{"data":{"models":[{"id":"claude-opus-4-1","name":"Anthropic: Claude Opus 4.1","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4-1-20250805","provider":"anthropic","author":"anthropic","version":"20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supportedPlugins":["web"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-opus-4-1-20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"20250805","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"web_search":10000,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4-1@20250805","provider":"vertex","author":"anthropic","version":"vertex-2023-10-16","ptbEnabled":true,"crossRegion":true,"pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-opus-4-1@20250805"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-opus-4-1@20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"web_search":10000,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-opus-4-1-20250805-v1:0","version":"20250805","crossRegion":true,"pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-opus-4-1-20250805-v1:0","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"20250805","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"web_search":10000,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/claude-opus-4-1-20250805","version":"20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/claude-opus-4-1-20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"20250805","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-opus-4.1","pricing":[{"threshold":0,"input":0.00001583,"output":0.00007913,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-opus-4.1","pricing":[{"threshold":0,"input":0.00001583,"output":0.00007913,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":15.83,"completion":79.13,"web_search":10000}}],"maxOutput":32000,"trainingDate":"2025-08-05T00:00:00.000Z","description":"Our most capable model with the highest level of intelligence and capability. Supports extended thinking, multilingual capabilities, and vision processing. Moderately fast latency with 32,000 max output tokens. Training data cut-off: March 2025. API model name: claude-opus-4-1-20250805","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},{"id":"claude-opus-4","name":"Anthropic: Claude Opus 4","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4-20250514","provider":"anthropic","author":"anthropic","version":"20250514","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supportedPlugins":["web"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-opus-4-20250514","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"20250514","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"web_search":10000,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4@20250514","provider":"vertex","author":"anthropic","version":"vertex-2023-10-16","ptbEnabled":true,"crossRegion":true,"pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-opus-4@20250514"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-opus-4@20250514","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"web_search":10000,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-opus-4-20250514-v1:0","version":"20250514","crossRegion":true,"pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-opus-4-20250514-v1:0","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"20250514","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"web_search":10000,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/cd-op-4-20250514","version":"20250514","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/cd-op-4-20250514","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"20250514","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-opus-4","pricing":[{"threshold":0,"input":0.00001583,"output":0.00007913,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-opus-4","pricing":[{"threshold":0,"input":0.00001583,"output":0.00007913,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":15.83,"completion":79.13,"web_search":10000}}],"maxOutput":32000,"trainingDate":"2025-05-14T00:00:00.000Z","description":"Our previous flagship model with very high intelligence and capability. Supports extended thinking, multilingual capabilities, and vision processing. Moderately fast latency with 32,000 max output tokens. Training data cut-off: March 2025. API model name: claude-opus-4-20250514","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},{"id":"claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-sonnet-4-20250514","provider":"anthropic","author":"anthropic","version":"20250514","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supportedPlugins":["web"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-sonnet-4-20250514","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250514","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"provider":"vertex","author":"anthropic","providerModelId":"claude-sonnet-4@20250514","version":"vertex-2023-10-16","ptbEnabled":true,"crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-sonnet-4@20250514"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-sonnet-4@20250514","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-sonnet-4-20250514-v1:0","version":"20250514","crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-sonnet-4-20250514-v1:0","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250514","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/cd-st-4-20250514","version":"20250514","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/cd-st-4-20250514","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250514","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-sonnet-4","pricing":[{"threshold":0,"input":0.00000633,"output":0.00002374,"web_search":0.01},{"threshold":200000,"input":0.00000633,"output":0.0000237375}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-sonnet-4","pricing":[{"threshold":0,"input":0.00000633,"output":0.00002374,"web_search":0.01},{"threshold":200000,"input":0.00000633,"output":0.0000237375}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":6.33,"completion":23.74,"web_search":10000},"pricingTiers":[{"prompt":6.33,"completion":23.74,"web_search":10000,"threshold":0},{"prompt":6.33,"completion":23.7375,"threshold":200000}]}],"maxOutput":64000,"trainingDate":"2025-05-14T00:00:00.000Z","description":"High-performance model with high intelligence and balanced performance. Supports extended thinking, multilingual capabilities, and vision processing. Fast latency with 64,000 max output tokens. API model name: claude-sonnet-4-20250514","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},{"id":"claude-3.7-sonnet","name":"Anthropic: Claude 3.7 Sonnet","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"provider":"anthropic","author":"anthropic","providerModelId":"claude-3-7-sonnet-20250219","version":"20250219","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"supportedPlugins":["web"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-3-7-sonnet-20250219","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250219","supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"provider":"vertex","author":"anthropic","providerModelId":"claude-3-7-sonnet@20250219","version":"vertex-2023-10-16","crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-3-7-sonnet@20250219","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-3-7-sonnet-20250219-v1:0","version":"20250219","crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-3-7-sonnet-20250219-v1:0","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250219","supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/cd-3-7-st-20250219","version":"20250219","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/cd-3-7-st-20250219","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250219","supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-3.7-sonnet","pricing":[{"threshold":0,"input":0.000003165,"output":0.00001583}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-3.7-sonnet","pricing":[{"threshold":0,"input":0.000003165,"output":0.00001583}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3.165,"completion":15.83}},{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"anthropic","modelConfig":{"provider":"deepinfra","author":"anthropic","providerModelId":"anthropic/claude-3-7-sonnet-latest","pricing":[{"threshold":0,"input":0.0000033,"output":0.0000165,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":200000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"anthropic/claude-3-7-sonnet-latest","pricing":[{"threshold":0,"input":0.0000033,"output":0.0000165,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":200000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3.3000000000000003,"completion":16.5,"cacheRead":0.33}}],"maxOutput":64000,"trainingDate":"2025-02-19T00:00:00.000Z","description":"High-performance model with toggleable extended thinking for complex reasoning tasks. Combines high intelligence with the ability to think through problems step-by-step. Fast latency with 64,000 max output tokens. API model name: claude-3-7-sonnet-20250219","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},{"id":"claude-3.5-sonnet-v2","name":"Anthropic: Claude 3.5 Sonnet v2","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-3-5-sonnet-20241022","provider":"anthropic","author":"anthropic","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"supportedPlugins":["web"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-3-5-sonnet-20241022","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-3-5-sonnet-v2@20241022","provider":"vertex","author":"anthropic","version":"vertex-2023-10-16","crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-3-5-sonnet-v2@20241022"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-3-5-sonnet-v2@20241022","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-3-5-sonnet-20241022-v2:0","version":"20241022","crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-3-5-sonnet-20241022-v2:0","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"version":"20241022","supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/cd-3-5-st-20241022","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/cd-3-5-st-20241022","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-3.5-sonnet","pricing":[{"threshold":0,"input":0.000003165,"output":0.00001583}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-3.5-sonnet","pricing":[{"threshold":0,"input":0.000003165,"output":0.00001583}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3.165,"completion":15.83}}],"maxOutput":8192,"trainingDate":"2024-10-22T00:00:00.000Z","description":"Our previous intelligent model with high level of intelligence and capability. Fast latency with multilingual and vision capabilities, but no extended thinking. 8,192 max output tokens. Training data cut-off: April 2024. Upgraded version API: claude-3-5-sonnet-20241022, Previous version API: claude-3-5-sonnet-20240620","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},{"id":"claude-3.5-haiku","name":"Anthropic: Claude 3.5 Haiku","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"provider":"anthropic","author":"anthropic","providerModelId":"claude-3-5-haiku-20241022","pricing":[{"threshold":0,"input":8e-7,"output":0.000004,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"supportedPlugins":["web"],"ptbEnabled":true,"endpointConfigs":{"*":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-3-5-haiku-20241022","pricing":[{"threshold":0,"input":8e-7,"output":0.000004,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":0.7999999999999999,"completion":4,"web_search":10000,"cacheRead":0.08,"cacheWrite":1}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"provider":"vertex","author":"anthropic","providerModelId":"claude-3-5-haiku@20241022","crossRegion":false,"pricing":[{"threshold":0,"input":8e-7,"output":0.000004,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"us-east5":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"us-east5","location":"us-east5","crossRegion":false},"provider":"vertex","providerModelId":"claude-3-5-haiku@20241022","pricing":[{"threshold":0,"input":8e-7,"output":0.000004,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":0.7999999999999999,"completion":4,"web_search":10000,"cacheRead":0.08,"cacheWrite":1}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-3-5-haiku-20241022-v1:0","version":"20241022","crossRegion":true,"pricing":[{"threshold":0,"input":8e-7,"output":0.000004,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"us-east-1":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-3-5-haiku-20241022-v1:0","pricing":[{"threshold":0,"input":8e-7,"output":0.000004,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"version":"20241022","supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":0.7999999999999999,"completion":4,"web_search":10000,"cacheRead":0.08,"cacheWrite":1}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/cd-3-5-hk-20241022","pricing":[{"threshold":0,"input":8e-7,"output":0.000004,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/cd-3-5-hk-20241022","pricing":[{"threshold":0,"input":8e-7,"output":0.000004,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":0.7999999999999999,"completion":4,"cacheRead":0.08,"cacheWrite":1}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-3.5-haiku","pricing":[{"threshold":0,"input":8.44e-7,"output":0.00000422}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-3.5-haiku","pricing":[{"threshold":0,"input":8.44e-7,"output":0.00000422}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":0.844,"completion":4.220000000000001}}],"maxOutput":8192,"trainingDate":"2024-10-22T00:00:00.000Z","description":"Our fastest model. Intelligence at blazing speeds. Multilingual and vision capabilities. 8,192 max output tokens. Training data cut-off: July 2024. API model name: claude-3-5-haiku-20241022","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},{"id":"claude-3-haiku-20240307","name":"Anthropic: Claude 3 Haiku","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"provider":"anthropic","author":"anthropic","providerModelId":"claude-3-haiku-20240307","pricing":[{"threshold":0,"input":2.5e-7,"output":0.00000125,"cacheMultipliers":{"cachedInput":0.12,"write5m":1.2,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":4096,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-3-haiku-20240307","pricing":[{"threshold":0,"input":2.5e-7,"output":0.00000125,"cacheMultipliers":{"cachedInput":0.12,"write5m":1.2,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":4096,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":1.25,"cacheRead":0.03,"cacheWrite":0.3}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/cd-3-hk-20240307","pricing":[{"threshold":0,"input":2.5e-7,"output":0.00000125,"cacheMultipliers":{"cachedInput":0.12,"write5m":1.2,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":4096,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/cd-3-hk-20240307","pricing":[{"threshold":0,"input":2.5e-7,"output":0.00000125,"cacheMultipliers":{"cachedInput":0.12,"write5m":1.2,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":4096,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":1.25,"cacheRead":0.03,"cacheWrite":0.3}}],"maxOutput":4096,"trainingDate":"2024-03-07T00:00:00.000Z","description":"Claude 3 Haiku is Anthropic's fastest and most compact model. Designed for near-instant responsiveness and seamless AI experiences that mimic human interactions. Multilingual and vision capabilities. 4,096 max output tokens. Training data cut-off: August 2023. API model name: claude-3-haiku-20240307","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},{"id":"claude-4.5-sonnet","name":"Anthropic: Claude Sonnet 4.5","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-sonnet-4-5-20250929","provider":"anthropic","author":"anthropic","version":"20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-sonnet-4-5-20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250929","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"provider":"vertex","author":"anthropic","providerModelId":"claude-sonnet-4-5@20250929","version":"vertex-2023-10-16","ptbEnabled":true,"crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-sonnet-4-5@20250929"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-sonnet-4-5@20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-sonnet-4-5-20250929-v1:0","version":"20250929","crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-sonnet-4-5-20250929-v1:0","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250929","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/claude-sonnet-4-5-20250929","version":"20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/claude-sonnet-4-5-20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250929","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-sonnet-4.5","pricing":[{"threshold":0,"input":0.00000633,"output":0.00002374}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-sonnet-4.5","pricing":[{"threshold":0,"input":0.00000633,"output":0.00002374}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":6.33,"completion":23.74}}],"maxOutput":64000,"trainingDate":"2025-09-29T00:00:00.000Z","description":"Best-in-class coding and agentic model with hours-long autonomous operation capabilities. Supports extended thinking, context awareness, parallel tool usage, and vision processing. Refined concise communication style with 64,000 max output tokens. API model name: claude-sonnet-4-5-20250929","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},{"id":"claude-4.5-haiku","name":"Anthropic: Claude 4.5 Haiku","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"provider":"anthropic","author":"anthropic","providerModelId":"claude-haiku-4-5-20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"supportedPlugins":["web"],"ptbEnabled":true,"endpointConfigs":{"*":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-haiku-4-5-20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":5,"web_search":10000,"cacheRead":0.09999999999999999,"cacheWrite":1.25}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"provider":"vertex","author":"anthropic","providerModelId":"claude-haiku-4-5@20251001","crossRegion":false,"pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"us-east5":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"us-east5","location":"us-east5","crossRegion":false},"provider":"vertex","providerModelId":"claude-haiku-4-5@20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":5,"web_search":10000,"cacheRead":0.09999999999999999,"cacheWrite":1.25}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-haiku-4-5-20251001-v1:0","version":"20251001","crossRegion":true,"pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"us-east-1":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-haiku-4-5-20251001-v1:0","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"version":"20251001","supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":5,"web_search":10000,"cacheRead":0.09999999999999999,"cacheWrite":1.25}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/claude-haiku-4-5-20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/claude-haiku-4-5-20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":5,"cacheRead":0.09999999999999999,"cacheWrite":1.25}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-haiku-4.5","pricing":[{"threshold":0,"input":0.00000105,"output":0.00000527}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-haiku-4.5","pricing":[{"threshold":0,"input":0.00000105,"output":0.00000527}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":1.0499999999999998,"completion":5.2700000000000005}}],"maxOutput":8192,"trainingDate":"2025-10-01T00:00:00.000Z","description":"Our fastest model. Intelligence at blazing speeds. Multilingual and vision capabilities. 8,192 max output tokens. Training data cut-off: October 2024. API model name: claude-haiku-4-5-20251001","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},{"id":"claude-sonnet-4-5-20250929","name":"Anthropic: Claude Sonnet 4.5 (20250929)","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-sonnet-4-5-20250929","provider":"anthropic","author":"anthropic","version":"20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-sonnet-4-5-20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250929","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"provider":"vertex","author":"anthropic","providerModelId":"claude-sonnet-4-5@20250929","version":"vertex-2023-10-16","ptbEnabled":true,"crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-sonnet-4-5@20250929"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-sonnet-4-5@20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-sonnet-4-5-20250929-v1:0","version":"20250929","crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-sonnet-4-5-20250929-v1:0","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250929","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/claude-sonnet-4-5-20250929","version":"20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/claude-sonnet-4-5-20250929","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}},{"threshold":200000,"input":0.000006,"output":0.0000225}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20250929","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75},"pricingTiers":[{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75,"threshold":0},{"prompt":6,"completion":22.5,"threshold":200000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-sonnet-4.5","pricing":[{"threshold":0,"input":0.00000633,"output":0.00002374},{"threshold":200000,"input":0.00000633,"output":0.0000237375}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-sonnet-4.5","pricing":[{"threshold":0,"input":0.00000633,"output":0.00002374},{"threshold":200000,"input":0.00000633,"output":0.0000237375}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":6.33,"completion":23.74},"pricingTiers":[{"prompt":6.33,"completion":23.74,"threshold":0},{"prompt":6.33,"completion":23.7375,"threshold":200000}]}],"maxOutput":64000,"trainingDate":"2025-09-29T00:00:00.000Z","description":"Best-in-class coding and agentic model with hours-long autonomous operation capabilities. Supports extended thinking, context awareness, parallel tool usage, and vision processing. Refined concise communication style with 64,000 max output tokens. API model name: claude-sonnet-4-5-20250929","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},{"id":"claude-haiku-4-5-20251001","name":"Anthropic: Claude 4.5 Haiku (20251001)","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"provider":"anthropic","author":"anthropic","providerModelId":"claude-haiku-4-5-20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"supportedPlugins":["web"],"ptbEnabled":true,"endpointConfigs":{"*":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-haiku-4-5-20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":5,"web_search":10000,"cacheRead":0.09999999999999999,"cacheWrite":1.25}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"provider":"vertex","author":"anthropic","providerModelId":"claude-haiku-4-5@20251001","crossRegion":false,"pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"us-east5":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"us-east5","location":"us-east5","crossRegion":false},"provider":"vertex","providerModelId":"claude-haiku-4-5@20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":5,"web_search":10000,"cacheRead":0.09999999999999999,"cacheWrite":1.25}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-haiku-4-5-20251001-v1:0","version":"20251001","crossRegion":true,"pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"us-east-1":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-haiku-4-5-20251001-v1:0","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"version":"20251001","supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":5,"web_search":10000,"cacheRead":0.09999999999999999,"cacheWrite":1.25}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/claude-haiku-4-5-20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}},"responseFormat":"ANTHROPIC"},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/claude-haiku-4-5-20251001","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":5,"cacheRead":0.09999999999999999,"cacheWrite":1.25}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-haiku-4.5","pricing":[{"threshold":0,"input":0.00000105,"output":0.00000527}],"contextLength":200000,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-haiku-4.5","pricing":[{"threshold":0,"input":0.00000105,"output":0.00000527}],"contextLength":200000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":1.0499999999999998,"completion":5.2700000000000005}}],"maxOutput":8192,"trainingDate":"2025-10-01T00:00:00.000Z","description":"Our fastest model. Intelligence at blazing speeds. Multilingual and vision capabilities. 8,192 max output tokens. Training data cut-off: October 2024. API model name: claude-haiku-4-5-20251001","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","top_k","stop"]},{"id":"claude-opus-4-1-20250805","name":"Anthropic: Claude Opus 4.1 (20250805)","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4-1-20250805","provider":"anthropic","author":"anthropic","version":"20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supportedPlugins":["web"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-opus-4-1-20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"20250805","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"web_search":10000,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4-1@20250805","provider":"vertex","author":"anthropic","version":"vertex-2023-10-16","ptbEnabled":true,"crossRegion":true,"pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-opus-4-1@20250805"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-opus-4-1@20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"web_search":10000,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-opus-4-1-20250805-v1:0","version":"20250805","crossRegion":true,"pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-opus-4-1-20250805-v1:0","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"20250805","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"web_search":10000,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/claude-opus-4-1-20250805","version":"20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/claude-opus-4-1-20250805","pricing":[{"threshold":0,"input":0.000015,"output":0.000075,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"version":"20250805","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":75,"cacheRead":1.5,"cacheWrite":18.75}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-opus-4.1","pricing":[{"threshold":0,"input":0.00001583,"output":0.00007913,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":32000,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-opus-4.1","pricing":[{"threshold":0,"input":0.00001583,"output":0.00007913,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":32000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":15.83,"completion":79.13,"web_search":10000}}],"maxOutput":32000,"trainingDate":"2025-08-05T00:00:00.000Z","description":"Our most capable model with the highest level of intelligence and capability. Supports extended thinking, multilingual capabilities, and vision processing. Moderately fast latency with 32,000 max output tokens. Training data cut-off: March 2025. API model name: claude-opus-4-1-20250805","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},{"id":"claude-4.5-opus","name":"Anthropic: Claude Opus 4.5","author":"anthropic","contextLength":200000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4-5-20251101","provider":"anthropic","author":"anthropic","version":"20251101","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supportedPlugins":["web"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-opus-4-5-20251101","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20251101","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":5,"completion":25,"web_search":10000,"cacheRead":0.5000000000000001,"cacheWrite":6.25}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4-5@20251101","provider":"vertex","author":"anthropic","version":"vertex-2023-10-16","ptbEnabled":true,"crossRegion":true,"pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-opus-4-5@20251101"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-opus-4-5@20251101","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":5,"completion":25,"web_search":10000,"cacheRead":0.5000000000000001,"cacheWrite":6.25}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-opus-4-5-20251101-v1:0","version":"20251101","crossRegion":true,"pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-opus-4-5-20251101-v1:0","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20251101","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":5,"completion":25,"web_search":10000,"cacheRead":0.5000000000000001,"cacheWrite":6.25}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/claude-opus-4-5-20251101","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/claude-opus-4-5-20251101","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":5,"completion":25,"web_search":10000,"cacheRead":0.5000000000000001,"cacheWrite":6.25}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-opus-4.5","pricing":[{"threshold":0,"input":0.000005275,"output":0.000026375,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-opus-4.5","pricing":[{"threshold":0,"input":0.000005275,"output":0.000026375,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":5.275,"completion":26.375,"web_search":10000}}],"maxOutput":64000,"trainingDate":"2025-11-24T00:00:00.000Z","description":"Claude Opus 4.5 is Anthropic's flagship model released November 2025, representing the highest level of intelligence and capability. Features extended thinking, multilingual capabilities, vision processing, and exceptional performance across complex reasoning tasks. Training data cut-off: March 2025. API model name: claude-opus-4-5","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},{"id":"claude-4.6-opus","name":"Anthropic: Claude Opus 4.6","author":"anthropic","contextLength":1000000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4-6-20260205","provider":"anthropic","author":"anthropic","version":"20260205","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supportedPlugins":["web"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-opus-4-6-20260205","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20260205","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":5,"completion":25,"web_search":10000,"cacheRead":0.5000000000000001,"cacheWrite":6.25}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-opus-4-6@20260205","provider":"vertex","author":"anthropic","version":"vertex-2023-10-16","ptbEnabled":true,"crossRegion":true,"pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-opus-4-6@20260205"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-opus-4-6@20260205","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"vertex-2023-10-16","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":5,"completion":25,"web_search":10000,"cacheRead":0.5000000000000001,"cacheWrite":6.25}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-opus-4-6-20260205-v1:0","version":"20260205","crossRegion":true,"pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-opus-4-6-20260205-v1:0","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20260205","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":5,"completion":25,"web_search":10000,"cacheRead":0.5000000000000001,"cacheWrite":6.25}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/claude-opus-4-6","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/claude-opus-4-6","pricing":[{"threshold":0,"input":0.000005,"output":0.000025,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":5,"completion":25,"web_search":10000,"cacheRead":0.5000000000000001,"cacheWrite":6.25}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"anthropic","modelConfig":{"provider":"openrouter","author":"anthropic","providerModelId":"anthropic/claude-opus-4.6","providerModelIdAliases":["anthropic/claude-4.6-opus-20260205","anthropic/claude-opus-4.6-20260205"],"pricing":[{"threshold":0,"input":0.000005275,"output":0.000026375,"web_search":0.01}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"anthropic/claude-opus-4.6","pricing":[{"threshold":0,"input":0.000005275,"output":0.000026375,"web_search":0.01}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":5.275,"completion":26.375,"web_search":10000}}],"maxOutput":64000,"trainingDate":"2026-02-05T00:00:00.000Z","description":"Claude Opus 4.6 is Anthropic's most capable model to date, released February 2026. Building on the intelligence of Opus 4.5, it brings new levels of reliability and precision to coding, agents, and enterprise workflows. Features a 1M context window, hybrid reasoning with extended thinking, and state-of-the-art performance on coding and agentic tasks. API model name: claude-opus-4-6","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},{"id":"claude-4.6-sonnet","name":"Anthropic: Claude Sonnet 4.6","author":"anthropic","contextLength":1000000,"endpoints":[{"provider":"anthropic","providerSlug":"anthropic","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-sonnet-4-6","provider":"anthropic","author":"anthropic","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"supportedPlugins":["web"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"anthropic","providerModelId":"claude-sonnet-4-6","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"anthropic","modelConfig":{"providerModelId":"claude-sonnet-4-6@20260217","provider":"vertex","author":"anthropic","ptbEnabled":true,"crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"responseFormat":"ANTHROPIC","endpointConfigs":{"global":{"providerModelId":"claude-sonnet-4-6@20260217"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"claude-sonnet-4-6@20260217","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"bedrock","providerSlug":"aws-bedrock","endpoint":{"author":"anthropic","modelConfig":{"provider":"bedrock","author":"anthropic","providerModelId":"anthropic.claude-sonnet-4-6-20260217-v1:0","version":"20260217","crossRegion":true,"pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"us-east-1":{}}},"userConfig":{"region":"us-east-1","location":"us-east-1","crossRegion":true},"provider":"bedrock","providerModelId":"anthropic.claude-sonnet-4-6-20260217-v1:0","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25}}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"version":"20260217","supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":10000,"cacheRead":0.30000000000000004,"cacheWrite":3.75}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"anthropic","modelConfig":{"provider":"helicone","author":"anthropic","providerModelId":"pa/claude-sonnet-4-6","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":1000000,"maxCompletionTokens":64000,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"ptbEnabled":true,"responseFormat":"ANTHROPIC","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/claude-sonnet-4-6","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"cacheMultipliers":{"cachedInput":0.1,"write5m":1.25,"write1h":2}}],"contextLength":1000000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"cacheRead":0.30000000000000004,"cacheWrite":3.75}}],"maxOutput":64000,"trainingDate":"2026-02-17T00:00:00.000Z","description":"Claude Sonnet 4.6 is Anthropic's most capable Sonnet model, released February 2026. Features near-Opus-level intelligence at Sonnet pricing, with a 1M context window, improved coding, computer use, and agentic capabilities. API model name: claude-sonnet-4-6","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_p","top_k"]},{"id":"gpt-4o","name":"OpenAI GPT-4o","author":"openai","contextLength":128000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4o","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.0000025,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"rateLimits":{"rpm":10000,"tpm":30000000,"tpd":15000000000},"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-4o","pricing":[{"threshold":0,"input":0.0000025,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":2.5,"completion":10,"web_search":10000,"cacheRead":1.25}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4o","provider":"azure","author":"openai","pricing":[{"threshold":0,"input":0.0000025,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"rateLimits":{"rpm":300,"tpm":50000},"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-4o","pricing":[{"threshold":0,"input":0.0000025,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":2.5,"completion":10,"web_search":10000,"cacheRead":1.25}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gt-4p","pricing":[{"threshold":0,"input":0.0000025,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gt-4p","pricing":[{"threshold":0,"input":0.0000025,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":2.5,"completion":10,"web_search":10000,"cacheRead":1.25}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-4o","pricing":[{"threshold":0,"input":0.00000264,"output":0.00001055,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-4o","pricing":[{"threshold":0,"input":0.00000264,"output":0.00001055,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":2.64,"completion":10.55,"web_search":10000}}],"maxOutput":16384,"trainingDate":"2024-05-13T00:00:00.000Z","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 while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},{"id":"gpt-4o-mini","name":"OpenAI GPT-4o-mini","author":"openai","contextLength":128000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4o-mini","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":1.5e-7,"output":6e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"rateLimits":{"rpm":30000,"tpm":150000000,"tpd":15000000000},"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-4o-mini","pricing":[{"threshold":0,"input":1.5e-7,"output":6e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.15,"completion":0.6,"web_search":10000,"cacheRead":0.075}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4o-mini","provider":"azure","author":"openai","pricing":[{"threshold":0,"input":1.5e-7,"output":6e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"rateLimits":{"rpm":2000,"tpm":200000},"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-4o-mini","pricing":[{"threshold":0,"input":1.5e-7,"output":6e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.15,"completion":0.6,"web_search":10000,"cacheRead":0.075}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gt-4p-m","pricing":[{"threshold":0,"input":1.5e-7,"output":6e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gt-4p-m","pricing":[{"threshold":0,"input":1.5e-7,"output":6e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.15,"completion":0.6,"web_search":10000,"cacheRead":0.075}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-4o-mini","pricing":[{"threshold":0,"input":1.6e-7,"output":6.3e-7,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-4o-mini","pricing":[{"threshold":0,"input":1.6e-7,"output":6.3e-7,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.16,"completion":0.63,"web_search":10000}}],"maxOutput":16384,"trainingDate":"2024-07-18T00:00:00.000Z","description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards.\n\nCheck out the launch announcement to learn more.\n\n#multimodal","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},{"id":"chatgpt-4o-latest","name":"OpenAI ChatGPT-4o","author":"openai","contextLength":128000,"endpoints":[{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/chatgpt-4o-latest","pricing":[{"threshold":0,"input":0.00000528,"output":0.00001582,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/chatgpt-4o-latest","pricing":[{"threshold":0,"input":0.00000528,"output":0.00001582,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":5.28,"completion":15.82,"web_search":10000}},{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"chatgpt-4o-latest","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.000005,"output":0.00002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"rateLimits":{"rpm":10000,"tpm":30000000,"tpd":15000000000},"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"chatgpt-4o-latest","pricing":[{"threshold":0,"input":0.000005,"output":0.00002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":5,"completion":20,"web_search":10000,"cacheRead":2.5}}],"maxOutput":16384,"trainingDate":"2024-08-14T00:00:00.000Z","description":"OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of GPT-4o in that it has additional RLHF. It is intended for research and evaluation.\n\nOpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},{"id":"o1","name":"OpenAI: o1","author":"openai","contextLength":200000,"endpoints":[{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/p1","pricing":[{"threshold":0,"input":0.000015,"output":0.00006,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/p1","pricing":[{"threshold":0,"input":0.000015,"output":0.00006,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":60,"web_search":10000,"cacheRead":7.5}}],"maxOutput":100000,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Reasoning model with extended thinking capabilities","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens"]},{"id":"o1-mini","name":"OpenAI: o1-mini","author":"openai","contextLength":128000,"endpoints":[{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/p1-m","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":65536,"supportedParameters":["max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/p1-m","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":128000,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.1,"completion":4.4,"web_search":10000,"cacheRead":0.55}}],"maxOutput":65536,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Efficient reasoning model","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens"]},{"id":"o3","name":"OpenAI o3","author":"openai","contextLength":200000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"o3-2025-04-16","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"rateLimits":{"rpm":10000,"tpm":30000000,"tpd":5000000000},"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"o3-2025-04-16","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":8,"web_search":10000,"cacheRead":0.5}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/p3","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["max_tokens"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/p3","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["max_tokens"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":8,"web_search":10000,"cacheRead":0.5}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/o3","pricing":[{"threshold":0,"input":0.00000211,"output":0.00000844,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/o3","pricing":[{"threshold":0,"input":0.00000211,"output":0.00000844,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":2.1100000000000003,"completion":8.440000000000001,"web_search":10000}}],"maxOutput":100000,"trainingDate":"2024-06-01T00:00:00.000Z","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. Use it to think through multi-step problems that involve analysis across text, code, and images. o3 is succeeded by GPT-5.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","max_tokens"]},{"id":"o3-pro","name":"OpenAI o3 Pro","author":"openai","contextLength":200000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"o3-pro-2025-06-10","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00002,"output":0.00008,"web_search":0.01}],"rateLimits":{"rpm":10000,"tpm":30000000,"tpd":5000000000},"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"o3-pro-2025-06-10","pricing":[{"threshold":0,"input":0.00002,"output":0.00008,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":20,"completion":80,"web_search":10000}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/p3-pro","pricing":[{"threshold":0,"input":0.00002,"output":0.00008,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["max_tokens"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/p3-pro","pricing":[{"threshold":0,"input":0.00002,"output":0.00008,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["max_tokens"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":20,"completion":80,"web_search":10000}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/o3-pro","pricing":[{"threshold":0,"input":0.0000211,"output":0.0000844,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/o3-pro","pricing":[{"threshold":0,"input":0.0000211,"output":0.0000844,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":21.1,"completion":84.4,"web_search":10000}}],"maxOutput":100000,"trainingDate":"2024-06-01T00:00:00.000Z","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 better answers. o3-pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests. Since o3-pro is designed to tackle tough problems, some requests may take several minutes to finish.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","max_tokens"]},{"id":"o3-mini","name":"OpenAI o3 Mini","author":"openai","contextLength":200000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"o3-mini","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"rateLimits":{"rpm":30000,"tpm":150000000,"tpd":15000000000},"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"o3-mini","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.1,"completion":4.4,"web_search":10000,"cacheRead":0.55}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"providerModelId":"o3-mini","provider":"azure","author":"openai","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":200000,"maxCompletionTokens":100000,"rateLimits":{"rpm":20,"tpm":200000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"o3-mini","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.1,"completion":4.4,"web_search":10000,"cacheRead":0.55}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/p3-m","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["max_tokens"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/p3-m","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["max_tokens"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.1,"completion":4.4,"web_search":10000,"cacheRead":0.55}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/o3-mini","pricing":[{"threshold":0,"input":0.00000116,"output":0.00000464,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/o3-mini","pricing":[{"threshold":0,"input":0.00000116,"output":0.00000464,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","n","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.16,"completion":4.64,"web_search":10000}}],"maxOutput":100000,"trainingDate":"2023-10-01T00:00:00.000Z","description":"o3-mini is our newest small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini supports key developer features, like Structured Outputs, function calling, and Batch API. This model supports the `reasoning_effort` parameter, which can be set to 'high', 'medium', or 'low' to control the thinking time of the model.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","max_tokens"]},{"id":"o4-mini","name":"OpenAI o4 Mini","author":"openai","contextLength":200000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"o4-mini","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"rateLimits":{"rpm":30000,"tpm":150000000,"tpd":15000000000},"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"o4-mini","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"]},"supportsPtb":true,"pricing":{"prompt":1.1,"completion":4.4,"web_search":10000,"cacheRead":0.275}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"providerModelId":"o4-mini","provider":"azure","author":"openai","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"rateLimits":{"rpm":20,"tpm":20000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"o4-mini","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"]},"supportsPtb":true,"pricing":{"prompt":1.1,"completion":4.4,"web_search":10000,"cacheRead":0.275}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/o4-mini","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/o4-mini","pricing":[{"threshold":0,"input":0.0000011,"output":0.0000044,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.1,"completion":4.4,"web_search":10000,"cacheRead":0.275}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/o4-mini","pricing":[{"threshold":0,"input":0.00000116,"output":0.00000464,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/o4-mini","pricing":[{"threshold":0,"input":0.00000116,"output":0.00000464,"web_search":0.01}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"]},"supportsPtb":true,"pricing":{"prompt":1.16,"completion":4.64,"web_search":10000}}],"maxOutput":100000,"trainingDate":"2024-06-01T00:00:00.000Z","description":"o4-mini is our latest small o-series model. It's optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks. It's succeeded by GPT-5 mini.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","max_tokens"]},{"id":"gpt-4.1","name":"OpenAI GPT-4.1","author":"openai","contextLength":1047576,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4.1","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"rateLimits":{"rpm":10000,"tpm":30000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-4.1","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":8,"web_search":10000,"cacheRead":0.5}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4.1","provider":"azure","author":"openai","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"rateLimits":{"rpm":50,"tpm":50000},"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-4.1","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":8,"web_search":10000,"cacheRead":0.5}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gt-4.1","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gt-4.1","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":8,"web_search":10000,"cacheRead":0.5}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-4.1","pricing":[{"threshold":0,"input":0.00000211,"output":0.00000844,"web_search":0.01}],"contextLength":1047576,"maxCompletionTokens":32768,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-4.1","pricing":[{"threshold":0,"input":0.00000211,"output":0.00000844,"web_search":0.01}],"contextLength":1047576,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":2.1100000000000003,"completion":8.440000000000001,"web_search":10000}}],"maxOutput":32768,"trainingDate":"2025-04-14T17:23:05.000Z","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 GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},{"id":"gpt-4.1-mini","name":"OpenAI GPT-4.1 Mini","author":"openai","contextLength":1047576,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4.1-mini","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":4e-7,"output":0.0000016,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"rateLimits":{"rpm":30000,"tpm":150000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-4.1-mini","pricing":[{"threshold":0,"input":4e-7,"output":0.0000016,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.39999999999999997,"completion":1.5999999999999999,"web_search":10000,"cacheRead":0.09999999999999999}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4.1-mini","provider":"azure","author":"openai","pricing":[{"threshold":0,"input":4e-7,"output":0.0000016,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"rateLimits":{"rpm":200,"tpm":200000},"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-4.1-mini","pricing":[{"threshold":0,"input":4e-7,"output":0.0000016,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.39999999999999997,"completion":1.5999999999999999,"web_search":10000,"cacheRead":0.09999999999999999}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gt-4.1-m","pricing":[{"threshold":0,"input":4e-7,"output":0.0000016,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gt-4.1-m","pricing":[{"threshold":0,"input":4e-7,"output":0.0000016,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.39999999999999997,"completion":1.5999999999999999,"web_search":10000,"cacheRead":0.09999999999999999}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-4.1-mini","pricing":[{"threshold":0,"input":4.2e-7,"output":0.00000169,"web_search":0.01}],"contextLength":1047576,"maxCompletionTokens":32768,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-4.1-mini","pricing":[{"threshold":0,"input":4.2e-7,"output":0.00000169,"web_search":0.01}],"contextLength":1047576,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.42,"completion":1.69,"web_search":10000}}],"maxOutput":32768,"trainingDate":"2025-04-14T17:23:01.000Z","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 instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider's polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},{"id":"gpt-4.1-nano","name":"OpenAI GPT-4.1 Nano","author":"openai","contextLength":1047576,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4.1-nano","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"rateLimits":{"rpm":30000,"tpm":150000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-4.1-nano","pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.09999999999999999,"completion":0.39999999999999997,"web_search":10000,"cacheRead":0.024999999999999998}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-4.1-nano","provider":"azure","author":"openai","pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"rateLimits":{"rpm":200,"tpm":200000},"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-4.1-nano","pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":1047576,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.09999999999999999,"completion":0.39999999999999997,"web_search":10000,"cacheRead":0.024999999999999998}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gt-4.1-n","pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":128000,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","temperature","top_p","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gt-4.1-n","pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":128000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop"]},"supportsPtb":true,"pricing":{"prompt":0.09999999999999999,"completion":0.39999999999999997,"web_search":10000,"cacheRead":0.024999999999999998}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-4.1-nano","pricing":[{"threshold":0,"input":1.1e-7,"output":4.2e-7,"web_search":0.01}],"contextLength":1047576,"maxCompletionTokens":32768,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-4.1-nano","pricing":[{"threshold":0,"input":1.1e-7,"output":4.2e-7,"web_search":0.01}],"contextLength":1047576,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.11,"completion":0.42,"web_search":10000}}],"maxOutput":32768,"trainingDate":"2025-04-14T17:22:49.000Z","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 token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT-4o mini. It's ideal for tasks like classification or autocompletion.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty"]},{"id":"gpt-5","name":"OpenAI GPT-5","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":272000,"maxCompletionTokens":128000,"rateLimits":{"rpm":500},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":272000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.13}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.32,"completion":10.55,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-01-01T00:00:00.000Z","description":"GPT-5 is OpenAI's most advanced language model, featuring enhanced reasoning capabilities with 80% fewer factual errors than o3. It supports a 400K total context (272K input + 128K output), advanced tool calling with reliable chaining of dozens of calls, and a new verbosity parameter for response length control. Ideal for complex reasoning, multi-step planning, and applications requiring high accuracy.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"]},{"id":"gpt-5-mini","name":"OpenAI GPT-5 Mini","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-mini","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":30000,"tpm":180000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5-mini","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":2,"web_search":10000,"cacheRead":0.024999999999999998}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-mini","provider":"azure","author":"openai","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.12}}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","structured_outputs"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5-mini","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.12}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","structured_outputs"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":2,"web_search":10000,"cacheRead":0.03}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5-mini","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5-mini","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":2,"web_search":10000,"cacheRead":0.024999999999999998}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5-mini","pricing":[{"threshold":0,"input":2.6e-7,"output":0.00000211,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5-mini","pricing":[{"threshold":0,"input":2.6e-7,"output":0.00000211,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.26,"completion":2.1100000000000003,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-01-01T00:00:00.000Z","description":"GPT-5 Mini delivers GPT-5-level performance at a fraction of the cost and latency. With the same 400K context window and advanced capabilities including tool calling and verbosity control, it's optimized for speed and efficiency while maintaining strong reasoning and instruction-following capabilities. Perfect for high-volume applications requiring advanced AI capabilities with resource constraints.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","structured_outputs"]},{"id":"gpt-5-nano","name":"OpenAI GPT-5 Nano","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-nano","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":30000,"tpm":180000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5-nano","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","stop"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.39999999999999997,"web_search":10000,"cacheRead":0.005}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5-nano","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":8192,"supportedParameters":["max_completion_tokens"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5-nano","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_completion_tokens"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","stop"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.39999999999999997,"web_search":10000,"cacheRead":0.005}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5-nano","pricing":[{"threshold":0,"input":5e-8,"output":4.2e-7,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5-nano","pricing":[{"threshold":0,"input":5e-8,"output":4.2e-7,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","stop"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.42,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-01-01T00:00:00.000Z","description":"GPT-5 Nano is the smallest and fastest model in the GPT-5 family, designed for ultra-low latency applications. Despite its compact size, it maintains the full 400K context window and delivers impressive performance on classification, completion, and simple reasoning tasks. Ideal for real-time applications, edge deployments, and high-throughput scenarios.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","verbosity"]},{"id":"gpt-5-chat-latest","name":"OpenAI GPT-5 Chat Latest","author":"openai","contextLength":128000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-chat-latest","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5-chat-latest","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5-chat-latest","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5-chat-latest","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5-chat","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5-chat","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"]},"supportsPtb":true,"pricing":{"prompt":1.32,"completion":10.55,"web_search":10000}}],"maxOutput":16384,"trainingDate":"2024-09-30T00:00:00.000Z","description":"GPT-5 Chat Latest is a continuously updated version of GPT-5 optimized for conversational interactions. It receives regular updates with the latest improvements in dialogue management, safety, and helpfulness. Features a 128K context window and 16K max output tokens, making it ideal for focused conversations. Knowledge cutoff: September 30, 2024.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"]},{"id":"gpt-5-pro","name":"OpenAI: GPT-5 Pro","author":"openai","contextLength":128000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-pro","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"rateLimits":{"rpm":10000,"tpm":30000000,"tpd":5000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5-pro","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":120,"web_search":10000}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5-pro","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"rateLimits":{"rpm":50,"tpm":100000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5-pro","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":120,"web_search":10000}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5-pro","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5-pro","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":120,"web_search":10000}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5-pro","pricing":[{"threshold":0,"input":0.00001583,"output":0.0001266,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5-pro","pricing":[{"threshold":0,"input":0.00001583,"output":0.0001266,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15.83,"completion":126.6,"web_search":10000}}],"maxOutput":32768,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Most capable GPT-5 model with extended thinking capabilities","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"]},{"id":"gpt-5-codex","name":"OpenAI: GPT-5 Codex","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-codex","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5-codex","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5-codex","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5-codex","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5-codex","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5-codex","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"]},"supportsPtb":true,"pricing":{"prompt":1.32,"completion":10.55,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Specialized model for code generation and analysis","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"]},{"id":"gpt-5-2025-08-07","name":"OpenAI GPT-5","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-2025-08-07","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5-2025-08-07","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5-2025-08-07","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":50,"tpm":100000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5-2025-08-07","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.13}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5-2025-08-07","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5-2025-08-07","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"openai","modelConfig":{"provider":"novita","author":"openai","providerModelId":"pa/gpt-5-2025-08-07","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"pa/gpt-5-2025-08-07","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5-2025-08-07","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5-2025-08-07","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.32,"completion":10.55,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-08-07T00:00:00.000Z","description":"GPT-5 is OpenAI's most advanced language model, featuring enhanced reasoning capabilities with 80% fewer factual errors than o3. It supports a 400K total context (272K input + 128K output), advanced tool calling with reliable chaining of dozens of calls, and a new verbosity parameter for response length control. Ideal for complex reasoning, multi-step planning, and applications requiring high accuracy.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"pinnedVersionOfModel":"gpt-5"},{"id":"gpt-5-mini-2025-08-07","name":"OpenAI GPT-5 Mini","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-mini-2025-08-07","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":30000,"tpm":180000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5-mini-2025-08-07","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":2,"web_search":10000,"cacheRead":0.024999999999999998}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5-mini-2025-08-07","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":200,"tpm":200000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5-mini-2025-08-07","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":2,"web_search":10000,"cacheRead":0.026}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5-mini-2025-08-07","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5-mini-2025-08-07","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":2,"web_search":10000,"cacheRead":0.024999999999999998}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"openai","modelConfig":{"provider":"novita","author":"openai","providerModelId":"pa/gpt-5-mini-2025-08-07","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"pa/gpt-5-mini-2025-08-07","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":2,"web_search":10000,"cacheRead":0.024999999999999998}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5-mini-2025-08-07","pricing":[{"threshold":0,"input":2.6e-7,"output":0.00000211,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5-mini-2025-08-07","pricing":[{"threshold":0,"input":2.6e-7,"output":0.00000211,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.26,"completion":2.1100000000000003,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-08-07T00:00:00.000Z","description":"GPT-5 Mini delivers GPT-5-level performance at a fraction of the cost and latency. With the same 400K context window and advanced capabilities including tool calling and verbosity control, it's optimized for speed and efficiency while maintaining strong reasoning and instruction-following capabilities. Perfect for high-volume applications requiring advanced AI capabilities with resource constraints.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"pinnedVersionOfModel":"gpt-5-mini"},{"id":"gpt-5-nano-2025-08-07","name":"OpenAI GPT-5 Nano","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-nano-2025-08-07","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":30000,"tpm":180000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5-nano-2025-08-07","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.39999999999999997,"web_search":10000,"cacheRead":0.005}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5-nano-2025-08-07","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":200,"tpm":200000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5-nano-2025-08-07","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.39999999999999997,"web_search":10000,"cacheRead":0.0052}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5-nano-2025-08-07","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5-nano-2025-08-07","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.39999999999999997,"web_search":10000,"cacheRead":0.005}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"openai","modelConfig":{"provider":"novita","author":"openai","providerModelId":"pa/gpt-5-nano-2025-08-07","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"pa/gpt-5-nano-2025-08-07","pricing":[{"threshold":0,"input":5e-8,"output":4e-7,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.39999999999999997,"web_search":10000,"cacheRead":0.005}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5-nano-2025-08-07","pricing":[{"threshold":0,"input":5e-8,"output":4.2e-7,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5-nano-2025-08-07","pricing":[{"threshold":0,"input":5e-8,"output":4.2e-7,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.42,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-08-07T00:00:00.000Z","description":"GPT-5 Nano is the smallest and fastest model in the GPT-5 family, designed for ultra-low latency applications. Despite its compact size, it maintains the full 400K context window and delivers impressive performance on classification, completion, and simple reasoning tasks. Ideal for real-time applications, edge deployments, and high-throughput scenarios.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"pinnedVersionOfModel":"gpt-5-nano"},{"id":"gpt-5-pro-2025-10-01","name":"OpenAI: GPT-5 Pro","author":"openai","contextLength":128000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5-pro-2025-10-01","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"rateLimits":{"rpm":10000,"tpm":30000000,"tpd":5000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5-pro-2025-10-01","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":120,"web_search":10000}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5-pro-2025-10-01","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"rateLimits":{"rpm":50,"tpm":100000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5-pro-2025-10-01","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":120,"web_search":10000}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5-pro-2025-10-01","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5-pro-2025-10-01","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":120,"web_search":10000}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"openai","modelConfig":{"provider":"novita","author":"openai","providerModelId":"pa/gpt-5-pro-2025-10-01","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"pa/gpt-5-pro-2025-10-01","pricing":[{"threshold":0,"input":0.000015,"output":0.00012,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15,"completion":120,"web_search":10000}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5-pro-2025-10-01","pricing":[{"threshold":0,"input":0.00001583,"output":0.0001266,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5-pro-2025-10-01","pricing":[{"threshold":0,"input":0.00001583,"output":0.0001266,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":15.83,"completion":126.6,"web_search":10000}}],"maxOutput":32768,"trainingDate":"2025-10-01T00:00:00.000Z","description":"Most capable GPT-5 model with extended thinking capabilities","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"pinnedVersionOfModel":"gpt-5-pro"},{"id":"gpt-5.1","name":"OpenAI GPT-5.1","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.1","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.1","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.1","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.1","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.32,"completion":10.55,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-01-01T00:00:00.000Z","description":"GPT-5.1 is an enhanced version of GPT-5 with improved performance and capabilities. It features the same 400K context window and advanced tool calling capabilities as GPT-5, with optimized pricing for better cost efficiency.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"]},{"id":"gpt-5.1-codex","name":"OpenAI: GPT-5.1 Codex","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.1-codex","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.1-codex","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.1-codex","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.1-codex","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"]},"supportsPtb":true,"pricing":{"prompt":1.32,"completion":10.55,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Specialized model for code generation and analysis, based on GPT-5.1","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"]},{"id":"gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1 Codex Mini","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.1-codex-mini","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":30000,"tpm":180000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.1-codex-mini","pricing":[{"threshold":0,"input":2.5e-7,"output":0.000002,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":2,"web_search":10000,"cacheRead":0.024999999999999998}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.1-codex-mini","pricing":[{"threshold":0,"input":2.6e-7,"output":0.00000211,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.1-codex-mini","pricing":[{"threshold":0,"input":2.6e-7,"output":0.00000211,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"]},"supportsPtb":true,"pricing":{"prompt":0.26,"completion":2.1100000000000003,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Compact specialized model for code generation and analysis, based on GPT-5.1","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"]},{"id":"gpt-5.1-chat-latest","name":"OpenAI GPT-5.1 Chat","author":"openai","contextLength":128000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.1-chat-latest","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.1-chat-latest","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.1-chat","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.1-chat","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"]},"supportsPtb":true,"pricing":{"prompt":1.32,"completion":10.55,"web_search":10000}}],"maxOutput":16384,"trainingDate":"2025-01-01T00:00:00.000Z","description":"GPT-5.1 Chat is a continuously updated version of GPT-5.1 optimized for conversational interactions. It receives regular updates with the latest improvements in dialogue management, safety, and helpfulness. Features a 128K context window and 16K max output tokens, making it ideal for focused conversations.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"]},{"id":"codex-mini-latest","name":"OpenAI Codex Mini Latest","author":"openai","contextLength":200000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"codex-mini-latest","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.0000015,"output":0.000006,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"rateLimits":{"rpm":30000,"tpm":180000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"codex-mini-latest","pricing":[{"threshold":0,"input":0.0000015,"output":0.000006,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":200000,"maxCompletionTokens":100000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","verbosity"]},"supportsPtb":true,"pricing":{"prompt":1.5,"completion":6,"web_search":10000,"cacheRead":0.375}}],"maxOutput":100000,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Latest version of Codex Mini, a compact specialized model for code generation and analysis","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"]},{"id":"gpt-5.1-2025-11-13","name":"OpenAI GPT-5.1","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.1-2025-11-13","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.1-2025-11-13","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5.1-2025-11-13","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":50,"tpm":100000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5.1-2025-11-13","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.104}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.13}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5.1-2025-11-13","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5.1-2025-11-13","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"openai","modelConfig":{"provider":"novita","author":"openai","providerModelId":"pa/gpt-5.1-2025-11-13","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"pa/gpt-5.1-2025-11-13","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"web_search":10000,"cacheRead":0.12500000000000003}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.1-2025-11-13","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.1-2025-11-13","pricing":[{"threshold":0,"input":0.00000132,"output":0.00001055,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.32,"completion":10.55,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-11-13T00:00:00.000Z","description":"GPT-5.1 is an enhanced version of GPT-5 with improved performance and capabilities. It features the same 400K context window and advanced tool calling capabilities as GPT-5, with optimized pricing for better cost efficiency.","inputModalities":["text","image"],"outputModalities":["text","image"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"pinnedVersionOfModel":"gpt-5.1"},{"id":"gpt-5.2","name":"OpenAI GPT-5.2","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.2","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.2","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.75,"completion":14,"web_search":10000,"cacheRead":0.17500000000000002}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5.2","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5.2","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":1.75,"completion":14,"web_search":10000,"cacheRead":0.17500000000000002}},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5.2","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":50,"tpm":100000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":false,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5.2","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":false,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":false,"pricing":{"prompt":1.75,"completion":14,"web_search":10000,"cacheRead":0.17500000000000002}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.2","pricing":[{"threshold":0,"input":0.00000185,"output":0.00001477,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.2","pricing":[{"threshold":0,"input":0.00000185,"output":0.00001477,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[]},"supportsPtb":true,"pricing":{"prompt":1.85,"completion":14.77,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-12-11T00:00:00.000Z","description":"GPT-5.2 is our best general-purpose model, part of the GPT-5 flagship model family. Our most intelligent model yet for both general and agentic tasks, GPT-5.2 shows improvements over the previous GPT-5.1 in:\n- General intelligence\n- Instruction following\n- Accuracy and token efficiency\n- Multimodality—especially vision\n- Code generation—especially front-end UI creation\n- Tool calling and context management in the API\n- Spreadsheet understanding and creation\n- Unlike the previous GPT-5.1 model, GPT-5.2 has new features for managing what the model knows and remembers to improve accuracy.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs"]},{"id":"gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","author":"openai","contextLength":400000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.2-pro","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.000021,"output":0.000168,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"rateLimits":{"rpm":10000,"tpm":30000000,"tpd":5000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.2-pro","pricing":[{"threshold":0,"input":0.000021,"output":0.000168,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":21,"completion":168,"web_search":10000}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5.2-pro","pricing":[{"threshold":0,"input":0.000021,"output":0.000168,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5.2-pro","pricing":[{"threshold":0,"input":0.000021,"output":0.000168,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":21,"completion":168,"web_search":10000}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.2-pro","pricing":[{"threshold":0,"input":0.00002216,"output":0.00017724,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.2-pro","pricing":[{"threshold":0,"input":0.00002216,"output":0.00017724,"web_search":0.01}],"contextLength":400000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[]},"supportsPtb":true,"pricing":{"prompt":22.16,"completion":177.24,"web_search":10000}}],"maxOutput":128000,"trainingDate":"2025-12-11T00:00:00.000Z","description":"Tough problems that may take longer to solve but require harder thinking","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs"]},{"id":"gpt-5.2-chat-latest","name":"OpenAI GPT-5.2 Chat","author":"openai","contextLength":128000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.2-chat-latest","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.2-chat-latest","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"]},"supportsPtb":true,"pricing":{"prompt":1.75,"completion":14,"web_search":10000,"cacheRead":0.17500000000000002}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5.2-chat-latest","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5.2-chat-latest","pricing":[{"threshold":0,"input":0.00000175,"output":0.000014,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens","n"]},"supportsPtb":true,"pricing":{"prompt":1.75,"completion":14,"web_search":10000,"cacheRead":0.17500000000000002}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.2-chat","pricing":[{"threshold":0,"input":0.00000185,"output":0.00001477,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.2-chat","pricing":[{"threshold":0,"input":0.00000185,"output":0.00001477,"web_search":0.01}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[]},"supportsPtb":true,"pricing":{"prompt":1.85,"completion":14.77,"web_search":10000}}],"maxOutput":16384,"trainingDate":"2025-12-11T00:00:00.000Z","description":"GPT-5.2 Chat is a continuously updated version of GPT-5.2 optimized for conversational interactions. It receives regular updates with the latest improvements in dialogue management, safety, and helpfulness. Features a 128K context window and 16K max output tokens, making it ideal for focused conversations.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs"]},{"id":"gpt-5.4","name":"OpenAI GPT-5.4","author":"openai","contextLength":1050000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.4","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":1050000,"maxCompletionTokens":128000,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.4","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":1050000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006},"pricingTiers":[{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006,"threshold":0},{"prompt":5,"completion":22.5,"threshold":272000}]},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5.4","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":1050000,"maxCompletionTokens":128000,"rateLimits":{"rpm":50,"tpm":100000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":false,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5.4","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":1050000,"maxCompletionTokens":128000,"ptbEnabled":false,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":false,"pricing":{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006},"pricingTiers":[{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006,"threshold":0},{"prompt":5,"completion":22.5,"threshold":272000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5.4","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5.4","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006},"pricingTiers":[{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006,"threshold":0},{"prompt":5,"completion":22.5,"threshold":272000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.4","pricing":[{"threshold":0,"input":0.0000026375,"output":0.000015825,"web_search":0.01},{"threshold":272000,"input":0.000005275,"output":0.0000237375}],"contextLength":1050000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.4","pricing":[{"threshold":0,"input":0.0000026375,"output":0.000015825,"web_search":0.01},{"threshold":272000,"input":0.000005275,"output":0.0000237375}],"contextLength":1050000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[]},"supportsPtb":true,"pricing":{"prompt":2.6375,"completion":15.825,"web_search":10000},"pricingTiers":[{"prompt":2.6375,"completion":15.825,"web_search":10000,"threshold":0},{"prompt":5.275,"completion":23.7375,"threshold":272000}]}],"maxOutput":128000,"trainingDate":"2026-03-05T00:00:00.000Z","description":"GPT-5.4 is our frontier model for complex professional work. Reasoning.effort supports: none (default), low, medium, high and xhigh. Features a 1.05M context window and 128K max output tokens with improvements in general intelligence, instruction following, accuracy, multimodality, code generation, tool calling, and context management over GPT-5.2.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs"]},{"id":"gpt-5.4-2026-03-05","name":"OpenAI GPT-5.4","author":"openai","contextLength":1050000,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-5.4-2026-03-05","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":1050000,"maxCompletionTokens":128000,"rateLimits":{"rpm":15000,"tpm":40000000,"tpd":15000000000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-5.4-2026-03-05","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":1050000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006},"pricingTiers":[{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006,"threshold":0},{"prompt":5,"completion":22.5,"threshold":272000}]},{"provider":"azure","providerSlug":"azure","endpoint":{"author":"openai","modelConfig":{"provider":"azure","author":"openai","providerModelId":"gpt-5.4-2026-03-05","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":1050000,"maxCompletionTokens":128000,"rateLimits":{"rpm":50,"tpm":100000},"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":false,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"azure","providerModelId":"gpt-5.4-2026-03-05","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":1050000,"maxCompletionTokens":128000,"ptbEnabled":false,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs"],"unsupportedParameters":["presence_penalty","frequency_penalty","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":false,"pricing":{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006},"pricingTiers":[{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006,"threshold":0},{"prompt":5,"completion":22.5,"threshold":272000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"openai","modelConfig":{"provider":"helicone","author":"openai","providerModelId":"pa/gpt-5.4-2026-03-05","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gpt-5.4-2026-03-05","pricing":[{"threshold":0,"input":0.0000025,"output":0.000015,"web_search":0.01,"cacheMultipliers":{"cachedInput":0.1}},{"threshold":272000,"input":0.000005,"output":0.0000225}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_completion_tokens","stop"],"unsupportedParameters":["temperature","top_p","presence_penalty","frequency_penalty","logprobs","top_logprobs","logit_bias","max_tokens"]},"supportsPtb":true,"pricing":{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006},"pricingTiers":[{"prompt":2.5,"completion":15,"web_search":10000,"cacheRead":0.25000000000000006,"threshold":0},{"prompt":5,"completion":22.5,"threshold":272000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-5.4-2026-03-05","pricing":[{"threshold":0,"input":0.0000026375,"output":0.000015825,"web_search":0.01},{"threshold":272000,"input":0.000005275,"output":0.0000237375}],"contextLength":1050000,"maxCompletionTokens":128000,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-5.4-2026-03-05","pricing":[{"threshold":0,"input":0.0000026375,"output":0.000015825,"web_search":0.01},{"threshold":272000,"input":0.000005275,"output":0.0000237375}],"contextLength":1050000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs","verbosity"],"unsupportedParameters":[]},"supportsPtb":true,"pricing":{"prompt":2.6375,"completion":15.825,"web_search":10000},"pricingTiers":[{"prompt":2.6375,"completion":15.825,"web_search":10000,"threshold":0},{"prompt":5.275,"completion":23.7375,"threshold":272000}]}],"maxOutput":128000,"trainingDate":"2026-03-05T00:00:00.000Z","description":"GPT-5.4 is our frontier model for complex professional work. Reasoning.effort supports: none (default), low, medium, high and xhigh. Features a 1.05M context window and 128K max output tokens with improvements in general intelligence, instruction following, accuracy, multimodality, code generation, tool calling, and context management over GPT-5.2.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_completion_tokens","response_format","stop","verbosity","temperature","top_p","logprobs","presence_penalty","frequency_penalty","logit_bias","max_tokens","top_logprobs"],"pinnedVersionOfModel":"gpt-5.4"},{"id":"gpt-oss-120b","name":"OpenAI GPT-OSS 120b","author":"openai","contextLength":131072,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"openai","modelConfig":{"providerModelId":"openai/gpt-oss-120b","provider":"deepinfra","author":"openai","pricing":[{"threshold":0,"input":4e-8,"output":1.6e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"quantization":"fp4","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"openai/gpt-oss-120b","pricing":[{"threshold":0,"input":4e-8,"output":1.6e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.04,"completion":0.16,"web_search":10000}},{"provider":"baseten","providerSlug":"baseten","endpoint":{"author":"openai","modelConfig":{"providerModelId":"openai/gpt-oss-120b","provider":"baseten","author":"openai","pricing":[{"threshold":0,"input":1e-7,"output":5e-7}],"contextLength":128072,"maxCompletionTokens":128072,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","stop","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"baseten","providerModelId":"openai/gpt-oss-120b","pricing":[{"threshold":0,"input":1e-7,"output":5e-7}],"contextLength":128072,"maxCompletionTokens":128072,"ptbEnabled":true,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","stop","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":0.09999999999999999,"completion":0.5}},{"provider":"groq","providerSlug":"groq","endpoint":{"author":"openai","modelConfig":{"providerModelId":"openai/gpt-oss-120b","provider":"groq","author":"openai","pricing":[{"threshold":0,"input":1.5e-7,"output":7.5e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":65536,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"openai/gpt-oss-120b","pricing":[{"threshold":0,"input":1.5e-7,"output":7.5e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.15,"completion":0.75,"web_search":10000}},{"provider":"cerebras","providerSlug":"cerebras","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-oss-120b","provider":"cerebras","author":"openai","pricing":[{"threshold":0,"input":3.5e-7,"output":7.5e-7}],"contextLength":131072,"maxCompletionTokens":40000,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","seed","logprobs","top_logprobs","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"cerebras","providerModelId":"gpt-oss-120b","pricing":[{"threshold":0,"input":3.5e-7,"output":7.5e-7}],"contextLength":131072,"maxCompletionTokens":40000,"ptbEnabled":true,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","seed","logprobs","top_logprobs","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":0.35,"completion":0.75}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-oss-120b","pricing":[{"threshold":0,"input":3.7e-7,"output":7.9e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-oss-120b","pricing":[{"threshold":0,"input":3.7e-7,"output":7.9e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.37,"completion":0.7899999999999999,"web_search":10000}}],"maxOutput":131072,"trainingDate":"2024-06-01T00:00:00.000Z","description":"gpt-oss-120b is our most powerful open-weight model, which fits into a single H100 GPU (117B parameters with 5.1B active parameters). Features permissive Apache 2.0 license, configurable reasoning effort (low, medium, high), full chain-of-thought access, fine-tunable parameters, and agentic capabilities including function calling, web browsing, Python code execution, and structured outputs.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p","max_tokens"]},{"id":"gpt-oss-20b","name":"OpenAI GPT-OSS 20b","author":"openai","contextLength":131072,"endpoints":[{"provider":"novita","providerSlug":"novita","endpoint":{"author":"openai","modelConfig":{"provider":"novita","author":"openai","providerModelId":"openai/gpt-oss-20b","pricing":[{"threshold":0,"input":5e-8,"output":2e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":32768,"quantization":"bf16","supportedParameters":["structured_outputs","reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"openai/gpt-oss-20b","pricing":[{"threshold":0,"input":5e-8,"output":2e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["structured_outputs","reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.19999999999999998,"web_search":10000}},{"provider":"groq","providerSlug":"groq","endpoint":{"author":"openai","modelConfig":{"providerModelId":"openai/gpt-oss-20b","provider":"groq","author":"openai","pricing":[{"threshold":0,"input":1e-7,"output":5e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":65536,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"openai/gpt-oss-20b","pricing":[{"threshold":0,"input":1e-7,"output":5e-7,"web_search":0.01}],"contextLength":131072,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.09999999999999999,"completion":0.5,"web_search":10000}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"openai","modelConfig":{"provider":"openrouter","author":"openai","providerModelId":"openai/gpt-oss-20b","pricing":[{"threshold":0,"input":1.1e-7,"output":5.3e-7,"web_search":0.01}],"contextLength":131000,"maxCompletionTokens":131000,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"openai/gpt-oss-20b","pricing":[{"threshold":0,"input":1.1e-7,"output":5.3e-7,"web_search":0.01}],"contextLength":131000,"maxCompletionTokens":131000,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.11,"completion":0.53,"web_search":10000}}],"maxOutput":131072,"trainingDate":"2024-06-01T00:00:00.000Z","description":"gpt-oss-20b is our medium-sized open-weight model for low latency, local, or specialized use-cases (21B parameters with 3.6B active parameters). Features permissive Apache 2.0 license, configurable reasoning effort (low, medium, high), full chain-of-thought access, fine-tunable parameters, and agentic capabilities including function calling, web browsing, Python code execution, and structured outputs.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p","max_tokens"]},{"id":"gpt-image-1","name":"OpenAI GPT Image 1","author":"openai","contextLength":8192,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-image-1","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.00000625,"output":0.0000125}],"contextLength":8192,"maxCompletionTokens":4096,"rateLimits":{"rpm":500,"tpm":1000000},"supportedParameters":["n"],"ptbEnabled":false,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-image-1","pricing":[{"threshold":0,"input":0.00000625,"output":0.0000125}],"contextLength":8192,"maxCompletionTokens":4096,"ptbEnabled":false,"supportedParameters":["n"]},"supportsPtb":false,"pricing":{"prompt":6.25,"completion":12.5}}],"maxOutput":4096,"trainingDate":"2025-04-01T00:00:00.000Z","description":"GPT Image 1 is OpenAI's image generation model that turns text and image inputs into high-fidelity images. It offers strong instruction following and image preservation capabilities.","inputModalities":["text","image"],"outputModalities":["image","text"],"supportedParameters":["n"]},{"id":"gpt-image-1.5","name":"OpenAI GPT Image 1.5","author":"openai","contextLength":8192,"endpoints":[{"provider":"openai","providerSlug":"openai","endpoint":{"author":"openai","modelConfig":{"providerModelId":"gpt-image-1.5","provider":"openai","author":"openai","pricing":[{"threshold":0,"input":0.000005,"output":0.00001}],"contextLength":8192,"maxCompletionTokens":4096,"rateLimits":{"rpm":500,"tpm":1000000},"supportedParameters":["n"],"ptbEnabled":false,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openai","providerModelId":"gpt-image-1.5","pricing":[{"threshold":0,"input":0.000005,"output":0.00001}],"contextLength":8192,"maxCompletionTokens":4096,"ptbEnabled":false,"supportedParameters":["n"]},"supportsPtb":false,"pricing":{"prompt":5,"completion":10}}],"maxOutput":4096,"trainingDate":"2025-12-01T00:00:00.000Z","description":"GPT Image 1.5 is OpenAI's state-of-the-art image generation model with better instruction following, 4× faster generation, and cheaper image tokens than GPT Image 1. It offers improved image preservation and editing capabilities.","inputModalities":["text","image"],"outputModalities":["image","text"],"supportedParameters":["n"]},{"id":"gemini-2.0-flash-exp","name":"Google Gemini 2.0 Flash Experimental","author":"google","contextLength":1000000,"endpoints":[{"provider":"google-ai-studio","providerSlug":"google-ai-studio","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-2.0-flash-exp","provider":"google-ai-studio","author":"google","pricing":[{"threshold":0,"input":0,"output":0,"image":{"input":0,"output":0.00012}}],"contextLength":1000000,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"],"rateLimits":{"rpm":10,"tpm":4000000},"ptbEnabled":false,"responseFormat":"GOOGLE","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"google-ai-studio","providerModelId":"gemini-2.0-flash-exp","pricing":[{"threshold":0,"input":0,"output":0,"image":{"input":0,"output":0.00012}}],"contextLength":1000000,"maxCompletionTokens":8192,"ptbEnabled":false,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"]},"supportsPtb":false,"pricing":{"prompt":0,"completion":0,"image":{"output":120}}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-2.0-flash-exp","provider":"vertex","author":"google","crossRegion":true,"pricing":[{"threshold":0,"input":0,"output":0,"image":{"input":0,"output":0.00012}}],"contextLength":1000000,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"],"responseFormat":"GOOGLE","ptbEnabled":false,"endpointConfigs":{"global":{"providerModelId":"gemini-2.0-flash-exp"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"gemini-2.0-flash-exp","pricing":[{"threshold":0,"input":0,"output":0,"image":{"input":0,"output":0.00012}}],"contextLength":1000000,"maxCompletionTokens":8192,"ptbEnabled":false,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"]},"supportsPtb":false,"pricing":{"prompt":0,"completion":0,"image":{"output":120}}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemini-2.0-flash-exp:free","pricing":[{"threshold":0,"input":0,"output":0,"image":{"input":0,"output":0.0001266}}],"contextLength":1000000,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"],"ptbEnabled":false,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemini-2.0-flash-exp:free","pricing":[{"threshold":0,"input":0,"output":0,"image":{"input":0,"output":0.0001266}}],"contextLength":1000000,"maxCompletionTokens":8192,"ptbEnabled":false,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"]},"supportsPtb":false,"pricing":{"prompt":0,"completion":0,"image":{"output":126.6}}}],"maxOutput":8192,"trainingDate":"2024-12-11T00:00:00","description":"Experimental version of Gemini 2.0 Flash with native image generation capabilities. Features multimodal input and output support including text and images.","inputModalities":["text","image"],"outputModalities":["text","image"],"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"]},{"id":"gemini-2.5-pro","name":"Google Gemini 2.5 Pro","author":"google","contextLength":1048576,"endpoints":[{"provider":"google-ai-studio","providerSlug":"google-ai-studio","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-2.5-pro","provider":"google-ai-studio","author":"google","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.0000025,"output":0.000015}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"rateLimits":{"rpm":2000,"tpm":8000000},"ptbEnabled":true,"responseFormat":"GOOGLE","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"google-ai-studio","providerModelId":"gemini-2.5-pro","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.0000025,"output":0.000015}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"cacheRead":0.3125,"cacheWrite":1.25},"pricingTiers":[{"prompt":1.25,"completion":10,"cacheRead":0.3125,"cacheWrite":1.25,"threshold":0},{"prompt":2.5,"completion":15,"threshold":200000}]},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-2.5-pro","provider":"vertex","author":"google","crossRegion":true,"pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.0000025,"output":0.000015}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"responseFormat":"GOOGLE","ptbEnabled":true,"endpointConfigs":{"global":{"providerModelId":"gemini-2.5-pro"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"gemini-2.5-pro","pricing":[{"threshold":0,"input":0.00000125,"output":0.00001,"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.0000025,"output":0.000015}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":1.25,"completion":10,"cacheRead":0.3125,"cacheWrite":1.25},"pricingTiers":[{"prompt":1.25,"completion":10,"cacheRead":0.3125,"cacheWrite":1.25,"threshold":0},{"prompt":2.5,"completion":15,"threshold":200000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemini-2.5-pro","pricing":[{"threshold":0,"input":0.00000264,"output":0.00001582}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemini-2.5-pro","pricing":[{"threshold":0,"input":0.00000264,"output":0.00001582}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":2.64,"completion":15.82}}],"maxOutput":65536,"trainingDate":"2025-06-17T07:12:24","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 and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},{"id":"gemini-2.5-flash","name":"Google Gemini 2.5 Flash","author":"google","contextLength":1048576,"endpoints":[{"provider":"google-ai-studio","providerSlug":"google-ai-studio","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-2.5-flash","provider":"google-ai-studio","author":"google","pricing":[{"threshold":0,"input":3e-7,"output":0.0000025,"audio":{"input":0.000001,"cachedInputMultiplier":0.1},"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.000001}],"contextLength":1048576,"maxCompletionTokens":65535,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"rateLimits":{"rpm":10000,"tpm":8000000},"ptbEnabled":true,"responseFormat":"GOOGLE","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"google-ai-studio","providerModelId":"gemini-2.5-flash","pricing":[{"threshold":0,"input":3e-7,"output":0.0000025,"audio":{"input":0.000001,"cachedInputMultiplier":0.1},"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.000001}],"contextLength":1048576,"maxCompletionTokens":65535,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":2.5,"audio":{"input":1,"cachedInput":0.09999999999999999},"cacheRead":0.075,"cacheWrite":0.3}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-2.5-flash","provider":"vertex","author":"google","crossRegion":true,"pricing":[{"threshold":0,"input":3e-7,"output":0.0000025,"audio":{"input":0.000001,"cachedInputMultiplier":0.1},"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.000001}],"contextLength":1048576,"maxCompletionTokens":65535,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"responseFormat":"GOOGLE","ptbEnabled":true,"endpointConfigs":{"global":{"providerModelId":"gemini-2.5-flash"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"gemini-2.5-flash","pricing":[{"threshold":0,"input":3e-7,"output":0.0000025,"audio":{"input":0.000001,"cachedInputMultiplier":0.1},"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.000001}],"contextLength":1048576,"maxCompletionTokens":65535,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":2.5,"audio":{"input":1,"cachedInput":0.09999999999999999},"cacheRead":0.075,"cacheWrite":0.3}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"google","modelConfig":{"provider":"helicone","author":"google","providerModelId":"pa/gmn-2.5-fls-lt-pw-06-17","pricing":[{"threshold":0,"input":3e-7,"output":0.0000025}],"contextLength":1048576,"maxCompletionTokens":65535,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gmn-2.5-fls-lt-pw-06-17","pricing":[{"threshold":0,"input":3e-7,"output":0.0000025}],"contextLength":1048576,"maxCompletionTokens":65535,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":2.5}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemini-2.5-flash","pricing":[{"threshold":0,"input":3.2e-7,"output":0.00000264}],"contextLength":1048576,"maxCompletionTokens":65535,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemini-2.5-flash","pricing":[{"threshold":0,"input":3.2e-7,"output":0.00000264}],"contextLength":1048576,"maxCompletionTokens":65535,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.32,"completion":2.64}}],"maxOutput":65535,"trainingDate":"2025-06-17T08:01:28","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 accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, allowing fine-tuned control over its reasoning process.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},{"id":"gemini-2.5-flash-lite","name":"Google Gemini 2.5 Flash Lite","author":"google","contextLength":1048576,"endpoints":[{"provider":"google-ai-studio","providerSlug":"google-ai-studio","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-2.5-flash-lite","provider":"google-ai-studio","author":"google","pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"audio":{"input":3e-7,"cachedInputMultiplier":0.0833333},"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.000001}],"contextLength":1048576,"maxCompletionTokens":65535,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"rateLimits":{"rpm":30000,"tpm":30000000},"ptbEnabled":true,"responseFormat":"GOOGLE","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"google-ai-studio","providerModelId":"gemini-2.5-flash-lite","pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"audio":{"input":3e-7,"cachedInputMultiplier":0.0833333},"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.000001}],"contextLength":1048576,"maxCompletionTokens":65535,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.09999999999999999,"completion":0.39999999999999997,"audio":{"input":0.3,"cachedInput":0.02499999},"cacheRead":0.024999999999999998,"cacheWrite":0.09999999999999999}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-2.5-flash-lite","provider":"vertex","author":"google","crossRegion":true,"pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"audio":{"input":3e-7,"cachedInputMultiplier":0.0833333},"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.000001}],"contextLength":1048576,"maxCompletionTokens":65535,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"responseFormat":"GOOGLE","ptbEnabled":true,"endpointConfigs":{"global":{"providerModelId":"gemini-2.5-flash-lite"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"gemini-2.5-flash-lite","pricing":[{"threshold":0,"input":1e-7,"output":4e-7,"audio":{"input":3e-7,"cachedInputMultiplier":0.0833333},"cacheMultipliers":{"cachedInput":0.25,"write5m":1},"cacheStoragePerHour":0.000001}],"contextLength":1048576,"maxCompletionTokens":65535,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.09999999999999999,"completion":0.39999999999999997,"audio":{"input":0.3,"cachedInput":0.02499999},"cacheRead":0.024999999999999998,"cacheWrite":0.09999999999999999}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemini-2.5-flash-lite","pricing":[{"threshold":0,"input":1.1e-7,"output":4.2e-7}],"contextLength":1048576,"maxCompletionTokens":65535,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemini-2.5-flash-lite","pricing":[{"threshold":0,"input":1.1e-7,"output":4.2e-7}],"contextLength":1048576,"maxCompletionTokens":65535,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.11,"completion":0.42}}],"maxOutput":65535,"trainingDate":"2025-07-22T09:04:36","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 across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},{"id":"gemini-3-pro-preview","name":"Google Gemini 3 Pro Preview","author":"google","contextLength":1048576,"endpoints":[{"provider":"google-ai-studio","providerSlug":"google-ai-studio","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-3-pro-preview","provider":"google-ai-studio","author":"google","pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.000004,"output":0.000018}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"rateLimits":{"rpm":2000,"tpm":8000000},"ptbEnabled":true,"responseFormat":"GOOGLE","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"google-ai-studio","providerModelId":"gemini-3-pro-preview","pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.000004,"output":0.000018}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":12,"cacheRead":0.19999999999999998},"pricingTiers":[{"prompt":2,"completion":12,"cacheRead":0.19999999999999998,"threshold":0},{"prompt":4,"completion":18,"threshold":200000}]},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-3-pro-preview","provider":"vertex","author":"google","crossRegion":true,"pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.000004,"output":0.000018}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"responseFormat":"GOOGLE","ptbEnabled":true,"endpointConfigs":{"global":{"providerModelId":"gemini-3-pro-preview"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"gemini-3-pro-preview","pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.000004,"output":0.000018}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":12,"cacheRead":0.19999999999999998},"pricingTiers":[{"prompt":2,"completion":12,"cacheRead":0.19999999999999998,"threshold":0},{"prompt":4,"completion":18,"threshold":200000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"google","modelConfig":{"provider":"helicone","author":"google","providerModelId":"pa/gemini-3-pro-preview","pricing":[{"threshold":0,"input":0.000002,"output":0.000012},{"threshold":200000,"input":0.000004,"output":0.000018}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gemini-3-pro-preview","pricing":[{"threshold":0,"input":0.000002,"output":0.000012},{"threshold":200000,"input":0.000004,"output":0.000018}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":12},"pricingTiers":[{"prompt":2,"completion":12,"threshold":0},{"prompt":4,"completion":18,"threshold":200000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemini-3-pro-preview","pricing":[{"threshold":0,"input":0.00000211,"output":0.00001266},{"threshold":200000,"input":0.00000422,"output":0.00001899}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemini-3-pro-preview","pricing":[{"threshold":0,"input":0.00000211,"output":0.00001266},{"threshold":200000,"input":0.00000422,"output":0.00001899}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":2.1100000000000003,"completion":12.66},"pricingTiers":[{"prompt":2.1100000000000003,"completion":12.66,"threshold":0},{"prompt":4.220000000000001,"completion":18.99,"threshold":200000}]}],"maxOutput":65536,"trainingDate":"2025-11-18T00:00:00","description":"Gemini 3 Pro Preview is Google's latest experimental AI model with advanced reasoning, coding, and multimodal capabilities. This preview version offers cutting-edge performance across various tasks including complex problem-solving, code generation, and scientific reasoning. It features enhanced accuracy and improved context understanding compared to previous generations.","inputModalities":["text","image","audio","video"],"outputModalities":["text"],"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},{"id":"gemini-3.1-pro-preview","name":"Google Gemini 3.1 Pro Preview","author":"google","contextLength":1048576,"endpoints":[{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-3.1-pro-preview","provider":"vertex","author":"google","crossRegion":true,"pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.000004,"output":0.000018,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"responseFormat":"GOOGLE","ptbEnabled":true,"endpointConfigs":{"global":{"providerModelId":"gemini-3.1-pro-preview"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"gemini-3.1-pro-preview","pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.0000045},{"threshold":200000,"input":0.000004,"output":0.000018,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":12,"cacheRead":0.19999999999999998},"pricingTiers":[{"prompt":2,"completion":12,"cacheRead":0.19999999999999998,"threshold":0},{"prompt":4,"completion":18,"cacheRead":0.39999999999999997,"threshold":200000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"google","modelConfig":{"provider":"helicone","author":"google","providerModelId":"pa/gemini-3.1-pro-preview","pricing":[{"threshold":0,"input":0.000002,"output":0.000012},{"threshold":200000,"input":0.000004,"output":0.000018}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gemini-3.1-pro-preview","pricing":[{"threshold":0,"input":0.000002,"output":0.000012},{"threshold":200000,"input":0.000004,"output":0.000018}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":12},"pricingTiers":[{"prompt":2,"completion":12,"threshold":0},{"prompt":4,"completion":18,"threshold":200000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemini-3.1-pro-preview","pricing":[{"threshold":0,"input":0.00000211,"output":0.00001266},{"threshold":200000,"input":0.00000422,"output":0.00001899}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemini-3.1-pro-preview","pricing":[{"threshold":0,"input":0.00000211,"output":0.00001266},{"threshold":200000,"input":0.00000422,"output":0.00001899}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":2.1100000000000003,"completion":12.66},"pricingTiers":[{"prompt":2.1100000000000003,"completion":12.66,"threshold":0},{"prompt":4.220000000000001,"completion":18.99,"threshold":200000}]}],"maxOutput":65536,"trainingDate":"2026-02-09T00:00:00","description":"Gemini 3.1 Pro Preview is Google's most advanced reasoning model, released February 2026. It uses extended thinking/chain-of-thought reasoning to work through complex problems. Scores 77.1% on ARC-AGI-2 (more than doubling Gemini 3 Pro's 31.1%), and tops the Artificial Analysis Intelligence Index v4.0 at half the cost of competitors. Features enhanced accuracy for ambitious agentic workflows, complex problem-solving, and scientific reasoning.","inputModalities":["text","image","audio","video"],"outputModalities":["text"],"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},{"id":"gemini-3-flash-preview","name":"Google Gemini 3 Flash Preview","author":"google","contextLength":1048576,"endpoints":[{"provider":"google-ai-studio","providerSlug":"google-ai-studio","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-3-flash-preview","provider":"google-ai-studio","author":"google","pricing":[{"threshold":0,"input":5e-7,"output":0.000003,"cacheMultipliers":{"cachedInput":0.1},"audio":{"input":0.000001,"cachedInputMultiplier":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"rateLimits":{"rpm":2000,"tpm":8000000},"ptbEnabled":true,"responseFormat":"GOOGLE","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"google-ai-studio","providerModelId":"gemini-3-flash-preview","pricing":[{"threshold":0,"input":5e-7,"output":0.000003,"cacheMultipliers":{"cachedInput":0.1},"audio":{"input":0.000001,"cachedInputMultiplier":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.5,"completion":3,"audio":{"input":1,"cachedInput":0.09999999999999999},"cacheRead":0.049999999999999996}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-3-flash-preview","provider":"vertex","author":"google","crossRegion":true,"pricing":[{"threshold":0,"input":5e-7,"output":0.000003,"cacheMultipliers":{"cachedInput":0.1},"audio":{"input":0.000001,"cachedInputMultiplier":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"responseFormat":"GOOGLE","ptbEnabled":true,"endpointConfigs":{"global":{"providerModelId":"gemini-3-flash-preview"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"gemini-3-flash-preview","pricing":[{"threshold":0,"input":5e-7,"output":0.000003,"cacheMultipliers":{"cachedInput":0.1},"audio":{"input":0.000001,"cachedInputMultiplier":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.5,"completion":3,"audio":{"input":1,"cachedInput":0.09999999999999999},"cacheRead":0.049999999999999996}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"google","modelConfig":{"provider":"helicone","author":"google","providerModelId":"pa/gemini-3-flash-preview","pricing":[{"threshold":0,"input":5e-7,"output":0.000003}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gemini-3-flash-preview","pricing":[{"threshold":0,"input":5e-7,"output":0.000003}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.5,"completion":3}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemini-3-flash-preview","pricing":[{"threshold":0,"input":5.275e-7,"output":0.000003165}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemini-3-flash-preview","pricing":[{"threshold":0,"input":5.275e-7,"output":0.000003165}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.5275000000000001,"completion":3.165}}],"maxOutput":65536,"trainingDate":"2025-12-17T00:00:00","description":"Gemini 3 Flash Preview is Google's latest fast and efficient AI model optimized for quick response times while maintaining high quality. This preview version offers excellent performance for everyday tasks including text generation, code assistance, and multimodal understanding at a lower cost than Pro variants.","inputModalities":["text","image","audio","video"],"outputModalities":["text"],"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},{"id":"gemini-3-pro-image-preview","name":"Google Gemini 3 Pro Image Preview","author":"google","contextLength":65536,"endpoints":[{"provider":"google-ai-studio","providerSlug":"google-ai-studio","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-3-pro-image-preview","provider":"google-ai-studio","author":"google","pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"image":{"input":0.000002,"output":0.00012}},{"threshold":200000,"input":0.000004,"output":0.000018,"image":{"input":0.000004,"output":0.00012}}],"contextLength":65536,"maxCompletionTokens":32768,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"],"rateLimits":{"rpm":100,"tpm":1000000},"ptbEnabled":true,"responseFormat":"GOOGLE","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"google-ai-studio","providerModelId":"gemini-3-pro-image-preview","pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"image":{"input":0.000002,"output":0.00012}},{"threshold":200000,"input":0.000004,"output":0.000018,"image":{"input":0.000004,"output":0.00012}}],"contextLength":65536,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":12,"image":{"input":2,"output":120}},"pricingTiers":[{"prompt":2,"completion":12,"image":{"input":2,"output":120},"threshold":0},{"prompt":4,"completion":18,"image":{"input":4,"output":120},"threshold":200000}]},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-3-pro-image-preview","provider":"vertex","author":"google","crossRegion":true,"pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"image":{"input":0.000002,"output":0.00012}},{"threshold":200000,"input":0.000004,"output":0.000018,"image":{"input":0.000004,"output":0.00012}}],"contextLength":65536,"maxCompletionTokens":32768,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"],"responseFormat":"GOOGLE","ptbEnabled":true,"endpointConfigs":{"global":{"providerModelId":"gemini-3-pro-image-preview"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"gemini-3-pro-image-preview","pricing":[{"threshold":0,"input":0.000002,"output":0.000012,"image":{"input":0.000002,"output":0.00012}},{"threshold":200000,"input":0.000004,"output":0.000018,"image":{"input":0.000004,"output":0.00012}}],"contextLength":65536,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":12,"image":{"input":2,"output":120}},"pricingTiers":[{"prompt":2,"completion":12,"image":{"input":2,"output":120},"threshold":0},{"prompt":4,"completion":18,"image":{"input":4,"output":120},"threshold":200000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemini-3-pro-image-preview","pricing":[{"threshold":0,"input":0.00000211,"output":0.00001266,"image":{"input":0.00000211,"output":0.0001266}},{"threshold":200000,"input":0.00000422,"output":0.00001899,"image":{"input":0.00000422,"output":0.0001266}}],"contextLength":65536,"maxCompletionTokens":32768,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemini-3-pro-image-preview","pricing":[{"threshold":0,"input":0.00000211,"output":0.00001266,"image":{"input":0.00000211,"output":0.0001266}},{"threshold":200000,"input":0.00000422,"output":0.00001899,"image":{"input":0.00000422,"output":0.0001266}}],"contextLength":65536,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"]},"supportsPtb":true,"pricing":{"prompt":2.1100000000000003,"completion":12.66,"image":{"input":2.1100000000000003,"output":126.6}},"pricingTiers":[{"prompt":2.1100000000000003,"completion":12.66,"image":{"input":2.1100000000000003,"output":126.6},"threshold":0},{"prompt":4.220000000000001,"completion":18.99,"image":{"input":4.220000000000001,"output":126.6},"threshold":200000}]}],"maxOutput":32768,"trainingDate":"2025-11-20T00:00:00","description":"Gemini 3 Pro Image is Google's native image generation model with state-of-the-art reasoning capabilities. It is the best model for complex and multi-turn image generation and editing, featuring improved accuracy and enhanced image quality. This preview version supports up to 14 input images and can generate up to 32 output images per request.","inputModalities":["text","image"],"outputModalities":["text","image"],"supportedParameters":["max_tokens","response_format","seed","stop","temperature","top_p"]},{"id":"gemini-3.1-flash-lite-preview","name":"Google Gemini 3.1 Flash-Lite Preview","author":"google","contextLength":1048576,"endpoints":[{"provider":"google-ai-studio","providerSlug":"google-ai-studio","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-3.1-flash-lite-preview","provider":"google-ai-studio","author":"google","pricing":[{"threshold":0,"input":2.5e-7,"output":0.0000015,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.000001,"audio":{"input":5e-7,"cachedInputMultiplier":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"rateLimits":{"rpm":2000,"tpm":8000000},"ptbEnabled":true,"responseFormat":"GOOGLE","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"google-ai-studio","providerModelId":"gemini-3.1-flash-lite-preview","pricing":[{"threshold":0,"input":2.5e-7,"output":0.0000015,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.000001,"audio":{"input":5e-7,"cachedInputMultiplier":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":1.5,"audio":{"input":0.5,"cachedInput":0.049999999999999996},"cacheRead":0.024999999999999998}},{"provider":"vertex","providerSlug":"google-vertex","endpoint":{"author":"google","modelConfig":{"providerModelId":"gemini-3.1-flash-lite-preview","provider":"vertex","author":"google","crossRegion":true,"pricing":[{"threshold":0,"input":2.5e-7,"output":0.0000015,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.000001,"audio":{"input":5e-7,"cachedInputMultiplier":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"responseFormat":"GOOGLE","ptbEnabled":true,"endpointConfigs":{"global":{"providerModelId":"gemini-3.1-flash-lite-preview"}}},"userConfig":{"region":"global","location":"global","crossRegion":true},"provider":"vertex","providerModelId":"gemini-3.1-flash-lite-preview","pricing":[{"threshold":0,"input":2.5e-7,"output":0.0000015,"cacheMultipliers":{"cachedInput":0.1},"cacheStoragePerHour":0.000001,"audio":{"input":5e-7,"cachedInputMultiplier":0.1}}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":1.5,"audio":{"input":0.5,"cachedInput":0.049999999999999996},"cacheRead":0.024999999999999998}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"google","modelConfig":{"provider":"helicone","author":"google","providerModelId":"pa/gemini-3.1-flash-lite-preview","pricing":[{"threshold":0,"input":2.5e-7,"output":0.0000015}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/gemini-3.1-flash-lite-preview","pricing":[{"threshold":0,"input":2.5e-7,"output":0.0000015}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.25,"completion":1.5}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemini-3.1-flash-lite-preview","pricing":[{"threshold":0,"input":2.6375e-7,"output":0.0000015825}],"contextLength":1048576,"maxCompletionTokens":65536,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemini-3.1-flash-lite-preview","pricing":[{"threshold":0,"input":2.6375e-7,"output":0.0000015825}],"contextLength":1048576,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.26375000000000004,"completion":1.5825}}],"maxOutput":65536,"trainingDate":"2026-03-01T00:00:00","description":"Gemini 3.1 Flash-Lite Preview is Google's most cost-efficient model, optimized for high-volume agentic tasks, translation, and simple data processing. Supports thinking/chain-of-thought reasoning, caching, function calling, structured outputs, search grounding, and code execution. Preview model with more restrictive rate limits.","inputModalities":["text","image","audio","video"],"outputModalities":["text"],"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"]},{"id":"gemma2-9b-it","name":"Google Gemma 2","author":"google","contextLength":8192,"endpoints":[{"provider":"chutes","providerSlug":"chutes","endpoint":{"author":"google","modelConfig":{"providerModelId":"unsloth/gemma-2-9b-it","provider":"chutes","author":"google","pricing":[{"threshold":0,"input":1e-8,"output":3e-8}],"contextLength":8192,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"chutes","providerModelId":"unsloth/gemma-2-9b-it","pricing":[{"threshold":0,"input":1e-8,"output":3e-8}],"contextLength":8192,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"]},"supportsPtb":true,"pricing":{"prompt":0.01,"completion":0.03}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"google","modelConfig":{"provider":"openrouter","author":"google","providerModelId":"google/gemma-2-9b-it","pricing":[{"threshold":0,"input":2.1e-7,"output":2.1e-7}],"contextLength":8192,"maxCompletionTokens":8192,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"google/gemma-2-9b-it","pricing":[{"threshold":0,"input":2.1e-7,"output":2.1e-7}],"contextLength":8192,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.21,"completion":0.21}}],"maxOutput":8192,"trainingDate":"2024-06-25T00:00:00.000Z","description":"Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","logprobs","top_logprobs"]},{"id":"gemma-3-12b-it","name":"Google Gemma 3 12B","author":"google","contextLength":131072,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"google","modelConfig":{"providerModelId":"google/gemma-3-12b-it","provider":"deepinfra","author":"google","pricing":[{"threshold":0,"input":5e-8,"output":1e-7}],"rateLimits":{"rpm":12000,"tpm":60000000,"tpd":6000000000},"quantization":"bf16","contextLength":131072,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"google/gemma-3-12b-it","pricing":[{"threshold":0,"input":5e-8,"output":1e-7}],"contextLength":131072,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.09999999999999999}}],"maxOutput":8192,"trainingDate":"2024-12-01T00:00:00.000Z","description":"Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},{"id":"grok-code-fast-1","name":"xAI Grok Code Fast 1","author":"xai","contextLength":256000,"endpoints":[{"provider":"xai","providerSlug":"xai","endpoint":{"author":"xai","modelConfig":{"providerModelId":"grok-code-fast-1","provider":"xai","author":"xai","pricing":[{"threshold":0,"input":2e-7,"output":0.0000015,"request":0,"web_search":0,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":256000,"maxCompletionTokens":10000,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"xai","providerModelId":"grok-code-fast-1","pricing":[{"threshold":0,"input":2e-7,"output":0.0000015,"request":0,"web_search":0,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":256000,"maxCompletionTokens":10000,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":1.5,"cacheRead":0.02}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"xai","modelConfig":{"providerModelId":"pa/grok-code-fast-1","provider":"helicone","author":"xai","pricing":[{"threshold":0,"input":2e-7,"output":0.0000015,"request":0,"web_search":0,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":256000,"maxCompletionTokens":10000,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/grok-code-fast-1","pricing":[{"threshold":0,"input":2e-7,"output":0.0000015,"request":0,"web_search":0,"cacheMultipliers":{"cachedInput":0.1}}],"contextLength":256000,"maxCompletionTokens":10000,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":1.5,"cacheRead":0.02}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"xai","modelConfig":{"provider":"openrouter","author":"xai","providerModelId":"x-ai/grok-code-fast-1","pricing":[{"threshold":0,"input":2.1e-7,"output":0.00000158}],"contextLength":256000,"maxCompletionTokens":10000,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"x-ai/grok-code-fast-1","pricing":[{"threshold":0,"input":2.1e-7,"output":0.00000158}],"contextLength":256000,"maxCompletionTokens":10000,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.21,"completion":1.5799999999999998}}],"maxOutput":10000,"trainingDate":"2024-08-25T00:00:00.000Z","description":"Speedy and economical reasoning model that excels at agentic coding. Features function calling, structured outputs, and reasoning capabilities.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},{"id":"grok-4","name":"xAI Grok 4","author":"xai","contextLength":256000,"endpoints":[{"provider":"xai","providerSlug":"xai","endpoint":{"author":"xai","modelConfig":{"providerModelId":"grok-4","provider":"xai","author":"xai","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":0.000006,"output":0.00003,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":256000,"maxCompletionTokens":256000,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"xai","providerModelId":"grok-4","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":0.000006,"output":0.00003,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":256000,"maxCompletionTokens":256000,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":25000,"cacheRead":0.75},"pricingTiers":[{"prompt":3,"completion":15,"web_search":25000,"cacheRead":0.75,"threshold":0},{"prompt":6,"completion":30,"web_search":25000,"cacheRead":0.75,"threshold":128000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"xai","modelConfig":{"providerModelId":"pa/grk-4","provider":"helicone","author":"xai","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":0.000006,"output":0.00003,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":256000,"maxCompletionTokens":256000,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/grk-4","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":0.000006,"output":0.00003,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":256000,"maxCompletionTokens":256000,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":25000,"cacheRead":0.75},"pricingTiers":[{"prompt":3,"completion":15,"web_search":25000,"cacheRead":0.75,"threshold":0},{"prompt":6,"completion":30,"web_search":25000,"cacheRead":0.75,"threshold":128000}]},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"xai","modelConfig":{"provider":"openrouter","author":"xai","providerModelId":"x-ai/grok-4","pricing":[{"threshold":0,"input":0.00000633,"output":0.00003165}],"contextLength":256000,"maxCompletionTokens":256000,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"x-ai/grok-4","pricing":[{"threshold":0,"input":0.00000633,"output":0.00003165}],"contextLength":256000,"maxCompletionTokens":256000,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":6.33,"completion":31.65}}],"maxOutput":256000,"trainingDate":"2024-07-09T00:00:00.000Z","description":"Latest and greatest flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades. Features function calling, structured outputs, and reasoning capabilities.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},{"id":"grok-4-fast-reasoning","name":"xAI: Grok 4 Fast Reasoning","author":"xai","contextLength":2000000,"endpoints":[{"provider":"xai","providerSlug":"xai","endpoint":{"author":"xai","modelConfig":{"providerModelId":"grok-4-fast","provider":"xai","author":"xai","providerModelIdAliases":["grok-4-fast-reasoning"],"pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":4e-7,"output":0.000001,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":2000000,"maxCompletionTokens":2000000,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"xai","providerModelId":"grok-4-fast","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":4e-7,"output":0.000001,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":2000000,"maxCompletionTokens":2000000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996},"pricingTiers":[{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996,"threshold":0},{"prompt":0.39999999999999997,"completion":1,"web_search":25000,"cacheRead":0.049999999999999996,"threshold":128000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"xai","modelConfig":{"providerModelId":"pa/grok-4-fast-reasoning","provider":"helicone","author":"xai","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":4e-7,"output":0.000001,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":2000000,"maxCompletionTokens":2000000,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/grok-4-fast-reasoning","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":4e-7,"output":0.000001,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":2000000,"maxCompletionTokens":2000000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996},"pricingTiers":[{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996,"threshold":0},{"prompt":0.39999999999999997,"completion":1,"web_search":25000,"cacheRead":0.049999999999999996,"threshold":128000}]}],"maxOutput":2000000,"trainingDate":"2025-09-01T00:00:00.000Z","description":"Grok 4 Fast is xAI's latest advancement in cost-efficient reasoning models. Built on xAI’s learnings from Grok 4, Grok 4 Fast delivers frontier-level performance across Enterprise and Consumer domains—with exceptional token efficiency. This model pushes the boundaries for smaller and faster AI, making high-quality reasoning accessible to more users and developers. Grok 4 Fast features state-of-the-art (SOTA) cost-efficiency, cutting-edge web and X search capabilities, a 2M token context window, and a unified architecture that blends reasoning and non-reasoning modes in one model.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"]},{"id":"grok-4-fast-non-reasoning","name":"xAI Grok 4 Fast Non-Reasoning","author":"xai","contextLength":2000000,"endpoints":[{"provider":"xai","providerSlug":"xai","endpoint":{"author":"xai","modelConfig":{"providerModelId":"grok-4-fast-non-reasoning","provider":"xai","author":"xai","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":2000000,"maxCompletionTokens":2000000,"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"xai","providerModelId":"grok-4-fast-non-reasoning","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":2000000,"maxCompletionTokens":2000000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"xai","modelConfig":{"providerModelId":"pa/grok-4-fast-non-reasoning","provider":"helicone","author":"xai","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":2000000,"maxCompletionTokens":2000000,"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/grok-4-fast-non-reasoning","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":2000000,"maxCompletionTokens":2000000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996}}],"maxOutput":2000000,"trainingDate":"2025-09-19T00:00:00.000Z","description":"Grok 4 Fast is xAI's latest advancement in cost-efficient reasoning models. Built on xAI’s learnings from Grok 4, Grok 4 Fast delivers frontier-level performance across Enterprise and Consumer domains—with exceptional token efficiency. This model pushes the boundaries for smaller and faster AI, making high-quality reasoning accessible to more users and developers. Grok 4 Fast features state-of-the-art (SOTA) cost-efficiency, cutting-edge web and X search capabilities, a 2M token context window. This non-reasoning model specifically excludes reasoning capabilities.","inputModalities":["text","image","audio"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"]},{"id":"grok-4-1-fast-non-reasoning","name":"xAI Grok 4.1 Fast Non-Reasoning","author":"xai","contextLength":2000000,"endpoints":[{"provider":"xai","providerSlug":"xai","endpoint":{"author":"xai","modelConfig":{"providerModelId":"grok-4-1-fast-non-reasoning","provider":"xai","author":"xai","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":2000000,"maxCompletionTokens":2000000,"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"xai","providerModelId":"grok-4-1-fast-non-reasoning","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":2000000,"maxCompletionTokens":2000000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"xai","modelConfig":{"providerModelId":"pa/grok-4-1-fast-non-reasoning","provider":"helicone","author":"xai","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":2000000,"maxCompletionTokens":2000000,"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/grok-4-1-fast-non-reasoning","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":2000000,"maxCompletionTokens":2000000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996}}],"maxOutput":30000,"trainingDate":"2025-11-17T00:00:00.000Z","description":"A frontier multimodal model optimized specifically for high-performance agentic tool calling.","inputModalities":["text","image"],"outputModalities":["text","image"],"supportedParameters":["max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"]},{"id":"grok-4-1-fast-reasoning","name":"xAI Grok 4.1 Fast Reasoning","author":"xai","contextLength":2000000,"endpoints":[{"provider":"xai","providerSlug":"xai","endpoint":{"author":"xai","modelConfig":{"providerModelId":"grok-4-1-fast-reasoning","provider":"xai","author":"xai","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":4e-7,"output":0.000001,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":2000000,"maxCompletionTokens":2000000,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"xai","providerModelId":"grok-4-1-fast-reasoning","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":4e-7,"output":0.000001,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":2000000,"maxCompletionTokens":2000000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996},"pricingTiers":[{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996,"threshold":0},{"prompt":0.39999999999999997,"completion":1,"web_search":25000,"cacheRead":0.049999999999999996,"threshold":128000}]},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"xai","modelConfig":{"providerModelId":"pa/grok-4-1-fast-reasoning","provider":"helicone","author":"xai","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":4e-7,"output":0.000001,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":2000000,"maxCompletionTokens":2000000,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/grok-4-1-fast-reasoning","pricing":[{"threshold":0,"input":2e-7,"output":5e-7,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}},{"threshold":128000,"input":4e-7,"output":0.000001,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":2000000,"maxCompletionTokens":2000000,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996},"pricingTiers":[{"prompt":0.19999999999999998,"completion":0.5,"web_search":25000,"cacheRead":0.049999999999999996,"threshold":0},{"prompt":0.39999999999999997,"completion":1,"web_search":25000,"cacheRead":0.049999999999999996,"threshold":128000}]}],"maxOutput":2000000,"trainingDate":"2025-11-17T00:00:00.000Z","description":"A frontier multimodal model optimized for high-performance agentic tool calling with reasoning capabilities.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning"]},{"id":"grok-3","name":"xAI Grok 3","author":"xai","contextLength":131072,"endpoints":[{"provider":"xai","providerSlug":"xai","endpoint":{"author":"xai","modelConfig":{"providerModelId":"grok-3","provider":"xai","author":"xai","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"xai","providerModelId":"grok-3","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":25000,"cacheRead":0.75}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"xai","modelConfig":{"providerModelId":"pa/grk-3","provider":"helicone","author":"xai","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/grk-3","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":25000,"cacheRead":0.75}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"xai","modelConfig":{"provider":"openrouter","author":"xai","providerModelId":"x-ai/grok-3","pricing":[{"threshold":0,"input":0.00000528,"output":0.00002638}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"x-ai/grok-3","pricing":[{"threshold":0,"input":0.00000528,"output":0.00002638}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":5.28,"completion":26.380000000000003}}],"maxOutput":131072,"trainingDate":"2024-06-01T00:00:00.000Z","description":"Excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science. Features function calling, structured outputs, and reasoning capabilities.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},{"id":"grok-3-mini","name":"xAI Grok 3 Mini","author":"xai","contextLength":131072,"endpoints":[{"provider":"xai","providerSlug":"xai","endpoint":{"author":"xai","modelConfig":{"providerModelId":"grok-3-mini","provider":"xai","author":"xai","pricing":[{"threshold":0,"input":3e-7,"output":5e-7,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"xai","providerModelId":"grok-3-mini","pricing":[{"threshold":0,"input":3e-7,"output":5e-7,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":0.5,"web_search":25000,"cacheRead":0.075}},{"provider":"helicone","providerSlug":"helicone","endpoint":{"author":"xai","modelConfig":{"providerModelId":"pa/grok-3-mini","provider":"helicone","author":"xai","pricing":[{"threshold":0,"input":3e-7,"output":5e-7,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"helicone","providerModelId":"pa/grok-3-mini","pricing":[{"threshold":0,"input":3e-7,"output":5e-7,"request":0,"web_search":0.025,"cacheMultipliers":{"cachedInput":0.25}}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":0.5,"web_search":25000,"cacheRead":0.075}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"xai","modelConfig":{"provider":"openrouter","author":"xai","providerModelId":"x-ai/grok-3-mini","pricing":[{"threshold":0,"input":6.33e-7,"output":0.00000422}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"x-ai/grok-3-mini","pricing":[{"threshold":0,"input":6.33e-7,"output":0.00000422}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.633,"completion":4.220000000000001}}],"maxOutput":131072,"trainingDate":"2024-06-01T00:00:00.000Z","description":"Lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. Features function calling, structured outputs, and reasoning capabilities.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},{"id":"llama-4-scout","name":"Meta Llama 4 Scout 17B 16E","author":"meta-llama","contextLength":131072,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"meta-llama","modelConfig":{"provider":"deepinfra","author":"meta-llama","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","pricing":[{"threshold":0,"input":8e-8,"output":3e-7}],"quantization":"fp8","contextLength":10000000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","functions","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","pricing":[{"threshold":0,"input":8e-8,"output":3e-7}],"contextLength":10000000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","functions","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":0.08,"completion":0.3}},{"provider":"groq","providerSlug":"groq","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","provider":"groq","author":"meta-llama","pricing":[{"threshold":0,"input":1.1e-7,"output":3.4e-7}],"contextLength":131072,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","pricing":[{"threshold":0,"input":1.1e-7,"output":3.4e-7}],"contextLength":131072,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.11,"completion":0.33999999999999997}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"meta-llama","modelConfig":{"provider":"novita","author":"meta-llama","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct","pricing":[{"threshold":0,"input":1e-7,"output":5e-7}],"quantization":"bf16","contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias","functions","tools"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct","pricing":[{"threshold":0,"input":1e-7,"output":5e-7}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias","functions","tools"]},"supportsPtb":true,"pricing":{"prompt":0.09999999999999999,"completion":0.5}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"meta-llama","modelConfig":{"provider":"openrouter","author":"meta-llama","providerModelId":"meta-llama/llama-4-scout","pricing":[{"threshold":0,"input":6.9e-7,"output":9e-7}],"contextLength":1048576,"maxCompletionTokens":1048576,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"meta-llama/llama-4-scout","pricing":[{"threshold":0,"input":6.9e-7,"output":9e-7}],"contextLength":1048576,"maxCompletionTokens":1048576,"ptbEnabled":true,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.69,"completion":0.8999999999999999}}],"maxOutput":8192,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Llama 4 instruction-tuned MoE (17B, 16 experts) for fast, high-quality chat, tool use, and multilingual reasoning with balanced latency and cost.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","frequency_penalty","presence_penalty","min_p","logit_bias","functions"]},{"id":"llama-4-maverick","name":"Meta Llama 4 Maverick 17B 128E","author":"meta-llama","contextLength":131072,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","provider":"deepinfra","author":"meta-llama","pricing":[{"threshold":0,"input":1.5e-7,"output":6e-7}],"quantization":"fp8","contextLength":1000000,"maxCompletionTokens":16384,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","tools","tool_choice","functions"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","pricing":[{"threshold":0,"input":1.5e-7,"output":6e-7}],"contextLength":1000000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","tools","tool_choice","functions"]},"supportsPtb":true,"pricing":{"prompt":0.15,"completion":0.6}},{"provider":"groq","providerSlug":"groq","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","provider":"groq","author":"meta-llama","pricing":[{"threshold":0,"input":2e-7,"output":6e-7}],"contextLength":131072,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","pricing":[{"threshold":0,"input":2e-7,"output":6e-7}],"contextLength":131072,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.6}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","provider":"novita","author":"meta-llama","pricing":[{"threshold":0,"input":1.7e-7,"output":8.5e-7}],"quantization":"fp8","contextLength":1048576,"maxCompletionTokens":1048576,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias","functions","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","pricing":[{"threshold":0,"input":1.7e-7,"output":8.5e-7}],"contextLength":1048576,"maxCompletionTokens":1048576,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias","functions","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":0.16999999999999998,"completion":0.85}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"meta-llama","modelConfig":{"provider":"openrouter","author":"meta-llama","providerModelId":"meta-llama/llama-4-maverick","pricing":[{"threshold":0,"input":6.6e-7,"output":0.0000019}],"contextLength":1048576,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"meta-llama/llama-4-maverick","pricing":[{"threshold":0,"input":6.6e-7,"output":0.0000019}],"contextLength":1048576,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.66,"completion":1.9}}],"maxOutput":8192,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Llama 4 instruction-tuned MoE (17B, 128 experts) targeting tougher reasoning and long-form tasks, trading more compute for higher response diversity and robustness.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","frequency_penalty","presence_penalty","min_p","logit_bias","functions"]},{"id":"llama-guard-4","name":"Meta Llama Guard 4 12B","author":"meta-llama","contextLength":131072,"endpoints":[{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"meta-llama","modelConfig":{"provider":"openrouter","author":"meta-llama","providerModelId":"meta-llama/llama-guard-4-12b","pricing":[{"threshold":0,"input":2.1e-7,"output":2.1e-7}],"contextLength":163840,"maxCompletionTokens":163840,"supportedParameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"meta-llama/llama-guard-4-12b","pricing":[{"threshold":0,"input":2.1e-7,"output":2.1e-7}],"contextLength":163840,"maxCompletionTokens":163840,"ptbEnabled":true,"supportedParameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.21,"completion":0.21}},{"provider":"groq","providerSlug":"groq","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/Llama-Guard-4-12B","provider":"groq","author":"meta-llama","pricing":[{"threshold":0,"input":2e-7,"output":6e-7}],"contextLength":131072,"maxCompletionTokens":1024,"supportedParameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"meta-llama/Llama-Guard-4-12B","pricing":[{"threshold":0,"input":2e-7,"output":6e-7}],"contextLength":131072,"maxCompletionTokens":1024,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.19999999999999998,"completion":0.6}}],"maxOutput":1024,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Meta’s latest safety/guardrail model for prompt and output moderation, aligning conversations to policy via classification and constrained generation.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"]},{"id":"llama-3.3-70b-versatile","name":"Meta Llama 3.3 70B Versatile","author":"meta-llama","contextLength":131072,"endpoints":[{"provider":"groq","providerSlug":"groq","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"llama-3.3-70b-versatile","provider":"groq","author":"meta-llama","pricing":[{"threshold":0,"input":5.9e-7,"output":7.9e-7}],"contextLength":131072,"maxCompletionTokens":32678,"supportedParameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"llama-3.3-70b-versatile","pricing":[{"threshold":0,"input":5.9e-7,"output":7.9e-7}],"contextLength":131072,"maxCompletionTokens":32678,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.59,"completion":0.7899999999999999}}],"maxOutput":32678,"trainingDate":"2024-12-06T00:00:00.000Z","description":"Llama-3.3-70B-Versatile is Meta's advanced multilingual large language model, optimized for a wide range of natural language processing tasks. With 70 billion parameters, it offers high performance across various benchmarks while maintaining efficiency suitable for diverse applications.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"]},{"id":"llama-3.3-70b-instruct","name":"Meta Llama 3.3 70B Instruct","author":"meta-llama","contextLength":128000,"endpoints":[{"provider":"novita","providerSlug":"novita","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/llama-3.3-70b-instruct","provider":"novita","author":"meta-llama","pricing":[{"threshold":0,"input":1.3e-7,"output":3.9e-7}],"quantization":"bf16","contextLength":131072,"maxCompletionTokens":120000,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tool_choice","tools"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"meta-llama/llama-3.3-70b-instruct","pricing":[{"threshold":0,"input":1.3e-7,"output":3.9e-7}],"contextLength":131072,"maxCompletionTokens":120000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tool_choice","tools"]},"supportsPtb":true,"pricing":{"prompt":0.13,"completion":0.39}},{"provider":"nebius","providerSlug":"nebius","endpoint":{"author":"meta-llama","modelConfig":{"provider":"nebius","author":"meta-llama","providerModelId":"meta-llama/Llama-3.3-70B-Instruct","pricing":[{"threshold":0,"input":1.3e-7,"output":4e-7}],"quantization":"fp8","contextLength":128000,"maxCompletionTokens":128000,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","top_k","repetition_penalty","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"nebius","providerModelId":"meta-llama/Llama-3.3-70B-Instruct","pricing":[{"threshold":0,"input":1.3e-7,"output":4e-7}],"contextLength":128000,"maxCompletionTokens":128000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","top_k","repetition_penalty","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":0.13,"completion":0.39999999999999997}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"meta-llama","modelConfig":{"provider":"openrouter","author":"meta-llama","providerModelId":"meta-llama/llama-3.3-70b-instruct","pricing":[{"threshold":0,"input":9.5e-7,"output":0.00000237}],"contextLength":131072,"maxCompletionTokens":8192,"supportedParameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"meta-llama/llama-3.3-70b-instruct","pricing":[{"threshold":0,"input":9.5e-7,"output":0.00000237}],"contextLength":131072,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.95,"completion":2.37}}],"maxOutput":16400,"trainingDate":"2024-12-06T00:00:00.000Z","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 is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p","min_p"]},{"id":"llama-3.1-8b-instant","name":"Meta Llama 3.1 8B Instant","author":"meta-llama","contextLength":131072,"endpoints":[{"provider":"groq","providerSlug":"groq","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"llama-3.1-8b-instant","provider":"groq","author":"meta-llama","pricing":[{"threshold":0,"input":5e-8,"output":8e-8}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"llama-3.1-8b-instant","pricing":[{"threshold":0,"input":5e-8,"output":8e-8}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.049999999999999996,"completion":0.08}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"meta-llama","modelConfig":{"provider":"openrouter","author":"meta-llama","providerModelId":"meta-llama/llama-3.1-8b-instruct","pricing":[{"threshold":0,"input":2.1e-7,"output":3.1e-7}],"contextLength":131072,"maxCompletionTokens":16384,"supportedParameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"meta-llama/llama-3.1-8b-instruct","pricing":[{"threshold":0,"input":2.1e-7,"output":3.1e-7}],"contextLength":131072,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.21,"completion":0.31}}],"maxOutput":32678,"trainingDate":"2024-07-01T00:00:00.000Z","description":"Compact 8B general-purpose model offering efficient inference for chat, coding, and RAG workflows on limited compute.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p","response_format","seed","top_logprobs"]},{"id":"llama-prompt-guard-2-86m","name":"Meta Llama Prompt Guard 2 86M","author":"meta-llama","contextLength":512,"endpoints":[{"provider":"groq","providerSlug":"groq","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/llama-prompt-guard-2-86m","provider":"groq","author":"meta-llama","pricing":[{"threshold":0,"input":1e-8,"output":1e-8}],"contextLength":512,"maxCompletionTokens":2,"supportedParameters":["max_tokens","temperature","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"meta-llama/llama-prompt-guard-2-86m","pricing":[{"threshold":0,"input":1e-8,"output":1e-8}],"contextLength":512,"maxCompletionTokens":2,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.01,"completion":0.01}}],"maxOutput":2,"trainingDate":"2024-10-01T00:00:00.000Z","description":"86M parameter multilingual prompt safety classifier based on mDeBERTa-base, detecting prompt injections and jailbreaks across 8+ languages with adversarial-resistant tokenization.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p"]},{"id":"llama-prompt-guard-2-22m","name":"Meta Llama Prompt Guard 2 22M","author":"meta-llama","contextLength":512,"endpoints":[{"provider":"groq","providerSlug":"groq","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/llama-prompt-guard-2-22m","provider":"groq","author":"meta-llama","pricing":[{"threshold":0,"input":1e-8,"output":1e-8}],"contextLength":512,"maxCompletionTokens":2,"supportedParameters":["max_tokens","temperature","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"meta-llama/llama-prompt-guard-2-22m","pricing":[{"threshold":0,"input":1e-8,"output":1e-8}],"contextLength":512,"maxCompletionTokens":2,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.01,"completion":0.01}}],"maxOutput":2,"trainingDate":"2024-10-01T00:00:00.000Z","description":"22M parameter lightweight prompt safety classifier based on DeBERTa-xsmall, offering 75% reduced latency for detecting prompt injections and jailbreaks, primarily optimized for English.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p"]},{"id":"llama-3.1-8b-instruct","name":"Meta Llama 3.1 8B Instruct","author":"meta-llama","contextLength":16384,"endpoints":[{"provider":"novita","providerSlug":"novita","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/llama-3.1-8b-instruct","provider":"novita","author":"meta-llama","pricing":[{"threshold":0,"input":2e-8,"output":5e-8}],"quantization":"fp8","contextLength":16384,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"meta-llama/llama-3.1-8b-instruct","pricing":[{"threshold":0,"input":2e-8,"output":5e-8}],"contextLength":16384,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.02,"completion":0.049999999999999996}},{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct","provider":"deepinfra","author":"meta-llama","pricing":[{"threshold":0,"input":3e-8,"output":5e-8}],"quantization":"bf16","contextLength":131072,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct","pricing":[{"threshold":0,"input":3e-8,"output":5e-8}],"contextLength":131072,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools"]},"supportsPtb":true,"pricing":{"prompt":0.03,"completion":0.049999999999999996}}],"maxOutput":16384,"trainingDate":"2024-07-23T00:00:00.000Z","description":"Meta's latest class of models, Llama 3.1, launched with a variety of sizes and configurations. The 8B instruct-tuned version is particularly fast and efficient. It has demonstrated strong performance in human evaluations, outperforming several leading closed-source models.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias","response_format","tool_choice","tools"]},{"id":"llama-3.1-8b-instruct-turbo","name":"Meta Llama 3.1 8B Instruct Turbo","author":"meta-llama","contextLength":128000,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","provider":"deepinfra","author":"meta-llama","pricing":[{"threshold":0,"input":2e-8,"output":3e-8}],"quantization":"fp8","contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","pricing":[{"threshold":0,"input":2e-8,"output":3e-8}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools"]},"supportsPtb":true,"pricing":{"prompt":0.02,"completion":0.03}},{"provider":"nebius","providerSlug":"nebius","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct-fast","provider":"nebius","author":"meta-llama","pricing":[{"threshold":0,"input":3e-8,"output":9e-8}],"quantization":"fp8","contextLength":128000,"maxCompletionTokens":8192,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","functions","tool_choice","tools"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"nebius","providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct-fast","pricing":[{"threshold":0,"input":3e-8,"output":9e-8}],"contextLength":128000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","functions","tool_choice","tools"]},"supportsPtb":true,"pricing":{"prompt":0.03,"completion":0.09}}],"maxOutput":128000,"trainingDate":"2024-07-23T00:00:00.000Z","description":"Optimized version of Llama 3.1 8B Instruct with 128K context window, designed for high-speed inference in multilingual chat and dialogue use cases with improved throughput and efficiency.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["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","logprobs","top_logprobs","functions"]},{"id":"hermes-2-pro-llama-3-8b","name":"Hermes 2 Pro Llama 3 8B","author":"meta-llama","contextLength":131072,"endpoints":[{"provider":"novita","providerSlug":"novita","endpoint":{"author":"meta-llama","modelConfig":{"providerModelId":"nousresearch/hermes-2-pro-llama-3-8b","provider":"novita","author":"meta-llama","pricing":[{"threshold":0,"input":1.4e-7,"output":1.4e-7}],"quantization":"fp16","contextLength":8192,"maxCompletionTokens":8192,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","functions","tools","top_k","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"nousresearch/hermes-2-pro-llama-3-8b","pricing":[{"threshold":0,"input":1.4e-7,"output":1.4e-7}],"contextLength":8192,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","functions","tools","top_k","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.14,"completion":0.14}}],"maxOutput":131072,"trainingDate":"2024-05-27T00:00:00.000Z","description":"Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","functions","tools","top_k","top_p"]},{"id":"kimi-k2-0711","name":"Kimi K2 (07/11)","author":"moonshotai","contextLength":131072,"endpoints":[{"provider":"novita","providerSlug":"novita","endpoint":{"author":"moonshotai","modelConfig":{"provider":"novita","author":"moonshotai","providerModelId":"moonshotai/kimi-k2-instruct","pricing":[{"threshold":0,"input":5.7e-7,"output":0.0000023}],"quantization":"fp8","contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"moonshotai/kimi-k2-instruct","pricing":[{"threshold":0,"input":5.7e-7,"output":0.0000023}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"]},"supportsPtb":true,"pricing":{"prompt":0.5700000000000001,"completion":2.3}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"moonshotai","modelConfig":{"provider":"openrouter","author":"moonshotai","providerModelId":"moonshotai/kimi-k2","pricing":[{"threshold":0,"input":0.00000105,"output":0.00000316}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"moonshotai/kimi-k2","pricing":[{"threshold":0,"input":0.00000105,"output":0.00000316}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":1.0499999999999998,"completion":3.1599999999999997}}],"maxOutput":16384,"trainingDate":"2025-01-01T00:00:00.000Z","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 agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p","top_k","repetition_penalty","structured_outputs"]},{"id":"kimi-k2-0905","name":"Kimi K2 (09/05)","author":"moonshotai","contextLength":262144,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"moonshotai","modelConfig":{"providerModelId":"moonshotai/Kimi-K2-Instruct-0905","provider":"deepinfra","author":"moonshotai","pricing":[{"threshold":0,"input":5e-7,"output":0.000002,"cacheMultipliers":{"cachedInput":0.8}}],"quantization":"fp4","contextLength":256000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"moonshotai/Kimi-K2-Instruct-0905","pricing":[{"threshold":0,"input":5e-7,"output":0.000002,"cacheMultipliers":{"cachedInput":0.8}}],"contextLength":256000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.5,"completion":2,"cacheRead":0.39999999999999997}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"moonshotai","modelConfig":{"provider":"novita","author":"moonshotai","providerModelId":"moonshotai/kimi-k2-0905","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"contextLength":262144,"maxCompletionTokens":262144,"supportedParameters":["structured_outputs","functions","tool_choice","tools","response_format","max_tokens","temperature","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"moonshotai/kimi-k2-0905","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"contextLength":262144,"maxCompletionTokens":262144,"ptbEnabled":true,"supportedParameters":["structured_outputs","functions","tool_choice","tools","response_format","max_tokens","temperature","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.5}},{"provider":"baseten","providerSlug":"baseten","endpoint":{"author":"moonshotai","modelConfig":{"provider":"baseten","author":"moonshotai","providerModelId":"moonshotai/Kimi-K2-Instruct-0905","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"contextLength":262000,"maxCompletionTokens":163800,"quantization":"fp4","supportedParameters":["structured_outputs","response_format","max_tokens","temperature","stop","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"baseten","providerModelId":"moonshotai/Kimi-K2-Instruct-0905","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"contextLength":262000,"maxCompletionTokens":163800,"ptbEnabled":true,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","stop","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.5}},{"provider":"fireworks","providerSlug":"fireworks","endpoint":{"author":"moonshotai","modelConfig":{"provider":"fireworks","author":"moonshotai","providerModelId":"accounts/fireworks/models/kimi-k2-instruct-0905","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"contextLength":262144,"maxCompletionTokens":262144,"supportedParameters":["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"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"fireworks","providerModelId":"accounts/fireworks/models/kimi-k2-instruct-0905","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"contextLength":262144,"maxCompletionTokens":262144,"ptbEnabled":true,"supportedParameters":["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"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.5}},{"provider":"groq","providerSlug":"groq","endpoint":{"author":"moonshotai","modelConfig":{"providerModelId":"moonshotai/kimi-k2-instruct-0905","provider":"groq","author":"moonshotai","pricing":[{"threshold":0,"input":0.000001,"output":0.000003,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":262144,"maxCompletionTokens":16384,"supportedParameters":["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"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"moonshotai/kimi-k2-instruct-0905","pricing":[{"threshold":0,"input":0.000001,"output":0.000003,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":262144,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["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"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":3,"cacheRead":0.5}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"moonshotai","modelConfig":{"provider":"openrouter","author":"moonshotai","providerModelId":"moonshotai/kimi-k2-0905","pricing":[{"threshold":0,"input":0.00000142,"output":0.00000528}],"contextLength":262144,"maxCompletionTokens":262144,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"moonshotai/kimi-k2-0905","pricing":[{"threshold":0,"input":0.00000142,"output":0.00000528}],"contextLength":262144,"maxCompletionTokens":262144,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":1.42,"completion":5.28}}],"maxOutput":16384,"trainingDate":"2025-09-05T00:00:00.000Z","description":"Enhanced version of Kimi K2 with doubled context window (256k tokens) and significantly improved coding capabilities, especially for frontend development. Features superior performance on public benchmarks (69.2% on SWE-bench Verified) and more polished code generation for web and 3D scenarios.\n\nKey Improvements\n2x Context Window: Increased from 128k to 256k tokens for better long-horizon task support.\nEnhanced Coding: Specialized training for frontend development, UI code generation, and tool calling.\nAgentic Capabilities: Improved reliability for code generation rivaling frontier closed models.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["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","functions"]},{"id":"kimi-k2-thinking","name":"Kimi K2 Thinking","author":"moonshotai","contextLength":256000,"endpoints":[{"provider":"canopywave","providerSlug":"canopywave","endpoint":{"author":"moonshotai","modelConfig":{"provider":"canopywave","author":"moonshotai","providerModelId":"moonshotai/kimi-k2-thinking","pricing":[{"threshold":0,"input":4.8e-7,"output":0.000002}],"quantization":"bf16","contextLength":262144,"maxCompletionTokens":262144,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tool_choice","tools","structured_outputs","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"canopywave","providerModelId":"moonshotai/kimi-k2-thinking","pricing":[{"threshold":0,"input":4.8e-7,"output":0.000002}],"contextLength":262144,"maxCompletionTokens":262144,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tool_choice","tools","structured_outputs","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.48,"completion":2}},{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"moonshotai","modelConfig":{"provider":"deepinfra","author":"moonshotai","providerModelId":"moonshotai/Kimi-K2-Thinking","pricing":[{"threshold":0,"input":5.5e-7,"output":0.0000025}],"quantization":"fp8","contextLength":256000,"maxCompletionTokens":8000,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"moonshotai/Kimi-K2-Thinking","pricing":[{"threshold":0,"input":5.5e-7,"output":0.0000025}],"contextLength":256000,"maxCompletionTokens":8000,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":0.55,"completion":2.5}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"moonshotai","modelConfig":{"provider":"novita","author":"moonshotai","providerModelId":"moonshotai/kimi-k2-thinking","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"quantization":"bf16","contextLength":262144,"maxCompletionTokens":262144,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tool_choice","tools","structured_outputs","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"moonshotai/kimi-k2-thinking","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"contextLength":262144,"maxCompletionTokens":262144,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tool_choice","tools","structured_outputs","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.5}},{"provider":"fireworks","providerSlug":"fireworks","endpoint":{"author":"moonshotai","modelConfig":{"provider":"fireworks","author":"moonshotai","providerModelId":"fireworks/kimi-k2-thinking","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"quantization":"int4","contextLength":256000,"maxCompletionTokens":4096,"supportedParameters":["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"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"fireworks","providerModelId":"fireworks/kimi-k2-thinking","pricing":[{"threshold":0,"input":6e-7,"output":0.0000025}],"contextLength":256000,"maxCompletionTokens":4096,"ptbEnabled":true,"supportedParameters":["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"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.5}}],"maxOutput":262144,"trainingDate":"2025-11-06T00:00:00.000Z","description":"Kimi K2 Thinking is a powerful open-source AI model from Moonshot AI designed for complex, step-by-step reasoning and long-horizon agentic tasks. It excels at solving challenging problems that require multiple steps of reasoning, data retrieval, and tool use, as it can execute up to 200–300 sequential tool calls without degradation. This makes it proficient in areas like math, coding, and autonomous web research by interleaving reasoning with tool invocation.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tool_choice","tools","structured_outputs","response_format","repetition_penalty","top_k","seed","min_p","logit_bias","logprobs","top_logprobs"]},{"id":"kimi-k2.5","name":"Kimi K2.5","author":"moonshotai","contextLength":262144,"endpoints":[{"provider":"fireworks","providerSlug":"fireworks","endpoint":{"author":"moonshotai","modelConfig":{"provider":"fireworks","author":"moonshotai","providerModelId":"accounts/fireworks/models/kimi-k2p5","pricing":[{"threshold":0,"input":0.0000012,"output":0.0000012,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":262144,"maxCompletionTokens":262144,"supportedParameters":["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"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"fireworks","providerModelId":"accounts/fireworks/models/kimi-k2p5","pricing":[{"threshold":0,"input":0.0000012,"output":0.0000012,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":262144,"maxCompletionTokens":262144,"ptbEnabled":true,"supportedParameters":["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"]},"supportsPtb":true,"pricing":{"prompt":1.2,"completion":1.2,"cacheRead":0.6}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"moonshotai","modelConfig":{"provider":"novita","author":"moonshotai","providerModelId":"moonshotai/kimi-k2.5","pricing":[{"threshold":0,"input":6e-7,"output":0.000003}],"contextLength":262144,"maxCompletionTokens":262144,"supportedParameters":["structured_outputs","functions","tool_choice","tools","response_format","max_tokens","temperature","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"moonshotai/kimi-k2.5","pricing":[{"threshold":0,"input":6e-7,"output":0.000003}],"contextLength":262144,"maxCompletionTokens":262144,"ptbEnabled":true,"supportedParameters":["structured_outputs","functions","tool_choice","tools","response_format","max_tokens","temperature","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":3}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"moonshotai","modelConfig":{"provider":"openrouter","author":"moonshotai","providerModelId":"moonshotai/kimi-k2.5","pricing":[{"threshold":0,"input":0.000001266,"output":0.000003165}],"contextLength":262144,"maxCompletionTokens":262144,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"moonshotai/kimi-k2.5","pricing":[{"threshold":0,"input":0.000001266,"output":0.000003165}],"contextLength":262144,"maxCompletionTokens":262144,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":1.266,"completion":3.165}}],"maxOutput":16384,"trainingDate":"2025-01-27T00:00:00.000Z","description":"Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. It delivers state-of-the-art visual coding capability and a self-directed agent swarm paradigm.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["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","seed","functions","min_p"]},{"id":"qwen2.5-coder-7b-fast","name":"Qwen2.5 Coder 7B fast","author":"alibaba","contextLength":32000,"endpoints":[{"provider":"nebius","providerSlug":"nebius","endpoint":{"author":"alibaba","modelConfig":{"providerModelId":"Qwen/Qwen2.5-Coder-7B-fast","provider":"nebius","author":"alibaba","pricing":[{"threshold":0,"input":3e-8,"output":9e-8}],"contextLength":32000,"maxCompletionTokens":8192,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"nebius","providerModelId":"Qwen/Qwen2.5-Coder-7B-fast","pricing":[{"threshold":0,"input":3e-8,"output":9e-8}],"contextLength":32000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs"]},"supportsPtb":true,"pricing":{"prompt":0.03,"completion":0.09}}],"maxOutput":8192,"trainingDate":"2024-09-15T00:00:00.000Z","description":"Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs"]},{"id":"qwen3-32b","name":"Qwen3 32B","author":"alibaba","contextLength":131072,"endpoints":[{"provider":"groq","providerSlug":"groq","endpoint":{"author":"alibaba","modelConfig":{"providerModelId":"Qwen/Qwen3-32B","provider":"groq","author":"alibaba","pricing":[{"threshold":0,"input":2.9e-7,"output":5.9e-7}],"contextLength":131072,"maxCompletionTokens":40960,"supportedParameters":["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"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"Qwen/Qwen3-32B","pricing":[{"threshold":0,"input":2.9e-7,"output":5.9e-7}],"contextLength":131072,"maxCompletionTokens":40960,"ptbEnabled":true,"supportedParameters":["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"]},"supportsPtb":true,"pricing":{"prompt":0.29,"completion":0.59}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"alibaba","modelConfig":{"providerModelId":"qwen/qwen3-32b","provider":"openrouter","author":"alibaba","pricing":[{"threshold":0,"input":4.22e-7,"output":8.44e-7}],"contextLength":40960,"maxCompletionTokens":40960,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"qwen/qwen3-32b","pricing":[{"threshold":0,"input":4.22e-7,"output":8.44e-7}],"contextLength":40960,"maxCompletionTokens":40960,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.422,"completion":0.844}}],"maxOutput":40960,"trainingDate":"2025-04-28T00:00:00.000Z","description":"Qwen3-32B is a 32.8 billion parameter language model that uniquely supports seamless switching between thinking mode for complex reasoning tasks and non-thinking mode for efficient general dialogue within a single model. The model excels across 100+ languages with enhanced reasoning capabilities, superior human preference alignment, and strong agent-based task performance, supporting up to 131,072 tokens with YaRN extension.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["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"]},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","author":"qwen","contextLength":41000,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"qwen","modelConfig":{"providerModelId":"Qwen/Qwen3-30B-A3B","provider":"deepinfra","author":"qwen","pricing":[{"threshold":0,"input":8e-8,"output":2.9e-7}],"rateLimits":{"rpm":12000,"tpm":60000000,"tpd":6000000000},"contextLength":32768,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","min_p"],"ptbEnabled":true,"quantization":"fp8","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"Qwen/Qwen3-30B-A3B","pricing":[{"threshold":0,"input":8e-8,"output":2.9e-7}],"contextLength":32768,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","min_p"]},"supportsPtb":true,"pricing":{"prompt":0.08,"completion":0.29}}],"maxOutput":41000,"trainingDate":"2025-06-01T00:00:00.000Z","description":"Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","seed","max_tokens","response_format","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","min_p"]},{"id":"qwen3-coder","name":"Qwen3 Coder 480B A35B Instruct Turbo","author":"qwen","contextLength":262144,"endpoints":[{"provider":"canopywave","providerSlug":"canopywave","endpoint":{"author":"alibaba","modelConfig":{"providerModelId":"qwen/qwen3-coder","provider":"canopywave","author":"alibaba","pricing":[{"threshold":0,"input":2.2e-7,"output":9.5e-7}],"contextLength":262144,"maxCompletionTokens":65536,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"quantization":"fp8","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"canopywave","providerModelId":"qwen/qwen3-coder","pricing":[{"threshold":0,"input":2.2e-7,"output":9.5e-7}],"contextLength":262144,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.22,"completion":0.95}},{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"qwen","modelConfig":{"providerModelId":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","provider":"deepinfra","author":"qwen","pricing":[{"threshold":0,"input":2.9e-7,"output":0.0000012}],"rateLimits":{"rpm":12000,"tpm":60000000,"tpd":6000000000},"contextLength":262144,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"quantization":"fp4","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","pricing":[{"threshold":0,"input":2.9e-7,"output":0.0000012}],"contextLength":262144,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.29,"completion":1.2}}],"maxOutput":16384,"trainingDate":"2025-07-23T00:00:00.000Z","description":"Qwen3-Coder-480B-A35B-Instruct is the Qwen3's most agentic code model, featuring significant performance on agentic coding, agentic browser-use and other foundational coding tasks, achieving results comparable to Claude Sonnet. This model supports multimodal capabilities including text, images, audio, video, and audio-visual reasoning.","inputModalities":["text","image","audio","video"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","author":"qwen","contextLength":262000,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"qwen","modelConfig":{"providerModelId":"Qwen/Qwen3-Next-80B-A3B-Instruct","provider":"deepinfra","author":"qwen","pricing":[{"threshold":0,"input":1.4e-7,"output":0.0000014}],"rateLimits":{"rpm":12000,"tpm":60000000,"tpd":6000000000},"quantization":"bf16","contextLength":262000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"Qwen/Qwen3-Next-80B-A3B-Instruct","pricing":[{"threshold":0,"input":1.4e-7,"output":0.0000014}],"contextLength":262000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.14,"completion":1.4}}],"maxOutput":16384,"trainingDate":"2025-01-01T00:00:00.000Z","description":"Qwen3-Next-80B-A3B-Instruct is a causal language model that is instruction-optimized for chat and agent applications. It features a Mixture-of-Experts (MoE) architecture that achieves an extremely low activation ratio, drastically reducing FLOPs per token while preserving model capacity. The model supports ultra-long contexts and has a Multi-Token Prediction (MTP) mechanism to boost performance and accelerate inference.","inputModalities":["text","image","video"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},{"id":"qwen3-235b-a22b-thinking","name":"Qwen3 235B A22B Thinking","author":"qwen","contextLength":262144,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"qwen","modelConfig":{"providerModelId":"Qwen/Qwen3-235B-A22B-Thinking-2507","provider":"deepinfra","author":"qwen","pricing":[{"threshold":0,"input":3e-7,"output":0.0000029}],"rateLimits":{"rpm":12000,"tpm":60000000,"tpd":6000000000},"quantization":"fp8","contextLength":262000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"Qwen/Qwen3-235B-A22B-Thinking-2507","pricing":[{"threshold":0,"input":3e-7,"output":0.0000029}],"contextLength":262000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":2.9000000000000004}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"qwen","modelConfig":{"providerModelId":"qwen/qwen3-235b-a22b-thinking-2507","provider":"novita","author":"qwen","pricing":[{"threshold":0,"input":3e-7,"output":0.000003}],"quantization":"fp8","contextLength":131072,"maxCompletionTokens":32768,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","functions","structured_outputs","reasoning"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"qwen/qwen3-235b-a22b-thinking-2507","pricing":[{"threshold":0,"input":3e-7,"output":0.000003}],"contextLength":131072,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","functions","structured_outputs","reasoning"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":3}}],"maxOutput":81920,"trainingDate":"2025-07-25T00:00:00.000Z","description":"Qwen3-235B-A22B-Thinking-2507 is the Qwen3's new model with scaling the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning.","inputModalities":["text","image","video"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","functions","structured_outputs","reasoning"]},{"id":"qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","author":"alibaba","contextLength":256000,"endpoints":[{"provider":"novita","providerSlug":"novita","endpoint":{"author":"alibaba","modelConfig":{"providerModelId":"qwen/qwen3-vl-235b-a22b-instruct","provider":"novita","author":"alibaba","pricing":[{"threshold":0,"input":3e-7,"output":0.0000015}],"quantization":"bf16","contextLength":131072,"maxCompletionTokens":32768,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"qwen/qwen3-vl-235b-a22b-instruct","pricing":[{"threshold":0,"input":3e-7,"output":0.0000015}],"contextLength":131072,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":1.5}}],"maxOutput":16384,"trainingDate":"2025-09-23T00:00:00.000Z","description":"Qwen3 VL 235B A22B Instruct is a powerful, open-weight multimodal model from Alibaba Cloud that excels at both language and vision tasks. It integrates strong text generation with advanced visual understanding of images and video, enabling applications like visual question answering, document parsing, chart extraction, and multilingual OCR. Key features include robust perception, spatial and long-form video comprehension, and the ability to follow complex instructions in multi-turn dialogues. This model also supports agentic interactions and tool use, including visual coding and GUI automation. ","inputModalities":["text","image","video"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B Instruct","author":"alibaba","contextLength":262144,"endpoints":[{"provider":"nebius","providerSlug":"nebius","endpoint":{"author":"qwen","modelConfig":{"providerModelId":"Qwen/Qwen3-Coder-30B-A3B-Instruct","provider":"nebius","author":"qwen","pricing":[{"threshold":0,"input":1e-7,"output":3e-7}],"quantization":"fp8","contextLength":262144,"maxCompletionTokens":262144,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"nebius","providerModelId":"Qwen/Qwen3-Coder-30B-A3B-Instruct","pricing":[{"threshold":0,"input":1e-7,"output":3e-7}],"contextLength":262144,"maxCompletionTokens":262144,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs"]},"supportsPtb":true,"pricing":{"prompt":0.09999999999999999,"completion":0.3}}],"maxOutput":262144,"trainingDate":"2025-07-31T00:00:00.000Z","description":"This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements: (a) Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks. (b) Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding. (c) Agentic Coding supporting for most platform such as Qwen Code, CLINE, featuring a specially designed function call format.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs"]},{"id":"deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","author":"deepseek","contextLength":128000,"endpoints":[{"provider":"chutes","providerSlug":"chutes","endpoint":{"author":"deepseek","modelConfig":{"provider":"chutes","author":"deepseek","providerModelId":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","pricing":[{"threshold":0,"input":3e-8,"output":1.3e-7}],"contextLength":128000,"maxCompletionTokens":32768,"supportedParameters":["max_tokens","temperature","top_p","stop","top_k","seed","min_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"chutes","providerModelId":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","pricing":[{"threshold":0,"input":3e-8,"output":1.3e-7}],"contextLength":128000,"maxCompletionTokens":32768,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","top_k","seed","min_p"]},"supportsPtb":true,"pricing":{"prompt":0.03,"completion":0.13}},{"provider":"groq","providerSlug":"groq","endpoint":{"author":"deepseek","modelConfig":{"providerModelId":"deepseek-r1-distill-llama-70b","provider":"groq","author":"deepseek","pricing":[{"threshold":0,"input":7.5e-7,"output":9.9e-7}],"contextLength":128000,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"groq","providerModelId":"deepseek-r1-distill-llama-70b","pricing":[{"threshold":0,"input":7.5e-7,"output":9.9e-7}],"contextLength":128000,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.75,"completion":0.9900000000000001}},{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"deepseek","modelConfig":{"provider":"deepinfra","author":"deepseek","providerModelId":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","pricing":[{"threshold":0,"input":6e-7,"output":0.0000012}],"contextLength":131072,"maxCompletionTokens":16384,"quantization":"fp8","supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","pricing":[{"threshold":0,"input":6e-7,"output":0.0000012}],"contextLength":131072,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":1.2}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"deepseek","modelConfig":{"provider":"openrouter","author":"deepseek","providerModelId":"deepseek/deepseek-r1-distill-llama-70b","pricing":[{"threshold":0,"input":0.00000211,"output":0.00000211}],"contextLength":131072,"maxCompletionTokens":131072,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"deepseek/deepseek-r1-distill-llama-70b","pricing":[{"threshold":0,"input":0.00000211,"output":0.00000211}],"contextLength":131072,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":2.1100000000000003,"completion":2.1100000000000003}}],"maxOutput":4096,"trainingDate":"2025-01-20T00:00:00.000Z","description":"DeepSeek-R1-Distill-Llama-70B is a 70-billion parameter model created by distilling the reasoning capabilities of DeepSeek's flagship R1 model (671B parameters) into Meta's Llama-3.3-70B-Instruct base. It achieves exceptional performance on mathematical reasoning and coding benchmarks (94.5% on MATH-500, 1633 CodeForces rating), rivaling OpenAI's o1-mini while being fully open-source under MIT license. The model demonstrates that advanced reasoning patterns from larger models can be effectively transferred to smaller, more deployable architectures through knowledge distillation.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p","response_format"]},{"id":"deepseek-v3","name":"DeepSeek V3","author":"deepseek","contextLength":128000,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"deepseek","modelConfig":{"provider":"deepinfra","author":"deepseek","providerModelId":"deepseek-ai/DeepSeek-V3.1","pricing":[{"threshold":0,"input":2.7e-7,"output":0.000001,"cacheMultipliers":{"cachedInput":0.8}}],"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"quantization":"fp4","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"deepseek-ai/DeepSeek-V3.1","pricing":[{"threshold":0,"input":2.7e-7,"output":0.000001,"cacheMultipliers":{"cachedInput":0.8}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.27,"completion":1,"cacheRead":0.21600000000000003}},{"provider":"deepseek","providerSlug":"deepseek","endpoint":{"author":"deepseek","modelConfig":{"provider":"deepseek","author":"deepseek","providerModelId":"deepseek-chat","pricing":[{"threshold":0,"input":5.6e-7,"output":0.00000168,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":128000,"maxCompletionTokens":8192,"supportedParameters":["frequency_penalty","function_call","functions","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepseek","providerModelId":"deepseek-chat","pricing":[{"threshold":0,"input":5.6e-7,"output":0.00000168,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":128000,"maxCompletionTokens":8192,"ptbEnabled":true,"supportedParameters":["frequency_penalty","function_call","functions","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.56,"completion":1.68,"cacheRead":0.07}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"deepseek","modelConfig":{"provider":"openrouter","author":"deepseek","providerModelId":"deepseek/deepseek-chat-v3.1","pricing":[{"threshold":0,"input":0.00000316,"output":0.00000475}],"contextLength":163840,"maxCompletionTokens":163840,"supportedParameters":["frequency_penalty","function_call","functions","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","tool_choice","tools","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"deepseek/deepseek-chat-v3.1","pricing":[{"threshold":0,"input":0.00000316,"output":0.00000475}],"contextLength":163840,"maxCompletionTokens":163840,"ptbEnabled":true,"supportedParameters":["frequency_penalty","function_call","functions","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","tool_choice","tools","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":3.1599999999999997,"completion":4.75}}],"maxOutput":8192,"trainingDate":"2024-12-26T00:00:00.000Z","description":"DeepSeek-V3.1 (deepseek-chat) is a powerful generalist model with 671B parameters, offering exceptional performance at an economical price. It achieves strong results on mathematical reasoning, coding, and general language tasks. The model supports 128K context length with a default output of 4K tokens (max 8K) and features advanced capabilities like function calling and JSON output.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","function_call","functions","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","tool_choice","tools","top_logprobs","top_p","repetition_penalty","top_k","min_p"]},{"id":"deepseek-v3.1-terminus","name":"DeepSeek V3.1 Terminus","author":"deepseek","contextLength":128000,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"deepseek","modelConfig":{"provider":"deepinfra","author":"deepseek","providerModelId":"deepseek-ai/DeepSeek-V3.1-Terminus","pricing":[{"threshold":0,"input":2.7e-7,"output":0.000001,"cacheMultipliers":{"cachedInput":0.8}}],"quantization":"fp4","contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"deepseek-ai/DeepSeek-V3.1-Terminus","pricing":[{"threshold":0,"input":2.7e-7,"output":0.000001,"cacheMultipliers":{"cachedInput":0.8}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.27,"completion":1,"cacheRead":0.21600000000000003}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"deepseek","modelConfig":{"provider":"novita","author":"deepseek","providerModelId":"deepseek/deepseek-v3.1-terminus","pricing":[{"threshold":0,"input":2.7e-7,"output":0.000001}],"quantization":"fp8","contextLength":98304,"maxCompletionTokens":65536,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"deepseek/deepseek-v3.1-terminus","pricing":[{"threshold":0,"input":2.7e-7,"output":0.000001}],"contextLength":98304,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.27,"completion":1}}],"maxOutput":16384,"trainingDate":"2025-09-22T00:00:00.000Z","description":"DeepSeek-V3.1 Terminus is an update to DeepSeek 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 performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process. Users can control the reasoning behaviour with the reasoning enabled boolean. The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","functions","structured_outputs","reasoning","tool_choice","tools","logit_bias"]},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","author":"deepseek","contextLength":163840,"endpoints":[{"provider":"canopywave","providerSlug":"canopywave","endpoint":{"author":"deepseek","modelConfig":{"provider":"canopywave","author":"deepseek","providerModelId":"deepseek/deepseek-chat-v3.2","pricing":[{"threshold":0,"input":2.6e-7,"output":4e-7}],"quantization":"fp8","contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"canopywave","providerModelId":"deepseek/deepseek-chat-v3.2","pricing":[{"threshold":0,"input":2.6e-7,"output":4e-7}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.26,"completion":0.39999999999999997}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"deepseek","modelConfig":{"provider":"novita","author":"deepseek","providerModelId":"deepseek/deepseek-v3.2-exp","pricing":[{"threshold":0,"input":2.7e-7,"output":4.1e-7}],"quantization":"fp8","contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"deepseek/deepseek-v3.2-exp","pricing":[{"threshold":0,"input":2.7e-7,"output":4.1e-7}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.27,"completion":0.41}},{"provider":"baseten","providerSlug":"baseten","endpoint":{"author":"deepseek","modelConfig":{"provider":"baseten","author":"deepseek","providerModelId":"deepseek-ai/DeepSeek-V3.2","pricing":[{"threshold":0,"input":3e-7,"output":4.5e-7}],"quantization":"fp8","contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","response_format","structured_outputs","top_k","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"baseten","providerModelId":"deepseek-ai/DeepSeek-V3.2","pricing":[{"threshold":0,"input":3e-7,"output":4.5e-7}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","response_format","structured_outputs","top_k","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":0.44999999999999996}}],"maxOutput":65536,"trainingDate":"2025-09-22T00:00:00.000Z","description":"DeepSeek-V3.2-Exp is an experimental model introducing the groundbreaking DeepSeek Sparse Attention (DSA) mechanism for enhanced long-context processing efficiency. Built on V3.1-Terminus, DSA achieves fine-grained sparse attention while maintaining identical output quality. This delivers substantial computational efficiency improvements without compromising accuracy. Comprehensive benchmarks confirm V3.2-Exp matches V3.1-Terminus performance, proving efficiency gains don't sacrifice capability. As both a powerful tool and research platform, it establishes new paradigms for efficient long-context AI processing.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["tools","tool_choice","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias","response_format","structured_outputs"]},{"id":"deepseek-reasoner","name":"DeepSeek Reasoner","author":"deepseek","contextLength":128000,"endpoints":[{"provider":"deepseek","providerSlug":"deepseek","endpoint":{"author":"deepseek","modelConfig":{"provider":"deepseek","author":"deepseek","providerModelId":"deepseek-reasoner","pricing":[{"threshold":0,"input":5.6e-7,"output":0.00000168,"cacheMultipliers":{"cachedInput":0.125}}],"quantization":"fp4","contextLength":128000,"maxCompletionTokens":64000,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepseek","providerModelId":"deepseek-reasoner","pricing":[{"threshold":0,"input":5.6e-7,"output":0.00000168,"cacheMultipliers":{"cachedInput":0.125}}],"contextLength":128000,"maxCompletionTokens":64000,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":0.56,"completion":1.68,"cacheRead":0.07}},{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"deepseek","modelConfig":{"provider":"deepinfra","author":"deepseek","providerModelId":"deepseek-ai/DeepSeek-R1-0528","pricing":[{"threshold":0,"input":5e-7,"output":0.00000215,"cacheMultipliers":{"cachedInput":0.8}}],"rateLimits":{"rpm":12000,"tpm":60000000,"tpd":6000000000},"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"deepseek-ai/DeepSeek-R1-0528","pricing":[{"threshold":0,"input":5e-7,"output":0.00000215,"cacheMultipliers":{"cachedInput":0.8}}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":0.5,"completion":2.1500000000000004,"cacheRead":0.39999999999999997}},{"provider":"openrouter","providerSlug":"openrouter","endpoint":{"author":"deepseek","modelConfig":{"provider":"openrouter","author":"deepseek","providerModelId":"deepseek/deepseek-r1","pricing":[{"threshold":0,"input":0.00000316,"output":0.00000844}],"contextLength":163840,"maxCompletionTokens":163840,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","top_logprobs","top_p"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"openrouter","providerModelId":"deepseek/deepseek-r1","pricing":[{"threshold":0,"input":0.00000316,"output":0.00000844}],"contextLength":163840,"maxCompletionTokens":163840,"ptbEnabled":true,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","top_logprobs","top_p"]},"supportsPtb":true,"pricing":{"prompt":3.1599999999999997,"completion":8.440000000000001}}],"maxOutput":64000,"trainingDate":"2025-01-20T00:00:00.000Z","description":"DeepSeek-Reasoner (DeepSeek-V3.1 Thinking Mode) is designed for advanced reasoning, mathematical problem-solving, and complex coding tasks. It uses chain-of-thought reasoning to break down complex problems and achieve superior performance on reasoning benchmarks. Supports 128K context with a default output of 32K tokens (max 64K) for extensive reasoning chains.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","stream","temperature","top_logprobs","top_p","repetition_penalty","top_k","min_p"]},{"id":"deepseek-tng-r1t2-chimera","name":"DeepSeek TNG R1T2 Chimera","author":"deepseek","contextLength":130000,"endpoints":[{"provider":"chutes","providerSlug":"chutes","endpoint":{"author":"deepseek","modelConfig":{"provider":"chutes","author":"deepseek","providerModelId":"tngtech/DeepSeek-TNG-R1T2-Chimera","pricing":[{"threshold":0,"input":3e-7,"output":0.0000012}],"contextLength":130000,"maxCompletionTokens":163840,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logprobs","logit_bias","top_logprobs","functions","tools"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"chutes","providerModelId":"tngtech/DeepSeek-TNG-R1T2-Chimera","pricing":[{"threshold":0,"input":3e-7,"output":0.0000012}],"contextLength":130000,"maxCompletionTokens":163840,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logprobs","logit_bias","top_logprobs","functions","tools"]},"supportsPtb":true,"pricing":{"prompt":0.3,"completion":1.2}}],"maxOutput":163840,"trainingDate":"2025-07-02T00:00:00.000Z","description":"DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0324 checkpoints with an Assembly-of-Experts merge. The tri-parent design yields strong reasoning performance while running roughly 20 % faster than the original R1 and more than 2× faster than R1-0528 under vLLM, giving a favorable cost-to-intelligence trade-off. The checkpoint supports contexts up to 60 k tokens in standard use (tested to ~130 k) and maintains consistent <think> token behaviour, making it suitable for long-context analysis, dialogue and other open-ended generation tasks.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logprobs","logit_bias","top_logprobs","functions","tools"]},{"id":"mistral-nemo","name":"Mistral Nemo","author":"mistral","contextLength":128000,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"mistral","modelConfig":{"providerModelId":"mistralai/Mistral-Nemo-Instruct-2407","provider":"deepinfra","author":"mistral","pricing":[{"threshold":0,"input":0.00002,"output":0.00004}],"rateLimits":{"rpm":12000,"tpm":60000000,"tpd":6000000000},"quantization":"fp8","contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"mistralai/Mistral-Nemo-Instruct-2407","pricing":[{"threshold":0,"input":0.00002,"output":0.00004}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":20,"completion":40}}],"maxOutput":16400,"trainingDate":"2024-07-18T00:00:00.000Z","description":"The Mistral-Nemo-Instruct-2407 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-Nemo-Base-2407. Trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},{"id":"mistral-small","name":"Mistral Small","author":"mistral","contextLength":128000,"endpoints":[{"provider":"deepinfra","providerSlug":"deepinfra","endpoint":{"author":"mistral","modelConfig":{"providerModelId":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","provider":"deepinfra","author":"mistral","pricing":[{"threshold":0,"input":0.000075,"output":0.0002}],"rateLimits":{"rpm":12000,"tpm":60000000,"tpd":6000000000},"contextLength":128000,"maxCompletionTokens":16384,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"],"ptbEnabled":true,"quantization":"fp8","endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"deepinfra","providerModelId":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","pricing":[{"threshold":0,"input":0.000075,"output":0.0002}],"contextLength":128000,"maxCompletionTokens":16384,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},"supportsPtb":true,"pricing":{"prompt":75,"completion":200}}],"maxOutput":128000,"trainingDate":"2024-02-26T00:00:00.000Z","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 WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks. It supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).","inputModalities":["text","image"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format"]},{"id":"mistral-large-2411","name":"Mistral-Large","author":"mistral","contextLength":128000,"endpoints":[{"provider":"mistral","providerSlug":"mistral","endpoint":{"author":"mistral","modelConfig":{"providerModelId":"mistral-large-2411","provider":"mistral","author":"mistral","pricing":[{"threshold":0,"input":0.000002,"output":0.000006}],"contextLength":128000,"maxCompletionTokens":4096,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"mistral","providerModelId":"mistral-large-2411","pricing":[{"threshold":0,"input":0.000002,"output":0.000006}],"contextLength":128000,"maxCompletionTokens":4096,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":6}}],"maxOutput":32768,"trainingDate":"2024-07-24T00:00:00.000Z","description":"Mistral Large 2.1","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"]},{"id":"glm-4.6","name":"Zai GLM-4.6","author":"zai","contextLength":204800,"endpoints":[{"provider":"canopywave","providerSlug":"canopywave","endpoint":{"author":"zai","modelConfig":{"providerModelId":"zai/glm-4.6","provider":"canopywave","author":"zai","pricing":[{"threshold":0,"input":4.5e-7,"output":0.0000015}],"quantization":"bf16","contextLength":204800,"maxCompletionTokens":131072,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"canopywave","providerModelId":"zai/glm-4.6","pricing":[{"threshold":0,"input":4.5e-7,"output":0.0000015}],"contextLength":204800,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.44999999999999996,"completion":1.5}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"zai","modelConfig":{"providerModelId":"zai-org/glm-4.6","provider":"novita","author":"zai","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022}],"quantization":"bf16","contextLength":204800,"maxCompletionTokens":131072,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"zai-org/glm-4.6","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022}],"contextLength":204800,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.2}},{"provider":"baseten","providerSlug":"baseten","endpoint":{"author":"zai","modelConfig":{"providerModelId":"zai-org/GLM-4.6","provider":"baseten","author":"zai","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022}],"quantization":"bf16","contextLength":200000,"maxCompletionTokens":131072,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"baseten","providerModelId":"zai-org/GLM-4.6","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022}],"contextLength":200000,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.2}}],"maxOutput":131072,"trainingDate":"2024-07-18T00:00:00.000Z","description":"As the latest iteration in the GLM series, GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},{"id":"glm-4.7","name":"Zai GLM-4.7","author":"zai","contextLength":204800,"endpoints":[{"provider":"canopywave","providerSlug":"canopywave","endpoint":{"author":"zai","modelConfig":{"providerModelId":"zai/glm-4.7","provider":"canopywave","author":"zai","pricing":[{"threshold":0,"input":4.3e-7,"output":0.00000175}],"quantization":"bf16","contextLength":198000,"maxCompletionTokens":131072,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"canopywave","providerModelId":"zai/glm-4.7","pricing":[{"threshold":0,"input":4.3e-7,"output":0.00000175}],"contextLength":198000,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.43,"completion":1.75}},{"provider":"novita","providerSlug":"novita","endpoint":{"author":"zai","modelConfig":{"providerModelId":"zai-org/glm-4.7","provider":"novita","author":"zai","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022,"cacheMultipliers":{"cachedInput":0.183}}],"quantization":"fp8","contextLength":204800,"maxCompletionTokens":131072,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"zai-org/glm-4.7","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022,"cacheMultipliers":{"cachedInput":0.183}}],"contextLength":204800,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.2,"cacheRead":0.1098}},{"provider":"fireworks","providerSlug":"fireworks","endpoint":{"author":"zai","modelConfig":{"providerModelId":"accounts/fireworks/models/glm-4p7","provider":"fireworks","author":"zai","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022,"cacheMultipliers":{"cachedInput":0.5}}],"quantization":"fp8","contextLength":198000,"maxCompletionTokens":131072,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"fireworks","providerModelId":"accounts/fireworks/models/glm-4p7","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022,"cacheMultipliers":{"cachedInput":0.5}}],"contextLength":198000,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.2,"cacheRead":0.3}},{"provider":"baseten","providerSlug":"baseten","endpoint":{"author":"zai","modelConfig":{"providerModelId":"zai-org/GLM-4.7","provider":"baseten","author":"zai","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022}],"quantization":"bf16","contextLength":200000,"maxCompletionTokens":131072,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"baseten","providerModelId":"zai-org/GLM-4.7","pricing":[{"threshold":0,"input":6e-7,"output":0.0000022}],"contextLength":200000,"maxCompletionTokens":131072,"ptbEnabled":true,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.6,"completion":2.2}},{"provider":"cerebras","providerSlug":"cerebras","endpoint":{"author":"zai","modelConfig":{"providerModelId":"zai-glm-4.7","provider":"cerebras","author":"zai","pricing":[{"threshold":0,"input":0.00000225,"output":0.00000275}],"quantization":"bf16","contextLength":131072,"maxCompletionTokens":40000,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"cerebras","providerModelId":"zai-glm-4.7","pricing":[{"threshold":0,"input":0.00000225,"output":0.00000275}],"contextLength":131072,"maxCompletionTokens":40000,"ptbEnabled":true,"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":2.25,"completion":2.75}}],"maxOutput":131072,"trainingDate":"2024-12-22T00:00:00.000Z","description":"GLM-4.7 is Zhipu AI's flagship coding model with major upgrades in advanced coding capabilities, multi-step reasoning, and agentic orchestration. Features Interleaved, Preserved, and Turn-level thinking modes.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["functions","structured_outputs","reasoning","tool_choice","tools","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},{"id":"ernie-4.5-21b-a3b-thinking","name":"Baidu Ernie 4.5 21B A3B Thinking","author":"baidu","contextLength":128000,"endpoints":[{"provider":"novita","providerSlug":"novita","endpoint":{"author":"baidu","modelConfig":{"provider":"novita","author":"baidu","providerModelId":"baidu/ernie-4.5-21B-A3B-Thinking","pricing":[{"threshold":0,"input":7e-8,"output":2.8e-7}],"quantization":"fp8","contextLength":131072,"maxCompletionTokens":65536,"supportedParameters":["reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"novita","providerModelId":"baidu/ernie-4.5-21B-A3B-Thinking","pricing":[{"threshold":0,"input":7e-8,"output":2.8e-7}],"contextLength":131072,"maxCompletionTokens":65536,"ptbEnabled":true,"supportedParameters":["reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},"supportsPtb":true,"pricing":{"prompt":0.07,"completion":0.28}}],"maxOutput":8000,"trainingDate":"2025-03-16T00:00:00.000Z","description":"ERNIE-4.5-21B-A3B-Thinking is a text-based Mixture of Experts (MoE) post-training model featuring 21B total parameters with 3B active parameters per token. It delivers enhanced performance on reasoning tasks, including logical reasoning, mathematics, science, coding, text generation, and academic benchmarks that typically require human expertise. The model offers efficient tool utilization capabilities and supports up to 128K tokens for long-context understanding.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","logit_bias"]},{"id":"sonar","name":"Perplexity Sonar","author":"perplexity","contextLength":127000,"endpoints":[{"provider":"perplexity","providerSlug":"perplexity","endpoint":{"author":"perplexity","modelConfig":{"providerModelId":"sonar","provider":"perplexity","author":"perplexity","pricing":[{"threshold":0,"input":0.000001,"output":0.000001,"request":0.005,"web_search":0.005}],"contextLength":127000,"maxCompletionTokens":4096,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"perplexity","providerModelId":"sonar","pricing":[{"threshold":0,"input":0.000001,"output":0.000001,"request":0.005,"web_search":0.005}],"contextLength":127000,"maxCompletionTokens":4096,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":1,"web_search":5000}}],"maxOutput":4096,"trainingDate":"2025-01-27T00:00:00.000Z","description":"Fast and accurate web-grounded chat model with real-time search capabilities. Ideal for general queries requiring up-to-date information from the web.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop"]},{"id":"sonar-pro","name":"Perplexity Sonar Pro","author":"perplexity","contextLength":200000,"endpoints":[{"provider":"perplexity","providerSlug":"perplexity","endpoint":{"author":"perplexity","modelConfig":{"providerModelId":"sonar-pro","provider":"perplexity","author":"perplexity","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0.006,"web_search":0.006}],"contextLength":200000,"maxCompletionTokens":4096,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"perplexity","providerModelId":"sonar-pro","pricing":[{"threshold":0,"input":0.000003,"output":0.000015,"request":0.006,"web_search":0.006}],"contextLength":200000,"maxCompletionTokens":4096,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop"]},"supportsPtb":true,"pricing":{"prompt":3,"completion":15,"web_search":6000}}],"maxOutput":4096,"trainingDate":"2025-01-27T00:00:00.000Z","description":"Advanced web-grounded chat model with enhanced search quality and 200K context window. Best for complex queries requiring comprehensive web research.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop"]},{"id":"sonar-reasoning","name":"Perplexity Sonar Reasoning","author":"perplexity","contextLength":127000,"endpoints":[{"provider":"perplexity","providerSlug":"perplexity","endpoint":{"author":"perplexity","modelConfig":{"providerModelId":"sonar-reasoning","provider":"perplexity","author":"perplexity","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"request":0.005,"web_search":0.005}],"contextLength":127000,"maxCompletionTokens":4096,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop","reasoning"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"perplexity","providerModelId":"sonar-reasoning","pricing":[{"threshold":0,"input":0.000001,"output":0.000005,"request":0.005,"web_search":0.005}],"contextLength":127000,"maxCompletionTokens":4096,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop","reasoning"]},"supportsPtb":true,"pricing":{"prompt":1,"completion":5,"web_search":5000}}],"maxOutput":4096,"trainingDate":"2025-01-27T00:00:00.000Z","description":"Web-grounded reasoning model that thinks step-by-step before responding. Combines search capabilities with logical reasoning for accurate, well-reasoned answers.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop","reasoning"]},{"id":"sonar-reasoning-pro","name":"Perplexity Sonar Reasoning Pro","author":"perplexity","contextLength":127000,"endpoints":[{"provider":"perplexity","providerSlug":"perplexity","endpoint":{"author":"perplexity","modelConfig":{"providerModelId":"sonar-reasoning-pro","provider":"perplexity","author":"perplexity","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"request":0.006,"web_search":0.006}],"contextLength":127000,"maxCompletionTokens":4096,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop","reasoning"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"perplexity","providerModelId":"sonar-reasoning-pro","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"request":0.006,"web_search":0.006}],"contextLength":127000,"maxCompletionTokens":4096,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop","reasoning"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":8,"web_search":6000}}],"maxOutput":4096,"trainingDate":"2025-01-27T00:00:00.000Z","description":"Advanced reasoning model with 128K context window designed for complex, multi-step queries. Provides in-depth analysis with web-grounded research and logical reasoning.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop","reasoning"]},{"id":"sonar-deep-research","name":"Perplexity Sonar Deep Research","author":"perplexity","contextLength":127000,"endpoints":[{"provider":"perplexity","providerSlug":"perplexity","endpoint":{"author":"perplexity","modelConfig":{"providerModelId":"sonar-deep-research","provider":"perplexity","author":"perplexity","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"request":0,"web_search":0.005}],"contextLength":127000,"maxCompletionTokens":4096,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop","reasoning"],"ptbEnabled":true,"endpointConfigs":{"*":{}}},"userConfig":{"region":"*","location":"*"},"provider":"perplexity","providerModelId":"sonar-deep-research","pricing":[{"threshold":0,"input":0.000002,"output":0.000008,"request":0,"web_search":0.005}],"contextLength":127000,"maxCompletionTokens":4096,"ptbEnabled":true,"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop","reasoning"]},"supportsPtb":true,"pricing":{"prompt":2,"completion":8,"web_search":5000}}],"maxOutput":4096,"trainingDate":"2025-01-27T00:00:00.000Z","description":"Specialized research model that conducts comprehensive multi-query searches with citation tracking and reasoning tokens. Automatically determines search depth needed for thorough investigation.","inputModalities":["text"],"outputModalities":["text"],"supportedParameters":["max_tokens","temperature","top_p","frequency_penalty","response_format","stop","reasoning"]}],"total":111,"filters":{"providers":[{"name":"anthropic","displayName":"Anthropic"},{"name":"azure","displayName":"Azure OpenAI"},{"name":"baseten","displayName":"Baseten"},{"name":"bedrock","displayName":"AWS Bedrock"},{"name":"canopywave","displayName":"Canopy Wave"},{"name":"cerebras","displayName":"Cerebras"},{"name":"chutes","displayName":"Chutes"},{"name":"deepinfra","displayName":"DeepInfra"},{"name":"deepseek","displayName":"DeepSeek"},{"name":"fireworks","displayName":"Fireworks"},{"name":"google-ai-studio","displayName":"Google AI Studio"},{"name":"groq","displayName":"Groq"},{"name":"helicone","displayName":"Helicone"},{"name":"mistral","displayName":"Mistral AI"},{"name":"nebius","displayName":"Nebius Token Factory"},{"name":"novita","displayName":"Novita"},{"name":"openai","displayName":"OpenAI"},{"name":"openrouter","displayName":"OpenRouter"},{"name":"perplexity","displayName":"Perplexity"},{"name":"vertex","displayName":"Vertex AI"},{"name":"xai","displayName":"xAI"}],"authors":["alibaba","anthropic","baidu","deepseek","google","meta-llama","mistral","moonshotai","openai","perplexity","qwen","xai","zai"],"capabilities":["audio","caching","image","web_search"]}},"error":null}