache_read":"0.0000005","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":942818,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","seed","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9887904943392,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-4.1-2025-04-14","model_id":"openai/gpt-4.1","model_name":"OpenAI: GPT-4.1","context_length":1047576,"pricing":{"prompt":"0.0000022","completion":"0.0000088","web_search":"0.01","input_cache_read":"0.00000055","discount":0},"provider_name":"Azure","tag":"azure/swedencentral","quantization":"unknown","max_completion_tokens":942818,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","seed","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":8.8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":3.8e-06,"_priciest_blended_per_m":4.180000000000001e-06,"_provider_spread_multiplier":1.1},{"id":"openai/o4-mini-high","canonical_slug":"openai/o4-mini-high-2025-04-16","hugging_face_id":"","name":"OpenAI: o4 Mini High","created":1744824212,"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000011","completion":"0.0000044","web_search":"0.01","input_cache_read":"0.000000275"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/o4-mini-high-2025-04-16/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["high"],"default_effort":"high"},"_prompt_per_m":1.1e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.75e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/o4-mini-high-2025-04-16","model_id":"openai/o4-mini-high","model_name":"OpenAI: o4 Mini High","context_length":200000,"pricing":{"prompt":"0.0000011","completion":"0.0000044","web_search":"0.01","input_cache_read":"0.000000275","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":100000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.75e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.0900000000000003e-06,"_priciest_blended_per_m":2.0900000000000003e-06,"_provider_spread_multiplier":1.0},{"id":"openai/o4-mini","canonical_slug":"openai/o4-mini-2025-04-16","hugging_face_id":"","name":"OpenAI: o4 Mini","created":1744820942,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000011","completion":"0.0000044","web_search":"0.01","input_cache_read":"0.000000275"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/o4-mini-2025-04-16/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":897,"win_rate":34,"rank":109},{"arena":"models","category":"codecategories","elo":1000,"win_rate":46.4,"rank":110},{"arena":"models","category":"dataviz","elo":1010,"win_rate":50,"rank":102},{"arena":"models","category":"gamedev","elo":1039,"win_rate":50,"rank":100},{"arena":"models","category":"uicomponent","elo":1009,"win_rate":46.9,"rank":100},{"arena":"models","category":"website","elo":1005,"win_rate":47.1,"rank":112}]},"reasoning":{"mandatory":false},"_prompt_per_m":1.1e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.75e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/o4-mini-2025-04-16","model_id":"openai/o4-mini","model_name":"OpenAI: o4 Mini","context_length":200000,"pricing":{"prompt":"0.0000011","completion":"0.0000044","web_search":"0.01","input_cache_read":"0.000000275","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":100000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.75e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.0900000000000003e-06,"_priciest_blended_per_m":2.0900000000000003e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen3-32b","canonical_slug":"qwen/qwen3-32b-04-28","hugging_face_id":"Qwen/Qwen3-32B","name":"Qwen: Qwen3 32B","created":1745875945,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000008","completion":"0.00000028"},"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-32b-04-28/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":11.4,"coding_index":15.3,"agentic_index":1.8}},"reasoning":{"mandatory":false},"_prompt_per_m":8e-08,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | qwen/qwen3-32b-04-28","model_id":"qwen/qwen3-32b","model_name":"Qwen: Qwen3 32B","context_length":40960,"pricing":{"prompt":"0.00000008","completion":"0.00000028","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.99521405154466,"uptime_last_5m":100,"uptime_last_1d":99.44673711198236,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-08,"_completion_per_m":2.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Nebius | qwen/qwen3-32b-04-28","model_id":"qwen/qwen3-32b","model_name":"Qwen: Qwen3 32B","context_length":40960,"pricing":{"prompt":"0.0000001","completion":"0.0000003","discount":0},"provider_name":"Nebius","tag":"nebius/base","quantization":"fp8","max_completion_tokens":36864,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.63820549927641,"uptime_last_5m":98.84726224783861,"uptime_last_1d":96.6289283137177,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SiliconFlow | qwen/qwen3-32b-04-28","model_id":"qwen/qwen3-32b","model_name":"Qwen: Qwen3 32B","context_length":131072,"pricing":{"prompt":"0.00000014","completion":"0.00000057","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":99.54188481675392,"uptime_last_5m":100,"uptime_last_1d":93.70374096376885,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4e-07,"_completion_per_m":5.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Groq | qwen/qwen3-32b-04-28","model_id":"qwen/qwen3-32b","model_name":"Qwen: Qwen3 32B","context_length":131072,"pricing":{"prompt":"0.00000029","completion":"0.00000059","input_cache_read":"0.000000145","discount":0},"provider_name":"Groq","tag":"groq","quantization":"unknown","max_completion_tokens":40960,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98729571048739,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.9e-07,"_completion_per_m":5.9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.45e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.3999999999999998e-07,"_priciest_blended_per_m":3.7999999999999996e-07,"_provider_spread_multiplier":2.7142857142857144},{"id":"openai/o3","canonical_slug":"openai/o3-2025-04-16","hugging_face_id":"","name":"OpenAI: o3","created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.01","input_cache_read":"0.0000005"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/o3-2025-04-16/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1044,"win_rate":51.9,"rank":103},{"arena":"models","category":"dataviz","elo":1200,"win_rate":48.1,"rank":50},{"arena":"models","category":"gamedev","elo":1070,"win_rate":56.9,"rank":94},{"arena":"models","category":"uicomponent","elo":1043,"win_rate":53.3,"rank":96},{"arena":"models","category":"website","elo":1056,"win_rate":53.8,"rank":103}]},"reasoning":{"mandatory":false},"_prompt_per_m":2e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/o3-2025-04-16","model_id":"openai/o3","model_name":"OpenAI: o3","context_length":200000,"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.01","input_cache_read":"0.0000005","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":100000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":3.8e-06,"_priciest_blended_per_m":3.8e-06,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-4.1-mini","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","hugging_face_id":"","name":"OpenAI: GPT-4.1 Mini","created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.0000016","web_search":"0.01","input_cache_read":"0.0000001"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4.1-mini-2025-04-14/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":880,"win_rate":30.5,"rank":111},{"arena":"models","category":"codecategories","elo":1018,"win_rate":47.5,"rank":109},{"arena":"models","category":"dataviz","elo":1053,"win_rate":49.2,"rank":97},{"arena":"models","category":"gamedev","elo":1107,"win_rate":58.5,"rank":87},{"arena":"models","category":"uicomponent","elo":987,"win_rate":45.4,"rank":103},{"arena":"models","category":"website","elo":1017,"win_rate":47.8,"rank":111}],"artificial_analysis":{"intelligence_index":14.8,"coding_index":20.2,"agentic_index":1.8}},"_prompt_per_m":4e-07,"_completion_per_m":1.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-4.1-mini-2025-04-14","model_id":"openai/gpt-4.1-mini","model_name":"OpenAI: GPT-4.1 Mini","context_length":1047576,"pricing":{"prompt":"0.0000004","completion":"0.0000016","web_search":"0.01","input_cache_read":"0.0000001","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":942818,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","seed","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.96349032493612,"uptime_last_5m":99.87468671679198,"uptime_last_1d":99.97742572194278,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":1.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-4.1-mini-2025-04-14","model_id":"openai/gpt-4.1-mini","model_name":"OpenAI: GPT-4.1 Mini","context_length":1047576,"pricing":{"prompt":"0.0000004","completion":"0.0000016","web_search":"0.01","input_cache_read":"0.0000001","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.32638729867949,"uptime_last_5m":98.71061778226259,"uptime_last_1d":99.48369826137153,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":1.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-4.1-mini-2025-04-14","model_id":"openai/gpt-4.1-mini","model_name":"OpenAI: GPT-4.1 Mini","context_length":1047576,"pricing":{"prompt":"0.00000044","completion":"0.00000176","web_search":"0.01","input_cache_read":"0.00000011","discount":0},"provider_name":"Azure","tag":"azure/swedencentral","quantization":"unknown","max_completion_tokens":942818,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","seed","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-07,"_completion_per_m":1.76e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":7.599999999999999e-07,"_priciest_blended_per_m":8.359999999999999e-07,"_provider_spread_multiplier":1.1},{"id":"openai/gpt-4.1-nano","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","hugging_face_id":"","name":"OpenAI: GPT-4.1 Nano","created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000004","web_search":"0.01","input_cache_read":"0.000000025"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4.1-nano-2025-04-14/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":969,"win_rate":46,"rank":104},{"arena":"models","category":"codecategories","elo":987,"win_rate":47.3,"rank":111},{"arena":"models","category":"dataviz","elo":910,"win_rate":41.1,"rank":114},{"arena":"models","category":"gamedev","elo":1007,"win_rate":49.6,"rank":107},{"arena":"models","category":"uicomponent","elo":942,"win_rate":43.9,"rank":109},{"arena":"models","category":"website","elo":993,"win_rate":48.1,"rank":113}],"artificial_analysis":{"intelligence_index":9.6,"coding_index":11.1,"agentic_index":1.2}},"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-4.1-nano-2025-04-14","model_id":"openai/gpt-4.1-nano","model_name":"OpenAI: GPT-4.1 Nano","context_length":1047576,"pricing":{"prompt":"0.0000001","completion":"0.0000004","web_search":"0.01","input_cache_read":"0.00000003","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":942818,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","seed","response_format","structured_outputs","tool_choice","tools","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97745716862038,"uptime_last_5m":100,"uptime_last_1d":99.97792232842744,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-4.1-nano-2025-04-14","model_id":"openai/gpt-4.1-nano","model_name":"OpenAI: GPT-4.1 Nano","context_length":1047576,"pricing":{"prompt":"0.0000001","completion":"0.0000004","web_search":"0.01","input_cache_read":"0.000000025","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.99491997596547,"uptime_last_5m":98.94701086956522,"uptime_last_1d":99.36584148744451,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-4.1-nano-2025-04-14","model_id":"openai/gpt-4.1-nano","model_name":"OpenAI: GPT-4.1 Nano","context_length":1047576,"pricing":{"prompt":"0.00000011","completion":"0.00000044","web_search":"0.01","input_cache_read":"0.000000033","discount":0},"provider_name":"Azure","tag":"azure/swedencentral","quantization":"unknown","max_completion_tokens":942818,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","seed","response_format","structured_outputs","tool_choice","tools","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":true,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-07,"_completion_per_m":4.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3.3e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":1.8999999999999998e-07,"_priciest_blended_per_m":2.0899999999999998e-07,"_provider_spread_multiplier":1.1},{"id":"meta-llama/llama-4-maverick","canonical_slug":"meta-llama/llama-4-maverick-17b-128e-instruct","hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","name":"Meta: Llama 4 Maverick","created":1743881822,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000008"},"top_provider":{"context_length":1048576,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-4-maverick-17b-128e-instruct/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":944,"win_rate":40.2,"rank":106},{"arena":"models","category":"codecategories","elo":904,"win_rate":35.8,"rank":118},{"arena":"models","category":"dataviz","elo":901,"win_rate":38.4,"rank":115},{"arena":"models","category":"gamedev","elo":874,"win_rate":33.7,"rank":118},{"arena":"models","category":"uicomponent","elo":925,"win_rate":40.8,"rank":111},{"arena":"models","category":"website","elo":891,"win_rate":34.4,"rank":121}],"artificial_analysis":{"intelligence_index":14.5,"coding_index":16.3,"agentic_index":1.2}},"_prompt_per_m":2e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | meta-llama/llama-4-maverick-17b-128e-instruct","model_id":"meta-llama/llama-4-maverick","model_name":"Meta: Llama 4 Maverick","context_length":1048576,"pricing":{"prompt":"0.0000002","completion":"0.0000008","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/base","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.82259466006636,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DigitalOcean | meta-llama/llama-4-maverick-17b-128e-instruct","model_id":"meta-llama/llama-4-maverick","model_name":"Meta: Llama 4 Maverick","context_length":128000,"pricing":{"prompt":"0.00000025","completion":"0.00000087","discount":0},"provider_name":"DigitalOcean","tag":"digitalocean","quantization":"unknown","max_completion_tokens":115200,"max_prompt_tokens":null,"supported_parameters":["temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.67002431399791,"uptime_last_5m":100,"uptime_last_1d":99.84592902811237,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":8.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | meta-llama/llama-4-maverick-17b-128e-instruct","model_id":"meta-llama/llama-4-maverick","model_name":"Meta: Llama 4 Maverick","context_length":1048576,"pricing":{"prompt":"0.00000027","completion":"0.00000085","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","structured_outputs","response_format"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":98.93845269313289,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":8.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | meta-llama/llama-4-maverick-17b-128e-instruct","model_id":"meta-llama/llama-4-maverick","model_name":"Meta: Llama 4 Maverick","context_length":524288,"pricing":{"prompt":"0.00000035","completion":"0.000001","input_cache_read":"0.00000017","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.92272820935504,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.7e-07,"_cached_write_per_m":null},{"name":"Google | meta-llama/llama-4-maverick-17b-128e-instruct","model_id":"meta-llama/llama-4-maverick","model_name":"Meta: Llama 4 Maverick","context_length":524288,"pricing":{"prompt":"0.00000035","completion":"0.00000115","discount":0},"provider_name":"Google","tag":"google-vertex/us-east5","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","frequency_penalty","presence_penalty","stop","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.84768599882835,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-07,"_completion_per_m":1.15e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":3.7999999999999996e-07,"_priciest_blended_per_m":5.9e-07,"_provider_spread_multiplier":1.5526315789473686},{"id":"mistralai/mistral-small-3.1-24b-instruct","canonical_slug":"mistralai/mistral-small-3.1-24b-instruct-2503","hugging_face_id":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","name":"Mistral: Mistral Small 3.1 24B","created":1742238937,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000000351","completion":"0.000000555"},"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-3.1-24b-instruct-2503/endpoints"},"_prompt_per_m":3.51e-07,"_completion_per_m":5.55e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Cloudflare | mistralai/mistral-small-3.1-24b-instruct-2503","model_id":"mistralai/mistral-small-3.1-24b-instruct","model_name":"Mistral: Mistral Small 3.1 24B","context_length":128000,"pricing":{"prompt":"0.000000351","completion":"0.000000555","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":102400,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.51e-07,"_completion_per_m":5.55e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Cloudflare","_cheapest_blended_per_m":4.1219999999999995e-07,"_priciest_blended_per_m":4.1219999999999995e-07,"_provider_spread_multiplier":1.0},{"id":"deepseek/deepseek-chat-v3-0324","canonical_slug":"deepseek/deepseek-chat-v3-0324","hugging_face_id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek: DeepSeek V3 0324","created":1742824755,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000001"},"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-07-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-chat-v3-0324/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":15.2,"coding_index":21.2,"agentic_index":1.6}},"_prompt_per_m":2.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | deepseek/deepseek-chat-v3-0324","model_id":"deepseek/deepseek-chat-v3-0324","model_name":"DeepSeek: DeepSeek V3 0324","context_length":163840,"pricing":{"prompt":"0.00000024","completion":"0.0000009","input_cache_read":"0.000000135","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":-2,"uptime_last_30m":94.79432107753914,"uptime_last_5m":98.51116625310173,"uptime_last_1d":90.8744198869641,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.4e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":null},{"name":"SiliconFlow | deepseek/deepseek-chat-v3-0324","model_id":"deepseek/deepseek-chat-v3-0324","model_name":"DeepSeek: DeepSeek V3 0324","context_length":163840,"pricing":{"prompt":"0.00000025","completion":"0.000001","discount":0},"provider_name":"SiliconFlow","tag":"siliconflow/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":96.9610636277303,"uptime_last_5m":94.32937181663837,"uptime_last_1d":97.91863155736505,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | deepseek/deepseek-chat-v3-0324","model_id":"deepseek/deepseek-chat-v3-0324","model_name":"DeepSeek: DeepSeek V3 0324","context_length":163840,"pricing":{"prompt":"0.00000027","completion":"0.00000112","input_cache_read":"0.000000135","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.2842535787321,"uptime_last_5m":98.87640449438202,"uptime_last_1d":97.85678158981707,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-07,"_completion_per_m":1.12e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.35e-07,"_cached_write_per_m":null},{"name":"GMICloud | deepseek/deepseek-chat-v3-0324","model_id":"deepseek/deepseek-chat-v3-0324","model_name":"DeepSeek: DeepSeek V3 0324","context_length":163840,"pricing":{"prompt":"0.00000029","completion":"0.00000114","input_cache_read":"0.00000011","discount":0},"provider_name":"GMICloud","tag":"gmicloud/fp8","quantization":"fp8","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":83.16831683168317,"uptime_last_5m":84.68468468468468,"uptime_last_1d":84.82615703430808,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.9e-07,"_completion_per_m":1.14e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null},{"name":"Crusoe | deepseek/deepseek-chat-v3-0324","model_id":"deepseek/deepseek-chat-v3-0324","model_name":"DeepSeek: DeepSeek V3 0324","context_length":163840,"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000025","discount":0},"provider_name":"Crusoe","tag":"crusoe/bf16","quantization":"bf16","max_completion_tokens":147456,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97266265718973,"uptime_last_5m":100,"uptime_last_1d":99.69640639332418,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":4.379999999999999e-07,"_priciest_blended_per_m":8e-07,"_provider_spread_multiplier":1.8264840182648403},{"id":"google/gemma-3-12b-it","canonical_slug":"google/gemma-3-12b-it","hugging_face_id":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","created":1741902625,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000005","completion":"0.00000015"},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-3-12b-it/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":5.5,"coding_index":5.8,"agentic_index":0.3}},"_prompt_per_m":5e-08,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | google/gemma-3-12b-it","model_id":"google/gemma-3-12b-it","model_name":"Google: Gemma 3 12B","context_length":131072,"pricing":{"prompt":"0.00000005","completion":"0.00000015","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98350379412734,"uptime_last_5m":100,"uptime_last_1d":99.9916123387431,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":8e-08,"_priciest_blended_per_m":8e-08,"_provider_spread_multiplier":1.0},{"id":"meta-llama/llama-4-scout","canonical_slug":"meta-llama/llama-4-scout-17b-16e-instruct","hugging_face_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","name":"Meta: Llama 4 Scout","created":1743881519,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","context_length":1310720,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":"0.00000011","completion":"0.00000034","input_cache_read":"0.000000055"},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-4-scout-17b-16e-instruct/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":814,"win_rate":26.6,"rank":121},{"arena":"models","category":"dataviz","elo":914,"win_rate":39.3,"rank":113},{"arena":"models","category":"gamedev","elo":809,"win_rate":27.4,"rank":120},{"arena":"models","category":"uicomponent","elo":794,"win_rate":25.5,"rank":116},{"arena":"models","category":"website","elo":770,"win_rate":22.7,"rank":127}],"artificial_analysis":{"intelligence_index":10.3,"coding_index":8.2,"agentic_index":1.1}},"_prompt_per_m":1.1e-07,"_completion_per_m":3.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | meta-llama/llama-4-scout-17b-16e-instruct","model_id":"meta-llama/llama-4-scout","model_name":"Meta: Llama 4 Scout","context_length":327680,"pricing":{"prompt":"0.0000001","completion":"0.0000003","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.97989141363362,"uptime_last_5m":100,"uptime_last_1d":99.9379935589785,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Groq | meta-llama/llama-4-scout-17b-16e-instruct","model_id":"meta-llama/llama-4-scout","model_name":"Meta: Llama 4 Scout","context_length":131072,"pricing":{"prompt":"0.00000011","completion":"0.00000034","input_cache_read":"0.000000055","discount":0},"provider_name":"Groq","tag":"groq","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.82652578457657,"uptime_last_5m":99.7340425531915,"uptime_last_1d":97.76050245033568,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-07,"_completion_per_m":3.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-08,"_cached_write_per_m":null},{"name":"Novita | meta-llama/llama-4-scout-17b-16e-instruct","model_id":"meta-llama/llama-4-scout","model_name":"Meta: Llama 4 Scout","context_length":131072,"pricing":{"prompt":"0.00000018","completion":"0.00000059","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":97.50205809714218,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.8e-07,"_completion_per_m":5.9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google | meta-llama/llama-4-scout-17b-16e-instruct","model_id":"meta-llama/llama-4-scout","model_name":"Meta: Llama 4 Scout","context_length":1310720,"pricing":{"prompt":"0.00000025","completion":"0.0000007","discount":0},"provider_name":"Google","tag":"google-vertex/us-east5","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","frequency_penalty","presence_penalty","stop","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.82174130597949,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.6e-07,"_priciest_blended_per_m":3.8499999999999997e-07,"_provider_spread_multiplier":2.4062499999999996},{"id":"google/gemma-3-4b-it","canonical_slug":"google/gemma-3-4b-it","hugging_face_id":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","created":1741905510,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000005","completion":"0.0000001"},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-3-4b-it/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":2.7,"agentic_index":null}},"_prompt_per_m":5e-08,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | google/gemma-3-4b-it","model_id":"google/gemma-3-4b-it","model_name":"Google: Gemma 3 4B","context_length":131072,"pricing":{"prompt":"0.00000005","completion":"0.0000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.92892679459844,"uptime_last_5m":100,"uptime_last_1d":99.85917301600891,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":6.499999999999999e-08,"_priciest_blended_per_m":6.499999999999999e-08,"_provider_spread_multiplier":1.0},{"id":"cohere/command-a","canonical_slug":"cohere/command-a-03-2025","hugging_face_id":"CohereForAI/c4ai-command-a-03-2025","name":"Cohere: Command A","created":1741894342,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001"},"top_provider":{"context_length":256000,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/cohere/command-a-03-2025/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":22.8,"coding_index":27.8,"agentic_index":9.2}},"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Cohere | cohere/command-a-03-2025","model_id":"cohere/command-a","model_name":"Cohere: Command A","context_length":256000,"pricing":{"prompt":"0.0000025","completion":"0.00001","discount":0},"provider_name":"Cohere","tag":"cohere","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.9896071502806,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Cohere","_cheapest_blended_per_m":4.75e-06,"_priciest_blended_per_m":4.75e-06,"_provider_spread_multiplier":1.0},{"id":"openai/o1-pro","canonical_slug":"openai/o1-pro","hugging_face_id":"","name":"OpenAI: o1-pro","created":1742423211,"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00015","completion":"0.0006","web_search":"0.01"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/o1-pro/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":0.00015,"_completion_per_m":0.0006,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/o1-pro","model_id":"openai/o1-pro","model_name":"OpenAI: o1-pro","context_length":200000,"pricing":{"prompt":"0.00015","completion":"0.0006","web_search":"0.01","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":100000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":0.00015,"_completion_per_m":0.0006,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":0.000285,"_priciest_blended_per_m":0.000285,"_provider_spread_multiplier":1.0},{"id":"rekaai/reka-flash-3","canonical_slug":"rekaai/reka-flash-3","hugging_face_id":"RekaAI/reka-flash-3","name":"Reka Flash 3","created":1741812813,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000002"},"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/rekaai/reka-flash-3/endpoints"},"reasoning":{"mandatory":true},"_prompt_per_m":1e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Reka | rekaai/reka-flash-3","model_id":"rekaai/reka-flash-3","model_name":"Reka Flash 3","context_length":65536,"pricing":{"prompt":"0.0000001","completion":"0.0000002","discount":0},"provider_name":"Reka","tag":"reka/fp8","quantization":"fp8","max_completion_tokens":58982,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Reka","_cheapest_blended_per_m":1.2999999999999997e-07,"_priciest_blended_per_m":1.2999999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"google/gemma-3-27b-it","canonical_slug":"google/gemma-3-27b-it","hugging_face_id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","created":1741756359,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000008","completion":"0.00000045","input_cache_read":"0.00000004"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-3-27b-it/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":7.4,"coding_index":10.1,"agentic_index":0.3}},"_prompt_per_m":8e-08,"_completion_per_m":4.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | google/gemma-3-27b-it","model_id":"google/gemma-3-27b-it","model_name":"Google: Gemma 3 27B","context_length":131072,"pricing":{"prompt":"0.00000008","completion":"0.00000016","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8124078788691,"uptime_last_5m":100,"uptime_last_1d":99.39517873149506,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-08,"_completion_per_m":1.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | google/gemma-3-27b-it","model_id":"google/gemma-3-27b-it","model_name":"Google: Gemma 3 27B","context_length":131072,"pricing":{"prompt":"0.00000008","completion":"0.00000045","input_cache_read":"0.00000004","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.88944168048646,"uptime_last_5m":99.61685823754789,"uptime_last_1d":98.90563645178993,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-08,"_completion_per_m":4.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-08,"_cached_write_per_m":null},{"name":"Nebius | google/gemma-3-27b-it","model_id":"google/gemma-3-27b-it","model_name":"Google: Gemma 3 27B","context_length":110000,"pricing":{"prompt":"0.0000001","completion":"0.0000003","discount":0},"provider_name":"Nebius","tag":"nebius/fp8","quantization":"fp8","max_completion_tokens":99000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","structured_outputs","response_format","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":false,"required":true,"function":true},"status":-5,"uptime_last_30m":67.75601566871853,"uptime_last_5m":70.00266880170804,"uptime_last_1d":82.11454775660464,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | google/gemma-3-27b-it","model_id":"google/gemma-3-27b-it","model_name":"Google: Gemma 3 27B","context_length":98304,"pricing":{"prompt":"0.000000119","completion":"0.0000002","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":66.85639941453894,"uptime_last_5m":54.08256880733945,"uptime_last_1d":92.89469254573942,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.19e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Phala | google/gemma-3-27b-it","model_id":"google/gemma-3-27b-it","model_name":"Google: Gemma 3 27B","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.00000046","input_cache_read":"0.000000075","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":235929,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":43.973719981875846,"uptime_last_5m":58.09659090909091,"uptime_last_1d":87.42104635919438,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":4.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.04e-07,"_priciest_blended_per_m":2.43e-07,"_provider_spread_multiplier":2.3365384615384612},{"id":"thedrummer/skyfall-36b-v2","canonical_slug":"thedrummer/skyfall-36b-v2","hugging_face_id":"TheDrummer/Skyfall-36B-v2","name":"TheDrummer: Skyfall 36B V2","created":1741636566,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000055","completion":"0.0000008","input_cache_read":"0.00000025"},"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/thedrummer/skyfall-36b-v2/endpoints"},"_prompt_per_m":5.5e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Parasail | thedrummer/skyfall-36b-v2","model_id":"thedrummer/skyfall-36b-v2","model_name":"TheDrummer: Skyfall 36B V2","context_length":32768,"pricing":{"prompt":"0.00000055","completion":"0.0000008","input_cache_read":"0.00000025","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":29491,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.5e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Parasail","_cheapest_blended_per_m":6.249999999999999e-07,"_priciest_blended_per_m":6.249999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"perplexity/sonar-reasoning-pro","canonical_slug":"perplexity/sonar-reasoning-pro","hugging_face_id":"","name":"Perplexity: Sonar Reasoning Pro","created":1741313308,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.005"},"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/perplexity/sonar-reasoning-pro/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":2e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Perplexity | perplexity/sonar-reasoning-pro","model_id":"perplexity/sonar-reasoning-pro","model_name":"Perplexity: Sonar Reasoning Pro","context_length":128000,"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.005","discount":0},"provider_name":"Perplexity","tag":"perplexity","quantization":"unknown","max_completion_tokens":115200,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.90383690739493,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Perplexity","_cheapest_blended_per_m":3.8e-06,"_priciest_blended_per_m":3.8e-06,"_provider_spread_multiplier":1.0},{"id":"perplexity/sonar-pro","canonical_slug":"perplexity/sonar-pro","hugging_face_id":"","name":"Perplexity: Sonar Pro","created":1741312423,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.005"},"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/perplexity/sonar-pro/endpoints"},"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Perplexity | perplexity/sonar-pro","model_id":"perplexity/sonar-pro","model_name":"Perplexity: Sonar Pro","context_length":200000,"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.005","discount":0},"provider_name":"Perplexity","tag":"perplexity","quantization":"unknown","max_completion_tokens":8000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99825849064969,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Perplexity","_cheapest_blended_per_m":6.5999999999999995e-06,"_priciest_blended_per_m":6.5999999999999995e-06,"_provider_spread_multiplier":1.0},{"id":"openai/o3-mini-high","canonical_slug":"openai/o3-mini-high-2025-01-31","hugging_face_id":"","name":"OpenAI: o3 Mini High","created":1739372611,"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...","context_length":200000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000011","completion":"0.0000044","web_search":"0.01","input_cache_read":"0.00000055"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/o3-mini-high-2025-01-31/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":15.7,"coding_index":16.3,"agentic_index":1.7}},"reasoning":{"mandatory":true,"supported_efforts":["high"],"default_effort":"high"},"_prompt_per_m":1.1e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/o3-mini-high-2025-01-31","model_id":"openai/o3-mini-high","model_name":"OpenAI: o3 Mini High","context_length":200000,"pricing":{"prompt":"0.0000011","completion":"0.0000044","web_search":"0.01","input_cache_read":"0.00000055","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":100000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.0900000000000003e-06,"_priciest_blended_per_m":2.0900000000000003e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen-plus","canonical_slug":"qwen/qwen-plus-2025-01-25","hugging_face_id":"","name":"Qwen: Qwen-Plus","created":1738409840,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000026","completion":"0.00000078","input_cache_read":"0.000000052","input_cache_write":"0.000000325","overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000078","completion":"0.00000234","input_cache_read":"0.000000156","input_cache_write":"0.000000975"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-plus-2025-01-25/endpoints"},"_prompt_per_m":2.6e-07,"_completion_per_m":7.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.2e-08,"_cached_write_per_m":3.25e-07,"_endpoints":[{"name":"Alibaba | qwen/qwen-plus-2025-01-25","model_id":"qwen/qwen-plus","model_name":"Qwen: Qwen-Plus","context_length":1000000,"pricing":{"prompt":"0.00000026","completion":"0.00000078","input_cache_read":"0.000000052","input_cache_write":"0.000000325","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000078","completion":"0.00000234","input_cache_read":"0.000000156","input_cache_write":"0.000000975"}]},"provider_name":"Alibaba","tag":"alibaba","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":995904,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.6e-07,"_completion_per_m":7.8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.2e-08,"_cached_write_per_m":3.25e-07}],"_cheapest_provider":"Alibaba","_cheapest_blended_per_m":4.16e-07,"_priciest_blended_per_m":4.16e-07,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen2.5-vl-72b-instruct","canonical_slug":"qwen/qwen2.5-vl-72b-instruct","hugging_face_id":"Qwen/Qwen2.5-VL-72B-Instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","created":1738410311,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.00000075"},"top_provider":{"context_length":32000,"max_completion_tokens":28800,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen2.5-vl-72b-instruct/endpoints"},"_prompt_per_m":2.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Nebius | qwen/qwen2.5-vl-72b-instruct","model_id":"qwen/qwen2.5-vl-72b-instruct","model_name":"Qwen: Qwen2.5 VL 72B Instruct","context_length":32000,"pricing":{"prompt":"0.00000025","completion":"0.00000075","discount":0},"provider_name":"Nebius","tag":"nebius/fp8","quantization":"fp8","max_completion_tokens":28800,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.42888643880926,"uptime_last_5m":100,"uptime_last_1d":98.34167029143106,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | qwen/qwen2.5-vl-72b-instruct","model_id":"qwen/qwen2.5-vl-72b-instruct","model_name":"Qwen: Qwen2.5 VL 72B Instruct","context_length":128000,"pricing":{"prompt":"0.0000008","completion":"0.000001","input_cache_read":"0.0000004","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":115200,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.5397008055236,"uptime_last_5m":99.53488372093024,"uptime_last_1d":99.83058584833883,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":4e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Nebius","_cheapest_blended_per_m":4e-07,"_priciest_blended_per_m":8.599999999999999e-07,"_provider_spread_multiplier":2.15},{"id":"mistralai/mistral-small-24b-instruct-2501","canonical_slug":"mistralai/mistral-small-24b-instruct-2501","hugging_face_id":"mistralai/Mistral-Small-24B-Instruct-2501","name":"Mistral: Mistral Small 3","created":1738255409,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.00000008"},"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-24b-instruct-2501/endpoints"},"_prompt_per_m":5e-08,"_completion_per_m":8e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | mistralai/mistral-small-24b-instruct-2501","model_id":"mistralai/mistral-small-24b-instruct-2501","model_name":"Mistral: Mistral Small 3","context_length":32768,"pricing":{"prompt":"0.00000005","completion":"0.00000008","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98339697825004,"uptime_last_5m":99.90426041168024,"uptime_last_1d":99.99892346282026,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":8e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":5.9e-08,"_priciest_blended_per_m":5.9e-08,"_provider_spread_multiplier":1.0},{"id":"openai/o3-mini","canonical_slug":"openai/o3-mini-2025-01-31","hugging_face_id":"","name":"OpenAI: o3 Mini","created":1738351721,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...","context_length":200000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000011","completion":"0.0000044","web_search":"0.01","input_cache_read":"0.00000055"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/o3-mini-2025-01-31/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":1.1e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/o3-mini-2025-01-31","model_id":"openai/o3-mini","model_name":"OpenAI: o3 Mini","context_length":200000,"pricing":{"prompt":"0.0000011","completion":"0.0000044","web_search":"0.01","input_cache_read":"0.00000055","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":100000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.1e-06,"_completion_per_m":4.4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":5.5e-07,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.0900000000000003e-06,"_priciest_blended_per_m":2.0900000000000003e-06,"_provider_spread_multiplier":1.0},{"id":"aion-labs/aion-rp-llama-3.1-8b","canonical_slug":"aion-labs/aion-rp-llama-3.1-8b","hugging_face_id":"","name":"AionLabs: Aion-RP 1.0 (8B)","created":1738696718,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000008","completion":"0.0000016"},"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/aion-labs/aion-rp-llama-3.1-8b/endpoints"},"_prompt_per_m":8e-07,"_completion_per_m":1.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"AionLabs | aion-labs/aion-rp-llama-3.1-8b","model_id":"aion-labs/aion-rp-llama-3.1-8b","model_name":"AionLabs: Aion-RP 1.0 (8B)","context_length":32768,"pricing":{"prompt":"0.0000008","completion":"0.0000016","discount":0},"provider_name":"AionLabs","tag":"aion-labs","quantization":"unknown","max_completion_tokens":29491,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":1.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"AionLabs","_cheapest_blended_per_m":1.0399999999999998e-06,"_priciest_blended_per_m":1.0399999999999998e-06,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-saba","canonical_slug":"mistralai/mistral-saba-2502","hugging_face_id":"","name":"Mistral: Saba","created":1739803239,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","context_length":32768,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000006","input_cache_read":"0.00000002"},"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-09-30","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-saba-2502/endpoints"},"_prompt_per_m":2e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-saba-2502","model_id":"mistralai/mistral-saba","model_name":"Mistral: Saba","context_length":32768,"pricing":{"prompt":"0.0000002","completion":"0.0000006","input_cache_read":"0.00000002","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":26214,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-saba-2502","model_id":"mistralai/mistral-saba","model_name":"Mistral: Saba","context_length":32768,"pricing":{"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000022","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":26214,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":6.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":3.2e-07,"_priciest_blended_per_m":3.52e-07,"_provider_spread_multiplier":1.0999999999999999},{"id":"perplexity/sonar-deep-research","canonical_slug":"perplexity/sonar-deep-research","hugging_face_id":"","name":"Perplexity: Sonar Deep Research","created":1741311246,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.005","internal_reasoning":"0.000003"},"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/perplexity/sonar-deep-research/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":2e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Perplexity | perplexity/sonar-deep-research","model_id":"perplexity/sonar-deep-research","model_name":"Perplexity: Sonar Deep Research","context_length":128000,"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.005","internal_reasoning":"0.000003","discount":0},"provider_name":"Perplexity","tag":"perplexity","quantization":"unknown","max_completion_tokens":115200,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":8e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Perplexity","_cheapest_blended_per_m":3.8e-06,"_priciest_blended_per_m":3.8e-06,"_provider_spread_multiplier":1.0},{"id":"deepseek/deepseek-r1-distill-llama-70b","canonical_slug":"deepseek/deepseek-r1-distill-llama-70b","hugging_face_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","name":"DeepSeek: R1 Distill Llama 70B","created":1737663169,"description":"DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.0000008","completion":"0.0000008"},"top_provider":{"context_length":8192,"max_completion_tokens":7372,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-07-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-r1-distill-llama-70b/endpoints"},"reasoning":{"mandatory":false},"_prompt_per_m":8e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | deepseek/deepseek-r1-distill-llama-70b","model_id":"deepseek/deepseek-r1-distill-llama-70b","model_name":"DeepSeek: R1 Distill Llama 70B","context_length":8192,"pricing":{"prompt":"0.0000008","completion":"0.0000008","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":7372,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":8e-07,"_priciest_blended_per_m":8e-07,"_provider_spread_multiplier":1.0},{"id":"perplexity/sonar","canonical_slug":"perplexity/sonar","hugging_face_id":"","name":"Perplexity: Sonar","created":1738013808,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","context_length":127072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000001","web_search":"0.005"},"top_provider":{"context_length":127072,"max_completion_tokens":114364,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/perplexity/sonar/endpoints"},"_prompt_per_m":1e-06,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Perplexity | perplexity/sonar","model_id":"perplexity/sonar","model_name":"Perplexity: Sonar","context_length":127072,"pricing":{"prompt":"0.000001","completion":"0.000001","web_search":"0.005","discount":0},"provider_name":"Perplexity","tag":"perplexity","quantization":"unknown","max_completion_tokens":114364,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99173901288714,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Perplexity","_cheapest_blended_per_m":1e-06,"_priciest_blended_per_m":1e-06,"_provider_spread_multiplier":1.0},{"id":"minimax/minimax-01","canonical_slug":"minimax/minimax-01","hugging_face_id":"MiniMaxAI/MiniMax-Text-01","name":"MiniMax: MiniMax-01","created":1736915462,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...","context_length":1000192,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000011"},"top_provider":{"context_length":1000192,"max_completion_tokens":900172,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-03-31","expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-01/endpoints"},"_prompt_per_m":2e-07,"_completion_per_m":1.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Minimax | minimax/minimax-01","model_id":"minimax/minimax-01","model_name":"MiniMax: MiniMax-01","context_length":1000192,"pricing":{"prompt":"0.0000002","completion":"0.0000011","discount":0},"provider_name":"Minimax","tag":"minimax","quantization":"unknown","max_completion_tokens":900172,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":1.1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Minimax","_cheapest_blended_per_m":4.7e-07,"_priciest_blended_per_m":4.7e-07,"_provider_spread_multiplier":1.0},{"id":"deepseek/deepseek-r1","canonical_slug":"deepseek/deepseek-r1","hugging_face_id":"deepseek-ai/DeepSeek-R1","name":"DeepSeek: R1","created":1737381095,"description":"DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....","context_length":64000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.0000007","completion":"0.0000025"},"top_provider":{"context_length":64000,"max_completion_tokens":16000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-07-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-r1/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":18.6,"coding_index":24.6,"agentic_index":3.1}},"reasoning":{"mandatory":true},"_prompt_per_m":7e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | deepseek/deepseek-r1","model_id":"deepseek/deepseek-r1","model_name":"DeepSeek: R1","context_length":64000,"pricing":{"prompt":"0.0000007","completion":"0.0000025","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":16000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99870780999638,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-07,"_completion_per_m":2.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":1.24e-06,"_priciest_blended_per_m":1.24e-06,"_provider_spread_multiplier":1.0},{"id":"deepseek/deepseek-chat","canonical_slug":"deepseek/deepseek-chat-v3","hugging_face_id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek: DeepSeek V3","created":1735241320,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.0000002574","completion":"0.0000010287"},"top_provider":{"context_length":128000,"max_completion_tokens":16000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-07-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-chat-v3/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1131,"win_rate":50.5,"rank":73},{"arena":"models","category":"codecategories","elo":1133,"win_rate":48.4,"rank":85},{"arena":"models","category":"dataviz","elo":1109,"win_rate":50,"rank":87},{"arena":"models","category":"gamedev","elo":1089,"win_rate":43.7,"rank":90},{"arena":"models","category":"svg","elo":1016,"win_rate":38.8,"rank":78},{"arena":"models","category":"uicomponent","elo":1119,"win_rate":52.7,"rank":80},{"arena":"models","category":"website","elo":1140,"win_rate":48.5,"rank":84}]},"_prompt_per_m":2.574e-07,"_completion_per_m":1.0287e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"StreamLake | deepseek/deepseek-chat-v3","model_id":"deepseek/deepseek-chat","model_name":"DeepSeek: DeepSeek V3","context_length":128000,"pricing":{"prompt":"0.0000002574","completion":"0.0000010287","discount":0.1},"provider_name":"StreamLake","tag":"streamlake","quantization":"unknown","max_completion_tokens":16000,"max_prompt_tokens":null,"supported_parameters":["response_format","structured_outputs","tools","tool_choice","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.53095684803002,"uptime_last_5m":98.9795918367347,"uptime_last_1d":99.65939197714944,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.574e-07,"_completion_per_m":1.0287e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | deepseek/deepseek-chat-v3","model_id":"deepseek/deepseek-chat","model_name":"DeepSeek: DeepSeek V3","context_length":163840,"pricing":{"prompt":"0.00000032","completion":"0.00000089","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp4","quantization":"fp4","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":99.30604982206405,"uptime_last_5m":99.20053297801465,"uptime_last_1d":92.60068186660985,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.2e-07,"_completion_per_m":8.9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | deepseek/deepseek-chat-v3","model_id":"deepseek/deepseek-chat","model_name":"DeepSeek: DeepSeek V3","context_length":64000,"pricing":{"prompt":"0.0000004","completion":"0.0000013","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":16000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.0450204638472,"uptime_last_5m":100,"uptime_last_1d":96.60555147641054,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":1.3e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"StreamLake","_cheapest_blended_per_m":4.8879e-07,"_priciest_blended_per_m":6.699999999999999e-07,"_provider_spread_multiplier":1.3707318071155299},{"id":"sao10k/l3.3-euryale-70b","canonical_slug":"sao10k/l3.3-euryale-70b-v2.3","hugging_face_id":"Sao10K/L3.3-70B-Euryale-v2.3","name":"Sao10K: Llama 3.3 Euryale 70B","created":1734535928,"description":"Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000065","completion":"0.00000075"},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/sao10k/l3.3-euryale-70b-v2.3/endpoints"},"_prompt_per_m":6.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"NextBit | sao10k/l3.3-euryale-70b-v2.3","model_id":"sao10k/l3.3-euryale-70b","model_name":"Sao10K: Llama 3.3 Euryale 70B","context_length":131072,"pricing":{"prompt":"0.00000065","completion":"0.00000075","discount":0},"provider_name":"NextBit","tag":"nextbit/bf16","quantization":"bf16","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","logprobs","top_logprobs","repetition_penalty","seed"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.2831541218638,"uptime_last_5m":100,"uptime_last_1d":98.4986788373769,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"NextBit","_cheapest_blended_per_m":6.8e-07,"_priciest_blended_per_m":6.8e-07,"_provider_spread_multiplier":1.0},{"id":"openai/o1","canonical_slug":"openai/o1-2024-12-17","hugging_face_id":"","name":"OpenAI: o1","created":1734459999,"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0.00006","web_search":"0.01","input_cache_read":"0.0000075"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/o1-2024-12-17/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":39.7,"agentic_index":null}},"reasoning":{"mandatory":false},"_prompt_per_m":1.5e-05,"_completion_per_m":6e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-06,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/o1-2024-12-17","model_id":"openai/o1","model_name":"OpenAI: o1","context_length":200000,"pricing":{"prompt":"0.000015","completion":"0.00006","web_search":"0.01","input_cache_read":"0.0000075","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":100000,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-05,"_completion_per_m":6e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-06,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.85e-05,"_priciest_blended_per_m":2.85e-05,"_provider_spread_multiplier":1.0},{"id":"microsoft/phi-4","canonical_slug":"microsoft/phi-4","hugging_face_id":"microsoft/phi-4","name":"Microsoft: Phi 4","created":1736489872,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000007","completion":"0.00000014"},"top_provider":{"context_length":16384,"max_completion_tokens":14745,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/microsoft/phi-4/endpoints"},"_prompt_per_m":7e-08,"_completion_per_m":1.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | microsoft/phi-4","model_id":"microsoft/phi-4","model_name":"Microsoft: Phi 4","context_length":16384,"pricing":{"prompt":"0.00000007","completion":"0.00000014","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/bf16","quantization":"bf16","max_completion_tokens":14745,"max_prompt_tokens":4096,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-08,"_completion_per_m":1.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":9.100000000000001e-08,"_priciest_blended_per_m":9.100000000000001e-08,"_provider_spread_multiplier":1.0},{"id":"cohere/command-r7b-12-2024","canonical_slug":"cohere/command-r7b-12-2024","hugging_face_id":"","name":"Cohere: Command R7B (12-2024)","created":1734158152,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":"0.0000000375","completion":"0.00000015"},"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/cohere/command-r7b-12-2024/endpoints"},"_prompt_per_m":3.75e-08,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Cohere | cohere/command-r7b-12-2024","model_id":"cohere/command-r7b-12-2024","model_name":"Cohere: Command R7B (12-2024)","context_length":128000,"pricing":{"prompt":"0.0000000375","completion":"0.00000015","discount":0},"provider_name":"Cohere","tag":"cohere","quantization":"unknown","max_completion_tokens":4000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.98360118071498,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.75e-08,"_completion_per_m":1.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Cohere","_cheapest_blended_per_m":7.124999999999999e-08,"_priciest_blended_per_m":7.124999999999999e-08,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-4o-2024-11-20","canonical_slug":"openai/gpt-4o-2024-11-20","hugging_face_id":"","name":"OpenAI: GPT-4o (2024-11-20)","created":1732127594,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-2024-11-20/endpoints"},"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-4o-2024-11-20","model_id":"openai/gpt-4o-2024-11-20","model_name":"OpenAI: GPT-4o (2024-11-20)","context_length":128000,"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":4.75e-06,"_priciest_blended_per_m":4.75e-06,"_provider_spread_multiplier":1.0},{"id":"amazon/nova-micro-v1","canonical_slug":"amazon/nova-micro-v1","hugging_face_id":"","name":"Amazon: Nova Micro 1.0","created":1733437237,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":"0.000000035","completion":"0.00000014"},"top_provider":{"context_length":128000,"max_completion_tokens":5120,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-10-31","expiration_date":null,"links":{"details":"/api/v1/models/amazon/nova-micro-v1/endpoints"},"_prompt_per_m":3.5e-08,"_completion_per_m":1.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Amazon Bedrock | amazon/nova-micro-v1","model_id":"amazon/nova-micro-v1","model_name":"Amazon: Nova Micro 1.0","context_length":128000,"pricing":{"prompt":"0.000000035","completion":"0.00000014","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":5120,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":92.95908428115587,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-08,"_completion_per_m":1.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | amazon/nova-micro-v1","model_id":"amazon/nova-micro-v1","model_name":"Amazon: Nova Micro 1.0","context_length":128000,"pricing":{"prompt":"0.000000035","completion":"0.00000014","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":5120,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":91.36826234451564,"uptime_last_5m":100,"uptime_last_1d":57.362689675691755,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.5e-08,"_completion_per_m":1.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":6.649999999999999e-08,"_priciest_blended_per_m":6.649999999999999e-08,"_provider_spread_multiplier":1.0},{"id":"amazon/nova-pro-v1","canonical_slug":"amazon/nova-pro-v1","hugging_face_id":"","name":"Amazon: Nova Pro 1.0","created":1733436303,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":"0.0000008","completion":"0.0000032"},"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-10-31","expiration_date":null,"links":{"details":"/api/v1/models/amazon/nova-pro-v1/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"website","elo":816,"win_rate":21.4,"rank":126}]},"_prompt_per_m":8e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Amazon Bedrock | amazon/nova-pro-v1","model_id":"amazon/nova-pro-v1","model_name":"Amazon: Nova Pro 1.0","context_length":300000,"pricing":{"prompt":"0.0000008","completion":"0.0000032","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":5120,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.93077189338871,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | amazon/nova-pro-v1","model_id":"amazon/nova-pro-v1","model_name":"Amazon: Nova Pro 1.0","context_length":300000,"pricing":{"prompt":"0.0000008","completion":"0.0000032","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":5120,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.91735537190083,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":3.2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":1.5199999999999998e-06,"_priciest_blended_per_m":1.5199999999999998e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen-2.5-coder-32b-instruct","canonical_slug":"qwen/qwen-2.5-coder-32b-instruct","hugging_face_id":"Qwen/Qwen2.5-Coder-32B-Instruct","name":"Qwen2.5 Coder 32B Instruct","created":1731368400,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.00000066","completion":"0.000001"},"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-2.5-coder-32b-instruct/endpoints"},"_prompt_per_m":6.6e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Cloudflare | qwen/qwen-2.5-coder-32b-instruct","model_id":"qwen/qwen-2.5-coder-32b-instruct","model_name":"Qwen2.5 Coder 32B Instruct","context_length":32768,"pricing":{"prompt":"0.00000066","completion":"0.000001","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":29491,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.6e-07,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Cloudflare","_cheapest_blended_per_m":7.62e-07,"_priciest_blended_per_m":7.62e-07,"_provider_spread_multiplier":1.0},{"id":"meta-llama/llama-3.3-70b-instruct","canonical_slug":"meta-llama/llama-3.3-70b-instruct","hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","name":"Meta: Llama 3.3 70B Instruct","created":1733506137,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000071","completion":"0.00000071","input_cache_read":"0.00000071"},"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null}},"_prompt_per_m":7.1e-07,"_completion_per_m":7.1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.1e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":131072,"pricing":{"prompt":"0.0000001","completion":"0.00000032","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/turbo","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":97.90901384571913,"uptime_last_5m":97.93373708585679,"uptime_last_1d":98.4350565648528,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":3.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Nebius | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":131072,"pricing":{"prompt":"0.00000013","completion":"0.0000004","discount":0},"provider_name":"Nebius","tag":"nebius/fp8","quantization":"fp8","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":54.78686233403215,"uptime_last_5m":82.05128205128204,"uptime_last_1d":44.20991323907455,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.3e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":12288,"pricing":{"prompt":"0.000000135","completion":"0.0000004","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":11059,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.78751369112814,"uptime_last_5m":97.57225433526011,"uptime_last_1d":95.667497854317,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.35e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"AkashML | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":131072,"pricing":{"prompt":"0.0000002","completion":"0.00000052","input_cache_read":"0.0000001","discount":0},"provider_name":"AkashML","tag":"akashml/fp8","quantization":"fp8","max_completion_tokens":128000,"max_prompt_tokens":null,"supported_parameters":["temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","max_tokens","structured_outputs","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.81048423730353,"uptime_last_5m":99.53512396694215,"uptime_last_1d":98.46481769814243,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-07,"_completion_per_m":5.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1e-07,"_cached_write_per_m":null},{"name":"Parasail | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":131072,"pricing":{"prompt":"0.00000022","completion":"0.0000005","input_cache_read":"0.00000011","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.90108803165182,"uptime_last_5m":99.83870967741936,"uptime_last_1d":99.35821113631845,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.1e-07,"_cached_write_per_m":null},{"name":"Crusoe | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":131072,"pricing":{"prompt":"0.00000025","completion":"0.00000075","input_cache_read":"0.00000013","discount":0},"provider_name":"Crusoe","tag":"crusoe/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.49752219647524,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.3e-07,"_cached_write_per_m":null},{"name":"Cloudflare | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":24000,"pricing":{"prompt":"0.000000293","completion":"0.000002253","discount":0},"provider_name":"Cloudflare","tag":"cloudflare/fp8","quantization":"fp8","max_completion_tokens":21600,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.42660550458714,"uptime_last_5m":98.50746268656717,"uptime_last_1d":96.27121081392005,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.93e-07,"_completion_per_m":2.253e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"SambaNova | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":131072,"pricing":{"prompt":"0.00000045","completion":"0.0000009","discount":0.25},"provider_name":"SambaNova","tag":"sambanova-turbo","quantization":"unknown","max_completion_tokens":3072,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.66666666666667,"uptime_last_5m":100,"uptime_last_1d":99.03118503118503,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Groq | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":131072,"pricing":{"prompt":"0.00000059","completion":"0.00000079","input_cache_read":"0.000000295","discount":0},"provider_name":"Groq","tag":"groq","quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.14563106796116,"uptime_last_5m":99.70370370370371,"uptime_last_1d":99.83231386695172,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.9e-07,"_completion_per_m":7.9e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.95e-07,"_cached_write_per_m":null},{"name":"CoreWeave | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":128000,"pricing":{"prompt":"0.00000071","completion":"0.00000071","input_cache_read":"0.00000071","discount":0},"provider_name":"CoreWeave","tag":"coreweave/fp16","quantization":"fp16","max_completion_tokens":115200,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.90196078431373,"uptime_last_5m":100,"uptime_last_1d":99.95932739204926,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.1e-07,"_completion_per_m":7.1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.1e-07,"_cached_write_per_m":null},{"name":"Google | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":128000,"pricing":{"prompt":"0.00000072","completion":"0.00000072","discount":0},"provider_name":"Google","tag":"google-vertex/us-central1","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","frequency_penalty","presence_penalty","stop","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96448548344135,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.2e-07,"_completion_per_m":7.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Google | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":128000,"pricing":{"prompt":"0.00000072","completion":"0.00000072","discount":0},"provider_name":"Google","tag":"google-vertex","quantization":"unknown","max_completion_tokens":115200,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.6124031007752,"uptime_last_5m":100,"uptime_last_1d":98.83438975624283,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.2e-07,"_completion_per_m":7.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Together | meta-llama/llama-3.3-70b-instruct","model_id":"meta-llama/llama-3.3-70b-instruct","model_name":"Meta: Llama 3.3 70B Instruct","context_length":131072,"pricing":{"prompt":"0.00000104","completion":"0.00000104","discount":0},"provider_name":"Together","tag":"together","quantization":"unknown","max_completion_tokens":2048,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":98.91891891891892,"uptime_last_5m":95.74468085106383,"uptime_last_1d":98.44051685727017,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.04e-06,"_completion_per_m":1.04e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1.6599999999999998e-07,"_priciest_blended_per_m":1.04e-06,"_provider_spread_multiplier":6.265060240963856},{"id":"mistralai/mistral-large-2407","canonical_slug":"mistralai/mistral-large-2407","hugging_face_id":"","name":"Mistral Large 2407","created":1731978415,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","context_length":131072,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002"},"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-03-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-large-2407/endpoints"},"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-large-2407","model_id":"mistralai/mistral-large-2407","model_name":"Mistral Large 2407","context_length":131072,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-large-2407","model_id":"mistralai/mistral-large-2407","model_name":"Mistral Large 2407","context_length":131072,"pricing":{"prompt":"0.0000022","completion":"0.0000066","input_cache_read":"0.00000022","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":6.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":3.2e-06,"_priciest_blended_per_m":3.52e-06,"_provider_spread_multiplier":1.1},{"id":"amazon/nova-lite-v1","canonical_slug":"amazon/nova-lite-v1","hugging_face_id":"","name":"Amazon: Nova Lite 1.0","created":1733437363,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":"0.00000006","completion":"0.00000024"},"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-10-31","expiration_date":null,"links":{"details":"/api/v1/models/amazon/nova-lite-v1/endpoints"},"_prompt_per_m":6e-08,"_completion_per_m":2.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Amazon Bedrock | amazon/nova-lite-v1","model_id":"amazon/nova-lite-v1","model_name":"Amazon: Nova Lite 1.0","context_length":300000,"pricing":{"prompt":"0.00000006","completion":"0.00000024","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":5120,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99745807949432,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-08,"_completion_per_m":2.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | amazon/nova-lite-v1","model_id":"amazon/nova-lite-v1","model_name":"Amazon: Nova Lite 1.0","context_length":300000,"pricing":{"prompt":"0.00000006","completion":"0.00000024","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock/eu-west-1","quantization":"unknown","max_completion_tokens":5120,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98486071861123,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-08,"_completion_per_m":2.4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":1.1399999999999999e-07,"_priciest_blended_per_m":1.1399999999999999e-07,"_provider_spread_multiplier":1.0},{"id":"anthracite-org/magnum-v4-72b","canonical_slug":"anthracite-org/magnum-v4-72b","hugging_face_id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","created":1729555200,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.000003","completion":"0.000005"},"top_provider":{"context_length":32768,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/anthracite-org/magnum-v4-72b/endpoints"},"_prompt_per_m":3e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Mancer 2 | anthracite-org/magnum-v4-72b","model_id":"anthracite-org/magnum-v4-72b","model_name":"Magnum v4 72B","context_length":32768,"pricing":{"prompt":"0.000003","completion":"0.000005","discount":0},"provider_name":"Mancer 2","tag":"mancer/fp8","quantization":"fp8","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Mancer 2","_cheapest_blended_per_m":3.6e-06,"_priciest_blended_per_m":3.6e-06,"_provider_spread_multiplier":1.0},{"id":"thedrummer/unslopnemo-12b","canonical_slug":"thedrummer/unslopnemo-12b","hugging_face_id":"TheDrummer/UnslopNemo-12B-v4.1","name":"TheDrummer: UnslopNemo 12B","created":1731103448,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","context_length":1024000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.0000004","completion":"0.0000004"},"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-04-30","expiration_date":null,"links":{"details":"/api/v1/models/thedrummer/unslopnemo-12b/endpoints"},"_prompt_per_m":4e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"NextBit | thedrummer/unslopnemo-12b","model_id":"thedrummer/unslopnemo-12b","model_name":"TheDrummer: UnslopNemo 12B","context_length":32768,"pricing":{"prompt":"0.0000004","completion":"0.0000004","discount":0},"provider_name":"NextBit","tag":"nextbit/fp8","quantization":"fp8","max_completion_tokens":26214,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":98.38884866039102,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | thedrummer/unslopnemo-12b","model_id":"thedrummer/unslopnemo-12b","model_name":"TheDrummer: UnslopNemo 12B","context_length":1024000,"pricing":{"prompt":"0.0000004","completion":"0.0000004","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":819200,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.97508098679292,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"NextBit","_cheapest_blended_per_m":4e-07,"_priciest_blended_per_m":4e-07,"_provider_spread_multiplier":1.0},{"id":"meta-llama/llama-3.2-3b-instruct","canonical_slug":"meta-llama/llama-3.2-3b-instruct","hugging_face_id":"meta-llama/Llama-3.2-3B-Instruct","name":"Meta: Llama 3.2 3B Instruct","created":1727222400,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000005","completion":"0.00000033"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints"},"_prompt_per_m":5e-08,"_completion_per_m":3.3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Parasail | meta-llama/llama-3.2-3b-instruct","model_id":"meta-llama/llama-3.2-3b-instruct","model_name":"Meta: Llama 3.2 3B Instruct","context_length":131072,"pricing":{"prompt":"0.00000005","completion":"0.00000033","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99574010372847,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":3.3e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Cloudflare | meta-llama/llama-3.2-3b-instruct","model_id":"meta-llama/llama-3.2-3b-instruct","model_name":"Meta: Llama 3.2 3B Instruct","context_length":80000,"pricing":{"prompt":"0.0000000509","completion":"0.000000335","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":72000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.57446808510639,"uptime_last_5m":null,"uptime_last_1d":99.67561430540913,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5.09e-08,"_completion_per_m":3.35e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Parasail","_cheapest_blended_per_m":1.34e-07,"_priciest_blended_per_m":1.3613e-07,"_provider_spread_multiplier":1.0158955223880595},{"id":"cohere/command-r-08-2024","canonical_slug":"cohere/command-r-08-2024","hugging_face_id":null,"name":"Cohere: Command R (08-2024)","created":1724976000,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-03-31","expiration_date":null,"links":{"details":"/api/v1/models/cohere/command-r-08-2024/endpoints"},"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Cohere | cohere/command-r-08-2024","model_id":"cohere/command-r-08-2024","model_name":"Cohere: Command R (08-2024)","context_length":128000,"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"provider_name":"Cohere","tag":"cohere","quantization":"unknown","max_completion_tokens":4000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.03846153846155,"uptime_last_5m":null,"uptime_last_1d":99.23123003194888,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Cohere","_cheapest_blended_per_m":2.8499999999999997e-07,"_priciest_blended_per_m":2.8499999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"meta-llama/llama-3.2-1b-instruct","canonical_slug":"meta-llama/llama-3.2-1b-instruct","hugging_face_id":"meta-llama/Llama-3.2-1B-Instruct","name":"Meta: Llama 3.2 1B Instruct","created":1727222400,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...","context_length":60000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.000000027","completion":"0.000000201"},"top_provider":{"context_length":60000,"max_completion_tokens":54000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints"},"_prompt_per_m":2.7e-08,"_completion_per_m":2.01e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Cloudflare | meta-llama/llama-3.2-1b-instruct","model_id":"meta-llama/llama-3.2-1b-instruct","model_name":"Meta: Llama 3.2 1B Instruct","context_length":60000,"pricing":{"prompt":"0.000000027","completion":"0.000000201","discount":0},"provider_name":"Cloudflare","tag":"cloudflare","quantization":"unknown","max_completion_tokens":54000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.7e-08,"_completion_per_m":2.01e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Cloudflare","_cheapest_blended_per_m":7.920000000000001e-08,"_priciest_blended_per_m":7.920000000000001e-08,"_provider_spread_multiplier":1.0},{"id":"cohere/command-r-plus-08-2024","canonical_slug":"cohere/command-r-plus-08-2024","hugging_face_id":null,"name":"Cohere: Command R+ (08-2024)","created":1724976000,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001"},"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-03-31","expiration_date":null,"links":{"details":"/api/v1/models/cohere/command-r-plus-08-2024/endpoints"},"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Cohere | cohere/command-r-plus-08-2024","model_id":"cohere/command-r-plus-08-2024","model_name":"Cohere: Command R+ (08-2024)","context_length":128000,"pricing":{"prompt":"0.0000025","completion":"0.00001","discount":0},"provider_name":"Cohere","tag":"cohere","quantization":"unknown","max_completion_tokens":4000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":94.58646616541353,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Cohere","_cheapest_blended_per_m":4.75e-06,"_priciest_blended_per_m":4.75e-06,"_provider_spread_multiplier":1.0},{"id":"qwen/qwen-2.5-72b-instruct","canonical_slug":"qwen/qwen-2.5-72b-instruct","hugging_face_id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen2.5 72B Instruct","created":1726704000,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.00000036","completion":"0.0000004"},"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-2.5-72b-instruct/endpoints"},"_prompt_per_m":3.6e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | qwen/qwen-2.5-72b-instruct","model_id":"qwen/qwen-2.5-72b-instruct","model_name":"Qwen2.5 72B Instruct","context_length":32768,"pricing":{"prompt":"0.00000036","completion":"0.0000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99355511784064,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.6e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | qwen/qwen-2.5-72b-instruct","model_id":"qwen/qwen-2.5-72b-instruct","model_name":"Qwen2.5 72B Instruct","context_length":32000,"pricing":{"prompt":"0.00000038","completion":"0.0000004","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":15.786384976525822,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3.8e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":3.72e-07,"_priciest_blended_per_m":3.86e-07,"_provider_spread_multiplier":1.0376344086021505},{"id":"qwen/qwen-2.5-7b-instruct","canonical_slug":"qwen/qwen-2.5-7b-instruct","hugging_face_id":"Qwen/Qwen2.5-7B-Instruct","name":"Qwen: Qwen2.5 7B Instruct","created":1729036800,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.0000001","completion":"0.0000002"},"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-2.5-7b-instruct/endpoints"},"_prompt_per_m":1e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Phala | qwen/qwen-2.5-7b-instruct","model_id":"qwen/qwen-2.5-7b-instruct","model_name":"Qwen: Qwen2.5 7B Instruct","context_length":32768,"pricing":{"prompt":"0.0000001","completion":"0.0000002","discount":0},"provider_name":"Phala","tag":"phala","quantization":"unknown","max_completion_tokens":29491,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":false,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99987476251843,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-07,"_completion_per_m":2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Phala","_cheapest_blended_per_m":1.2999999999999997e-07,"_priciest_blended_per_m":1.2999999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"sao10k/l3.1-euryale-70b","canonical_slug":"sao10k/l3.1-euryale-70b","hugging_face_id":"Sao10K/L3.1-70B-Euryale-v2.2","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","created":1724803200,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000085","completion":"0.00000085"},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/sao10k/l3.1-euryale-70b/endpoints"},"_prompt_per_m":8.5e-07,"_completion_per_m":8.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | sao10k/l3.1-euryale-70b","model_id":"sao10k/l3.1-euryale-70b","model_name":"Sao10K: Llama 3.1 Euryale 70B v2.2","context_length":131072,"pricing":{"prompt":"0.00000085","completion":"0.00000085","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.9719534427149,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8.5e-07,"_completion_per_m":8.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | sao10k/l3.1-euryale-70b","model_id":"sao10k/l3.1-euryale-70b","model_name":"Sao10K: Llama 3.1 Euryale 70B v2.2","context_length":8192,"pricing":{"prompt":"0.0000014504","completion":"0.0000014504","discount":0.02},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":7372,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.68798751950078,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.4504e-06,"_completion_per_m":1.4504e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":8.5e-07,"_priciest_blended_per_m":1.4504e-06,"_provider_spread_multiplier":1.7063529411764704},{"id":"openai/gpt-4o-2024-08-06","canonical_slug":"openai/gpt-4o-2024-08-06","hugging_face_id":null,"name":"OpenAI: GPT-4o (2024-08-06)","created":1722902400,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-2024-08-06/endpoints"},"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-4o-2024-08-06","model_id":"openai/gpt-4o-2024-08-06","model_name":"OpenAI: GPT-4o (2024-08-06)","context_length":128000,"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.92181391712275,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-4o-2024-08-06","model_id":"openai/gpt-4o-2024-08-06","model_name":"OpenAI: GPT-4o (2024-08-06)","context_length":128000,"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.49335022165928,"uptime_last_5m":100,"uptime_last_1d":99.86978463863551,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":4.75e-06,"_priciest_blended_per_m":4.75e-06,"_provider_spread_multiplier":1.0},{"id":"nousresearch/hermes-3-llama-3.1-405b","canonical_slug":"nousresearch/hermes-3-llama-3.1-405b","hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-405B","name":"Nous: Hermes 3 405B Instruct","created":1723766400,"description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"chatml"},"pricing":{"prompt":"0.000001","completion":"0.000001"},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints"},"_prompt_per_m":1e-06,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | nousresearch/hermes-3-llama-3.1-405b","model_id":"nousresearch/hermes-3-llama-3.1-405b","model_name":"Nous: Hermes 3 405B Instruct","context_length":131072,"pricing":{"prompt":"0.000001","completion":"0.000001","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":1e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":1e-06,"_priciest_blended_per_m":1e-06,"_provider_spread_multiplier":1.0},{"id":"meta-llama/llama-3.1-70b-instruct","canonical_slug":"meta-llama/llama-3.1-70b-instruct","hugging_face_id":"meta-llama/Meta-Llama-3.1-70B-Instruct","name":"Meta: Llama 3.1 70B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.0000004","completion":"0.0000004"},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.1-70b-instruct/endpoints"},"_prompt_per_m":4e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | meta-llama/llama-3.1-70b-instruct","model_id":"meta-llama/llama-3.1-70b-instruct","model_name":"Meta: Llama 3.1 70B Instruct","context_length":131072,"pricing":{"prompt":"0.0000004","completion":"0.0000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/turbo","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.98166819431714,"uptime_last_5m":99.9479979199168,"uptime_last_1d":99.62513544421951,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Amazon Bedrock | meta-llama/llama-3.1-70b-instruct","model_id":"meta-llama/llama-3.1-70b-instruct","model_name":"Meta: Llama 3.1 70B Instruct","context_length":131072,"pricing":{"prompt":"0.00000072","completion":"0.00000072","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":8192,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.98314945546134,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7.2e-07,"_completion_per_m":7.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"CoreWeave | meta-llama/llama-3.1-70b-instruct","model_id":"meta-llama/llama-3.1-70b-instruct","model_name":"Meta: Llama 3.1 70B Instruct","context_length":131072,"pricing":{"prompt":"0.0000008","completion":"0.0000008","input_cache_read":"0.0000008","discount":0},"provider_name":"CoreWeave","tag":"coreweave/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","structured_outputs","logprobs","top_logprobs","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.81861870515793,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-07,"_completion_per_m":8e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":4e-07,"_priciest_blended_per_m":8e-07,"_provider_spread_multiplier":2.0},{"id":"meta-llama/llama-3.1-8b-instruct","canonical_slug":"meta-llama/llama-3.1-8b-instruct","hugging_face_id":"meta-llama/Meta-Llama-3.1-8B-Instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000005","completion":"0.00000008","input_cache_read":"0.000000025"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":5.4,"agentic_index":null}},"_prompt_per_m":5e-08,"_completion_per_m":8e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.9735723566851,"uptime_last_5m":99.94646680942184,"uptime_last_1d":99.89095309994293,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-08,"_completion_per_m":4e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":16384,"pricing":{"prompt":"0.00000002","completion":"0.00000005","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":14745,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.48762333391034,"uptime_last_5m":99.69331425066449,"uptime_last_1d":99.37621895322296,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-08,"_completion_per_m":5e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Groq | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000005","completion":"0.00000008","input_cache_read":"0.000000025","discount":0},"provider_name":"Groq","tag":"groq","quantization":"unknown","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.96711119598545,"uptime_last_5m":99.99316519718407,"uptime_last_1d":99.93887585018928,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":8e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.5e-08,"_cached_write_per_m":null},{"name":"Cloudflare | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":32000,"pricing":{"prompt":"0.000000152","completion":"0.000000287","discount":0},"provider_name":"Cloudflare","tag":"cloudflare/fp8","quantization":"fp8","max_completion_tokens":28800,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.35374641256995,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.52e-07,"_completion_per_m":2.87e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"CoreWeave | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000022","completion":"0.00000022","input_cache_read":"0.00000022","discount":0},"provider_name":"CoreWeave","tag":"coreweave/bf16","quantization":"bf16","max_completion_tokens":117964,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.96544209940141,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-07,"_completion_per_m":2.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":2.6e-08,"_priciest_blended_per_m":2.2e-07,"_provider_spread_multiplier":8.461538461538462},{"id":"nousresearch/hermes-3-llama-3.1-70b","canonical_slug":"nousresearch/hermes-3-llama-3.1-70b","hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-70B","name":"Nous: Hermes 3 70B Instruct","created":1723939200,"description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"chatml"},"pricing":{"prompt":"0.0000007","completion":"0.0000007"},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/nousresearch/hermes-3-llama-3.1-70b/endpoints"},"_prompt_per_m":7e-07,"_completion_per_m":7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | nousresearch/hermes-3-llama-3.1-70b","model_id":"nousresearch/hermes-3-llama-3.1-70b","model_name":"Nous: Hermes 3 70B Instruct","context_length":131072,"pricing":{"prompt":"0.0000007","completion":"0.0000007","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":false,"function":false},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":7e-07,"_completion_per_m":7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":7e-07,"_priciest_blended_per_m":7e-07,"_provider_spread_multiplier":1.0},{"id":"sao10k/l3-lunaris-8b","canonical_slug":"sao10k/l3-lunaris-8b","hugging_face_id":"Sao10K/L3-8B-Lunaris-v1","name":"Sao10K: Llama 3 8B Lunaris","created":1723507200,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000004","completion":"0.00000005"},"top_provider":{"context_length":8192,"max_completion_tokens":7372,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/sao10k/l3-lunaris-8b/endpoints"},"_prompt_per_m":4e-08,"_completion_per_m":5e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Parasail | sao10k/l3-lunaris-8b","model_id":"sao10k/l3-lunaris-8b","model_name":"Sao10K: Llama 3 8B Lunaris","context_length":8192,"pricing":{"prompt":"0.00000004","completion":"0.00000005","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":7372,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.83561643835617,"uptime_last_5m":100,"uptime_last_1d":99.95946213169864,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-08,"_completion_per_m":5e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | sao10k/l3-lunaris-8b","model_id":"sao10k/l3-lunaris-8b","model_name":"Sao10K: Llama 3 8B Lunaris","context_length":8192,"pricing":{"prompt":"0.00000004","completion":"0.00000005","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/turbo","quantization":"fp8","max_completion_tokens":7372,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.73368841544608,"uptime_last_5m":100,"uptime_last_1d":99.96035722544626,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-08,"_completion_per_m":5e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | sao10k/l3-lunaris-8b","model_id":"sao10k/l3-lunaris-8b","model_name":"Sao10K: Llama 3 8B Lunaris","context_length":8192,"pricing":{"prompt":"0.00000005","completion":"0.00000005","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":7372,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.67227684274843,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-08,"_completion_per_m":5e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Parasail","_cheapest_blended_per_m":4.3e-08,"_priciest_blended_per_m":5e-08,"_provider_spread_multiplier":1.1627906976744184},{"id":"mistralai/mistral-nemo","canonical_slug":"mistralai/mistral-nemo","hugging_face_id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral: Mistral Nemo","created":1721347200,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.000000019","completion":"0.00000003"},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-04-30","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-nemo/endpoints"},"_prompt_per_m":1.9e-08,"_completion_per_m":3e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"DeepInfra | mistralai/mistral-nemo","model_id":"mistralai/mistral-nemo","model_name":"Mistral: Mistral Nemo","context_length":131072,"pricing":{"prompt":"0.000000019","completion":"0.00000003","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":66.2773519163763,"uptime_last_5m":50.56999544003647,"uptime_last_1d":79.6872379107253,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.9e-08,"_completion_per_m":3e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | mistralai/mistral-nemo","model_id":"mistralai/mistral-nemo","model_name":"Mistral: Mistral Nemo","context_length":131072,"pricing":{"prompt":"0.00000003","completion":"0.00000003","discount":0},"provider_name":"Parasail","tag":"parasail/fp8","quantization":"fp8","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.95501574448943,"uptime_last_5m":100,"uptime_last_1d":99.98370510646731,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-08,"_completion_per_m":3e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Novita | mistralai/mistral-nemo","model_id":"mistralai/mistral-nemo","model_name":"Mistral: Mistral Nemo","context_length":60288,"pricing":{"prompt":"0.00000004","completion":"0.00000017","discount":0},"provider_name":"Novita","tag":"novita/fp8","quantization":"fp8","max_completion_tokens":16000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":-5,"uptime_last_30m":48.606303516123155,"uptime_last_5m":37.857142857142854,"uptime_last_1d":74.68221267642676,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-08,"_completion_per_m":1.7e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Io Net | mistralai/mistral-nemo","model_id":"mistralai/mistral-nemo","model_name":"Mistral: Mistral Nemo","context_length":128000,"pricing":{"prompt":"0.000000044","completion":"0.00000016","input_cache_read":"0.000000029","discount":0},"provider_name":"Io Net","tag":"io-net/fp16","quantization":"fp16","max_completion_tokens":102400,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","seed","tools","tool_choice"],"supports_tool_choice":{"none":false,"auto":true,"required":true,"function":true},"status":-2,"uptime_last_30m":91.69574770582913,"uptime_last_5m":94.37590711175616,"uptime_last_1d":94.64042920938348,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.4e-08,"_completion_per_m":1.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.9e-08,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-nemo","model_id":"mistralai/mistral-nemo","model_name":"Mistral: Mistral Nemo","context_length":131072,"pricing":{"prompt":"0.000000165","completion":"0.000000165","input_cache_read":"0.0000000165","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":104857,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97271292814008,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.65e-07,"_completion_per_m":1.65e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.65e-08,"_cached_write_per_m":null}],"_cheapest_provider":"DeepInfra","_cheapest_blended_per_m":2.23e-08,"_priciest_blended_per_m":1.65e-07,"_provider_spread_multiplier":7.3991031390134525},{"id":"openai/gpt-4o-mini","canonical_slug":"openai/gpt-4o-mini","hugging_face_id":null,"name":"OpenAI: GPT-4o-mini","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-mini/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":11.4,"agentic_index":1}},"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-4o-mini","model_id":"openai/gpt-4o-mini","model_name":"OpenAI: GPT-4o-mini","context_length":128000,"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97550029511008,"uptime_last_5m":99.97802016649725,"uptime_last_1d":99.87128579662304,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-4o-mini","model_id":"openai/gpt-4o-mini","model_name":"OpenAI: GPT-4o-mini","context_length":128000,"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.97891694820254,"uptime_last_5m":99.98333101819698,"uptime_last_1d":99.9765522355612,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-4o-mini","model_id":"openai/gpt-4o-mini","model_name":"OpenAI: GPT-4o-mini","context_length":128000,"pricing":{"prompt":"0.000000165","completion":"0.00000066","input_cache_read":"0.0000000825","discount":0},"provider_name":"Azure","tag":"azure/swedencentral","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.65e-07,"_completion_per_m":6.6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":8.25e-08,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":2.8499999999999997e-07,"_priciest_blended_per_m":3.135e-07,"_provider_spread_multiplier":1.1},{"id":"openai/gpt-4o","canonical_slug":"openai/gpt-4o","hugging_face_id":null,"name":"OpenAI: GPT-4o","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":912,"win_rate":39.2,"rank":107},{"arena":"models","category":"codecategories","elo":885,"win_rate":34.8,"rank":119},{"arena":"models","category":"dataviz","elo":876,"win_rate":36,"rank":116},{"arena":"models","category":"gamedev","elo":942,"win_rate":42.3,"rank":114},{"arena":"models","category":"uicomponent","elo":911,"win_rate":38.1,"rank":113},{"arena":"models","category":"website","elo":851,"win_rate":31.5,"rank":124}]},"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-4o","model_id":"openai/gpt-4o","model_name":"OpenAI: GPT-4o","context_length":128000,"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.73884410128308,"uptime_last_5m":99.7628927089508,"uptime_last_1d":99.84559772941378,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":1.25e-06,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-4o","model_id":"openai/gpt-4o","model_name":"OpenAI: GPT-4o","context_length":128000,"pricing":{"prompt":"0.0000025","completion":"0.00001","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.84968057121382,"uptime_last_5m":100,"uptime_last_1d":99.94394906469935,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-06,"_completion_per_m":1e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":4.75e-06,"_priciest_blended_per_m":4.75e-06,"_provider_spread_multiplier":1.0},{"id":"mistralai/mixtral-8x22b-instruct","canonical_slug":"mistralai/mixtral-8x22b-instruct","hugging_face_id":"mistralai/Mixtral-8x22B-Instruct-v0.1","name":"Mistral: Mixtral 8x22B Instruct","created":1713312000,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","context_length":65536,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002"},"top_provider":{"context_length":65536,"max_completion_tokens":52428,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-01-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mixtral-8x22b-instruct/endpoints"},"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mixtral-8x22b-instruct","model_id":"mistralai/mixtral-8x22b-instruct","model_name":"Mistral: Mixtral 8x22B Instruct","context_length":65536,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":52428,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mixtral-8x22b-instruct","model_id":"mistralai/mixtral-8x22b-instruct","model_name":"Mistral: Mixtral 8x22B Instruct","context_length":65536,"pricing":{"prompt":"0.0000022","completion":"0.0000066","input_cache_read":"0.00000022","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":52428,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":6.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":3.2e-06,"_priciest_blended_per_m":3.52e-06,"_provider_spread_multiplier":1.1},{"id":"google/gemma-2-27b-it","canonical_slug":"google/gemma-2-27b-it","hugging_face_id":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","created":1720828800,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000065","completion":"0.00000065"},"top_provider":{"context_length":8192,"max_completion_tokens":2048,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-2-27b-it/endpoints"},"_prompt_per_m":6.5e-07,"_completion_per_m":6.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"NextBit | google/gemma-2-27b-it","model_id":"google/gemma-2-27b-it","model_name":"Google: Gemma 2 27B","context_length":8192,"pricing":{"prompt":"0.00000065","completion":"0.00000065","discount":0},"provider_name":"NextBit","tag":"nextbit/int4","quantization":"int4","max_completion_tokens":2048,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.5e-07,"_completion_per_m":6.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"NextBit","_cheapest_blended_per_m":6.5e-07,"_priciest_blended_per_m":6.5e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-4o-mini-2024-07-18","canonical_slug":"openai/gpt-4o-mini-2024-07-18","hugging_face_id":null,"name":"OpenAI: GPT-4o-mini (2024-07-18)","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-mini-2024-07-18/endpoints"},"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-4o-mini-2024-07-18","model_id":"openai/gpt-4o-mini-2024-07-18","model_name":"OpenAI: GPT-4o-mini (2024-07-18)","context_length":128000,"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":7.5e-08,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":2.8499999999999997e-07,"_priciest_blended_per_m":2.8499999999999997e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-4o-2024-05-13","canonical_slug":"openai/gpt-4o-2024-05-13","hugging_face_id":null,"name":"OpenAI: GPT-4o (2024-05-13)","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000015"},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-2024-05-13/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":24.2,"agentic_index":null}},"_prompt_per_m":5e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-4o-2024-05-13","model_id":"openai/gpt-4o-2024-05-13","model_name":"OpenAI: GPT-4o (2024-05-13)","context_length":128000,"pricing":{"prompt":"0.000005","completion":"0.000015","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.97703788748565,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-4o-2024-05-13","model_id":"openai/gpt-4o-2024-05-13","model_name":"OpenAI: GPT-4o (2024-05-13)","context_length":128000,"pricing":{"prompt":"0.000005","completion":"0.000015","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.8003992015968,"uptime_last_5m":100,"uptime_last_1d":99.90646136134696,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-06,"_completion_per_m":1.5e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":8e-06,"_priciest_blended_per_m":8e-06,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-4-turbo","canonical_slug":"openai/gpt-4-turbo","hugging_face_id":null,"name":"OpenAI: GPT-4 Turbo","created":1712620800,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00003"},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4-turbo/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":21.5,"agentic_index":null}},"_prompt_per_m":1e-05,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-4-turbo","model_id":"openai/gpt-4-turbo","model_name":"OpenAI: GPT-4 Turbo","context_length":128000,"pricing":{"prompt":"0.00001","completion":"0.00003","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":1.6e-05,"_priciest_blended_per_m":1.6e-05,"_provider_spread_multiplier":1.0},{"id":"anthropic/claude-3-haiku","canonical_slug":"anthropic/claude-3-haiku","hugging_face_id":null,"name":"Anthropic: Claude 3 Haiku","created":1710288000,"description":"Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.00000125","web_search":"0.01","input_cache_read":"0.00000003","input_cache_write":"0.0000003","input_cache_write_1h":"0.0000005"},"top_provider":{"context_length":200000,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-08-31","expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-3-haiku/endpoints"},"_prompt_per_m":2.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":3e-07,"_endpoints":[{"name":"Amazon Bedrock | anthropic/claude-3-haiku","model_id":"anthropic/claude-3-haiku","model_name":"Anthropic: Claude 3 Haiku","context_length":200000,"pricing":{"prompt":"0.00000025","completion":"0.00000125","web_search":"0.01","input_cache_read":"0.00000003","input_cache_write":"0.0000003","input_cache_write_1h":"0.0000005","discount":0},"provider_name":"Amazon Bedrock","tag":"amazon-bedrock","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.99943495482464,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.5e-07,"_completion_per_m":1.25e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":3e-08,"_cached_write_per_m":3e-07}],"_cheapest_provider":"Amazon Bedrock","_cheapest_blended_per_m":5.5e-07,"_priciest_blended_per_m":5.5e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-3.5-turbo-0613","canonical_slug":"openai/gpt-3.5-turbo-0613","hugging_face_id":null,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","created":1706140800,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","context_length":4095,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000002"},"top_provider":{"context_length":4095,"max_completion_tokens":3685,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-3.5-turbo-0613/endpoints"},"_prompt_per_m":1e-06,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-3.5-turbo-0613","model_id":"openai/gpt-3.5-turbo-0613","model_name":"OpenAI: GPT-3.5 Turbo (older v0613)","context_length":4095,"pricing":{"prompt":"0.000001","completion":"0.000002","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":3685,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-06,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":1.2999999999999998e-06,"_priciest_blended_per_m":1.2999999999999998e-06,"_provider_spread_multiplier":1.0},{"id":"mistralai/mistral-large","canonical_slug":"mistralai/mistral-large","hugging_face_id":null,"name":"Mistral Large","created":1708905600,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","context_length":128000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002"},"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-11-30","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-large/endpoints"},"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null,"_endpoints":[{"name":"Mistral | mistralai/mistral-large","model_id":"mistralai/mistral-large","model_name":"Mistral Large","context_length":128000,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0},"provider_name":"Mistral","tag":"mistral/zdr","quantization":"unknown","max_completion_tokens":102400,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":97.0873786407767,"uptime_last_5m":null,"uptime_last_1d":82.82786885245902,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-large","model_id":"mistralai/mistral-large","model_name":"Mistral Large","context_length":128000,"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0},"provider_name":"Mistral","tag":"mistral","quantization":"unknown","max_completion_tokens":102400,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":85.89149603945599,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2e-06,"_completion_per_m":6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2e-07,"_cached_write_per_m":null},{"name":"Mistral | mistralai/mistral-large","model_id":"mistralai/mistral-large","model_name":"Mistral Large","context_length":128000,"pricing":{"prompt":"0.0000022","completion":"0.0000066","input_cache_read":"0.00000022","discount":0},"provider_name":"Mistral","tag":"mistral/eu","quantization":"unknown","max_completion_tokens":102400,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":2.2e-06,"_completion_per_m":6.6e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":2.2e-07,"_cached_write_per_m":null}],"_cheapest_provider":"Mistral","_cheapest_blended_per_m":3.2e-06,"_priciest_blended_per_m":3.52e-06,"_provider_spread_multiplier":1.1},{"id":"openai/gpt-4-turbo-preview","canonical_slug":"openai/gpt-4-turbo-preview","hugging_face_id":null,"name":"OpenAI: GPT-4 Turbo Preview","created":1706140800,"description":"The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00003"},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4-turbo-preview/endpoints"},"_prompt_per_m":1e-05,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-4-turbo-preview","model_id":"openai/gpt-4-turbo-preview","model_name":"OpenAI: GPT-4 Turbo Preview","context_length":128000,"pricing":{"prompt":"0.00001","completion":"0.00003","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":null,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1e-05,"_completion_per_m":3e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":1.6e-05,"_priciest_blended_per_m":1.6e-05,"_provider_spread_multiplier":1.0},{"id":"microsoft/wizardlm-2-8x22b","canonical_slug":"microsoft/wizardlm-2-8x22b","hugging_face_id":"microsoft/WizardLM-2-8x22B","name":"WizardLM-2 8x22B","created":1713225600,"description":"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...","context_length":65535,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"vicuna"},"pricing":{"prompt":"0.00000062","completion":"0.00000062"},"top_provider":{"context_length":65535,"max_completion_tokens":8000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-04-30","expiration_date":null,"links":{"details":"/api/v1/models/microsoft/wizardlm-2-8x22b/endpoints"},"_prompt_per_m":6.2e-07,"_completion_per_m":6.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Novita | microsoft/wizardlm-2-8x22b","model_id":"microsoft/wizardlm-2-8x22b","model_name":"WizardLM-2 8x22B","context_length":65535,"pricing":{"prompt":"0.00000062","completion":"0.00000062","discount":0},"provider_name":"Novita","tag":"novita/bf16","quantization":"bf16","max_completion_tokens":8000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6.2e-07,"_completion_per_m":6.2e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Novita","_cheapest_blended_per_m":6.2e-07,"_priciest_blended_per_m":6.2e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-3.5-turbo-instruct","canonical_slug":"openai/gpt-3.5-turbo-instruct","hugging_face_id":null,"name":"OpenAI: GPT-3.5 Turbo Instruct","created":1695859200,"description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.","context_length":4095,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":"chatml"},"pricing":{"prompt":"0.0000015","completion":"0.000002"},"top_provider":{"context_length":4095,"max_completion_tokens":3685,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-3.5-turbo-instruct/endpoints"},"_prompt_per_m":1.5e-06,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-3.5-turbo-instruct","model_id":"openai/gpt-3.5-turbo-instruct","model_name":"OpenAI: GPT-3.5 Turbo Instruct","context_length":4095,"pricing":{"prompt":"0.0000015","completion":"0.000002","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":3685,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":1.5e-06,"_completion_per_m":2e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":1.6499999999999999e-06,"_priciest_blended_per_m":1.6499999999999999e-06,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-3.5-turbo-16k","canonical_slug":"openai/gpt-3.5-turbo-16k","hugging_face_id":null,"name":"OpenAI: GPT-3.5 Turbo 16k","created":1693180800,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","context_length":16385,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000004"},"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-3.5-turbo-16k/endpoints"},"_prompt_per_m":3e-06,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Azure | openai/gpt-3.5-turbo-16k","model_id":"openai/gpt-3.5-turbo-16k","model_name":"OpenAI: GPT-3.5 Turbo 16k","context_length":16385,"pricing":{"prompt":"0.000003","completion":"0.000004","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":99.52830188679245,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"OpenAI | openai/gpt-3.5-turbo-16k","model_id":"openai/gpt-3.5-turbo-16k","model_name":"OpenAI: GPT-3.5 Turbo 16k","context_length":16385,"pricing":{"prompt":"0.000003","completion":"0.000004","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-06,"_completion_per_m":4e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Azure","_cheapest_blended_per_m":3.2999999999999997e-06,"_priciest_blended_per_m":3.2999999999999997e-06,"_provider_spread_multiplier":1.0},{"id":"mancer/weaver","canonical_slug":"mancer/weaver","hugging_face_id":null,"name":"Mancer: Weaver (alpha)","created":1690934400,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","context_length":8000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":"0.0000005","completion":"0.00000075"},"top_provider":{"context_length":8000,"max_completion_tokens":6000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-06-30","expiration_date":null,"links":{"details":"/api/v1/models/mancer/weaver/endpoints"},"_prompt_per_m":5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"Mancer 2 | mancer/weaver","model_id":"mancer/weaver","model_name":"Mancer: Weaver (alpha)","context_length":8000,"pricing":{"prompt":"0.0000005","completion":"0.00000075","discount":0},"provider_name":"Mancer 2","tag":"mancer/fp8","quantization":"fp8","max_completion_tokens":6000,"max_prompt_tokens":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":7.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"Mancer 2","_cheapest_blended_per_m":5.75e-07,"_priciest_blended_per_m":5.75e-07,"_provider_spread_multiplier":1.0},{"id":"openrouter/auto","canonical_slug":"openrouter/auto","hugging_face_id":null,"name":"Auto Router","created":1699401600,"description":"The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...","context_length":2000000,"architecture":{"modality":"text+image+file+audio+video->text+image","input_modalities":["text","image","audio","file","video"],"output_modalities":["text","image"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","prediction","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openrouter/auto/endpoints"},"_prompt_per_m":-1.0,"_completion_per_m":-1.0,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[],"_cheapest_provider":null,"_cheapest_blended_per_m":-1.0,"_priciest_blended_per_m":-1.0,"_provider_spread_multiplier":null},{"id":"gryphe/mythomax-l2-13b","canonical_slug":"gryphe/mythomax-l2-13b","hugging_face_id":"Gryphe/MythoMax-L2-13b","name":"MythoMax 13B","created":1688256000,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":"0.00000006","completion":"0.00000006"},"top_provider":{"context_length":4096,"max_completion_tokens":3686,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-06-30","expiration_date":null,"links":{"details":"/api/v1/models/gryphe/mythomax-l2-13b/endpoints"},"_prompt_per_m":6e-08,"_completion_per_m":6e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"NextBit | gryphe/mythomax-l2-13b","model_id":"gryphe/mythomax-l2-13b","model_name":"MythoMax 13B","context_length":4096,"pricing":{"prompt":"0.00000006","completion":"0.00000006","discount":0},"provider_name":"NextBit","tag":"nextbit/int4","quantization":"int4","max_completion_tokens":3686,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","repetition_penalty","seed"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.55053830876973,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":6e-08,"_completion_per_m":6e-08,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Parasail | gryphe/mythomax-l2-13b","model_id":"gryphe/mythomax-l2-13b","model_name":"MythoMax 13B","context_length":4096,"pricing":{"prompt":"0.00000008","completion":"0.00000011","discount":0},"provider_name":"Parasail","tag":"parasail/fp16","quantization":"fp16","max_completion_tokens":3686,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.41520467836257,"uptime_last_5m":100,"uptime_last_1d":98.13753581661892,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":8e-08,"_completion_per_m":1.1e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"DeepInfra | gryphe/mythomax-l2-13b","model_id":"gryphe/mythomax-l2-13b","model_name":"MythoMax 13B","context_length":4096,"pricing":{"prompt":"0.0000004","completion":"0.0000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp16","quantization":"fp16","max_completion_tokens":3686,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.9026184808483,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":4e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Mancer 2 | gryphe/mythomax-l2-13b","model_id":"gryphe/mythomax-l2-13b","model_name":"MythoMax 13B","context_length":8192,"pricing":{"prompt":"0.0000004","completion":"0.0000006","discount":0},"provider_name":"Mancer 2","tag":"mancer/fp8","quantization":"fp8","max_completion_tokens":7372,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","response_format","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":99.90700557966522,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4e-07,"_completion_per_m":6e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"NextBit","_cheapest_blended_per_m":6e-08,"_priciest_blended_per_m":4.5999999999999994e-07,"_provider_spread_multiplier":7.666666666666666},{"id":"undi95/remm-slerp-l2-13b","canonical_slug":"undi95/remm-slerp-l2-13b","hugging_face_id":"Undi95/ReMM-SLERP-L2-13B","name":"ReMM SLERP 13B","created":1689984000,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","context_length":6144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":"0.00000045","completion":"0.00000065"},"top_provider":{"context_length":6144,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-06-30","expiration_date":null,"links":{"details":"/api/v1/models/undi95/remm-slerp-l2-13b/endpoints"},"_prompt_per_m":4.5e-07,"_completion_per_m":6.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"NextBit | undi95/remm-slerp-l2-13b","model_id":"undi95/remm-slerp-l2-13b","model_name":"ReMM SLERP 13B","context_length":6144,"pricing":{"prompt":"0.00000045","completion":"0.00000065","discount":0},"provider_name":"NextBit","tag":"nextbit/bf16","quantization":"bf16","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","repetition_penalty","seed"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":97.95535546801726,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":6.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Mancer 2 | undi95/remm-slerp-l2-13b","model_id":"undi95/remm-slerp-l2-13b","model_name":"ReMM SLERP 13B","context_length":6144,"pricing":{"prompt":"0.00000045","completion":"0.00000065","discount":0},"provider_name":"Mancer 2","tag":"mancer/fp8","quantization":"fp8","max_completion_tokens":5529,"max_prompt_tokens":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":99.74554707379136,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":4.5e-07,"_completion_per_m":6.5e-07,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"NextBit","_cheapest_blended_per_m":5.1e-07,"_priciest_blended_per_m":5.1e-07,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-4","canonical_slug":"openai/gpt-4","hugging_face_id":null,"name":"OpenAI: GPT-4","created":1685232000,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","context_length":8191,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00003","completion":"0.00006"},"top_provider":{"context_length":8191,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":13.1,"agentic_index":null}},"_prompt_per_m":3e-05,"_completion_per_m":6e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-4","model_id":"openai/gpt-4","model_name":"OpenAI: GPT-4","context_length":8191,"pricing":{"prompt":"0.00003","completion":"0.00006","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-05,"_completion_per_m":6e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null},{"name":"Azure | openai/gpt-4","model_id":"openai/gpt-4","model_name":"OpenAI: GPT-4","context_length":8191,"pricing":{"prompt":"0.00003","completion":"0.00006","discount":0},"provider_name":"Azure","tag":"azure","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","logit_bias","logprobs","top_logprobs","response_format","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":null,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":3e-05,"_completion_per_m":6e-05,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":3.9e-05,"_priciest_blended_per_m":3.9e-05,"_provider_spread_multiplier":1.0},{"id":"openai/gpt-3.5-turbo","canonical_slug":"openai/gpt-3.5-turbo","hugging_face_id":null,"name":"OpenAI: GPT-3.5 Turbo","created":1685232000,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","context_length":16385,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000015"},"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-3.5-turbo/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":10.7,"agentic_index":null}},"_prompt_per_m":5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null,"_endpoints":[{"name":"OpenAI | openai/gpt-3.5-turbo","model_id":"openai/gpt-3.5-turbo","model_name":"OpenAI: GPT-3.5 Turbo","context_length":16385,"pricing":{"prompt":"0.0000005","completion":"0.0000015","discount":0},"provider_name":"OpenAI","tag":"openai","quantization":"unknown","max_completion_tokens":4096,"max_prompt_tokens":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null,"_prompt_per_m":5e-07,"_completion_per_m":1.5e-06,"_image_per_m":null,"_request_per_m":null,"_cached_read_per_m":null,"_cached_write_per_m":null}],"_cheapest_provider":"OpenAI","_cheapest_blended_per_m":8e-07,"_priciest_blended_per_m":8e-07,"_provider_spread_multiplier":1.0}]}