{"data":[{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.003,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","developer":"DeepSeek","input_price_per_million":0.15,"intelligence_score":39.5,"last_verified":"2026-09-11T13:08:15.118580","max_output_tokens":384000,"metadata":{"attachment":true,"family":"deepseek-flash","knowledge":"2025-05","license":"MIT","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Image, Text","name":"DeepSeek V4.1 Flash","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1000000,"cost":{"cache_read":0.003,"input":0.15,"output":0.6},"doc":"https://docs.nano-gpt.com","output":384000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"deepseek/deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1050000,"cost":{"cache_read":0.003,"input":0.15,"output":0.6},"doc":"https://llmgateway.io/docs","output":393216,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"deepseek/deepseek-v4.1-flash","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"doc":"https://hyper.charm.land","output":26214,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://requesty.ai/solution/llm-routing/models","output":393216,"provider":"Requesty","provider_id":"requesty","provider_model_id":"deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":1048576,"cost":{"input":0.3,"output":1.2},"doc":"https://huggingface.co/docs/inference-providers","output":384000,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1000000,"cost":{"cache_read":0.0054,"cache_write":0.27,"input":0.27,"output":1.08},"doc":"https://www.crossmodel.ai/docs","output":384000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"deepseek/deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.006,"input":0.3,"output":1.2},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":393216,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"deepseek/deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.0075,"input":0.375,"output":1.5},"doc":"https://docs.venice.ai","output":131072,"provider":"Venice AI","provider_id":"venice","provider_model_id":"deepseek-v4-1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1050000,"cost":{"cache_read":0.003,"input":0.15,"output":0.6},"doc":"https://llmgateway.io/docs","output":384000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":1000000,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://fireworks.ai/docs/","output":384000,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/deepseek-v4p1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.006,"input":0.2,"output":0.6},"doc":"https://deepinfra.com/models","output":384000,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.006,"input":0.3,"output":1.2},"doc":"https://kilo.ai","output":384000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"deepseek/deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1000000,"cost":{"cache_read":0.003,"input":0.15,"output":0.6},"doc":"https://docs.merge.dev/merge-gateway","output":384000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"deepseek/deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.deepseek.com","context":1000000,"cost":{"cache_read":0.003,"input":0.15,"output":0.6,"reasoning":0.6},"doc":"https://api-docs.deepseek.com/quick_start/pricing","output":384000,"provider":"DeepSeek","provider_id":"deepseek","provider_model_id":"deepseek-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.003,"input":0.15,"output":0.6},"doc":"https://openrouter.ai/models","output":384000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"deepseek/deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.006,"input":0.3,"output":1.2},"doc":"https://ofox.ai/docs","output":384000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"deepseek/deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":1000000,"cost":{"cache_read":0.003,"input":0.15,"output":0.6},"doc":"https://opencode.ai/docs/zen","output":384000,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"deepseek-v4.1-flash","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":0.6,"release_date":"2026-09-10","slug":"deepseek/deepseek-v4.1-flash","source":"Models.dev","source_url":"https://models.dev/models/deepseek/deepseek-v4.1-flash/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":2.0,"coding_score":0.0,"confidence":"Medium","context_length":1050000,"description":"Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.","developer":"OpenAI","input_price_per_million":20.0,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:15.872564","max_output_tokens":128000,"metadata":{"attachment":true,"family":"gpt-astra","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":false,"tool_call":true},"modalities":"Image, Pdf, Text","name":"GPT-6 Astra (Fast)","offerings":[{"api":"","context":1050000,"cost":{"cache_read":2,"cache_write":25,"context_over_200k":{"cache_read":4,"cache_write":25,"input":40,"output":150},"input":20,"output":100,"tiers":[{"cache_read":4,"cache_write":25,"input":40,"output":150,"tier":{"size":272001,"type":"context"}}]},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"openai/gpt-6-astra-fast","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":100.0,"release_date":"2026-09-04","slug":"openai/gpt-6-astra-fast","source":"Models.dev","source_url":"https://models.dev/models/openai/gpt-6-astra-fast/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":51.5,"benchmark_data":[{"date":"2026-09-03","name":"Agents' Last Exam","score":59.3,"source":"https://openai.com/index/gpt-6-astra/"},{"dataset":"V2-Offline (v2026.08.08)","date":"2026-09-03","metric":"partial score","name":"OSWorld","score":72.6,"source":"https://openai.com/index/gpt-6-astra/","version":"2.0"},{"date":"2026-09-03","metric":"accuracy","name":"ScreenSpot-Pro","score":92.7,"source":"https://openai.com/index/gpt-6-astra/","variant":"no tools"},{"date":"2026-09-03","metric":"success rate","name":"AutomationBench","score":41.4,"source":"https://openai.com/index/gpt-6-astra/"},{"date":"2026-09-03","metric":"geometric overlap","name":"BenchCAD","score":95.9,"source":"https://openai.com/index/gpt-6-astra/","variant":"with tools"},{"date":"2026-09-03","metric":"accuracy","name":"BrowseComp","score":91.5,"source":"https://openai.com/index/gpt-6-astra/"},{"date":"2026-09-03","metric":"success rate","name":"Terminal-Bench","score":57.9,"source":"https://openai.com/index/gpt-6-astra/","version":"4.0"},{"date":"2026-09-03","metric":"resolve rate","name":"DeepSWE","score":74.1,"source":"https://openai.com/index/gpt-6-astra/","version":"1.1"},{"dataset":"Extended","date":"2026-09-03","metric":"score","name":"FrontierCode","score":64.5,"source":"https://openai.com/index/gpt-6-astra/","version":"1.1"},{"date":"2026-09-03","metric":"success rate","name":"Terminal-Bench Science","score":64.6,"source":"https://openai.com/index/gpt-6-astra/","version":"0.1"},{"dataset":"Tier 4","date":"2026-09-03","metric":"accuracy","name":"FrontierMath","score":97.6,"source":"https://openai.com/index/gpt-6-astra/","version":"v2"},{"date":"2026-09-03","metric":"accuracy","name":"GPQA Diamond","score":96,"source":"https://openai.com/index/gpt-6-astra/"},{"date":"2026-09-03","metric":"accuracy","name":"Humanity's Last Exam","score":57.2,"source":"https://openai.com/index/gpt-6-astra/","variant":"with tools"},{"date":"2026-09-03","metric":"success rate","name":"ExploitBench","score":100,"source":"https://openai.com/index/gpt-6-astra/","variant":"without production safeguards"},{"date":"2026-09-03","metric":"success rate","name":"SRE-Bench","score":88,"source":"https://openai.com/index/gpt-6-astra/","variant":"single attempt"},{"date":"2026-09-03","harness":"Responses API","metric":"RHAE","name":"ARC-AGI-3","score":99.9,"source":"https://openai.com/index/gpt-6-astra/"},{"date":"2026-09-03","metric":"index score","name":"Artificial Analysis Intelligence Index","score":61,"source":"https://artificialanalysis.ai/articles/benchmarking-gpt-6-astra","variant":"max","version":"4.1.1"},{"date":"2026-09-03","harness":"Codex","metric":"index score","name":"Artificial Analysis Coding Agent Index","score":67,"source":"https://artificialanalysis.ai/articles/benchmarking-gpt-6-astra","variant":"max","version":"1.4"}],"cached_input_price_per_million":1.0,"coding_score":76.9,"confidence":"Medium","context_length":1050000,"description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","developer":"OpenAI","input_price_per_million":10.0,"intelligence_score":52.8,"last_verified":"2026-09-11T13:08:15.766485","max_output_tokens":128000,"metadata":{"attachment":true,"family":"gpt-astra","knowledge":"2026-04-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":false,"tool_call":true},"modalities":"Image, Pdf, Text","name":"GPT-6 Astra","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"doc":"https://docs.nano-gpt.com","output":128000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"openai/gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.vivgrid.com/v1","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.vivgrid.com/models","output":128000,"provider":"Vivgrid","provider_id":"vivgrid","provider_model_id":"gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"doc":"https://llmgateway.io/docs","output":128000,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"openai/gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1050000,"cost":{"cache_read":1,"context_over_200k":{"cache_read":2,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://requesty.ai/solution/llm-routing/models","output":128000,"provider":"Requesty","provider_id":"requesty","provider_model_id":"gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://www.crossmodel.ai/docs","output":128000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"openai/gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272001,"type":"context"}}]},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"openai/gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.github.com/en/copilot","output":128000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"openai/gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure","provider_id":"azure","provider_model_id":"gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":1.1,"cache_write":13.75,"context_over_200k":{"cache_read":2.2,"cache_write":27.5,"input":22,"output":82.5},"input":11,"output":55,"tiers":[{"cache_read":2.2,"cache_write":27.5,"input":22,"output":82.5,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","output":128000,"provider":"Amazon Bedrock","provider_id":"amazon-bedrock","provider_model_id":"openai.gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1050000,"cost":{"cache_read":1,"input":10,"output":50},"doc":"https://docs.merge.dev/merge-gateway","output":128000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"openai/gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://opencode.ai/docs/zen","output":128000,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://openrouter.ai/models","output":128000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"openai/gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"doc":"https://ofox.ai/docs","output":128000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"openai/gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://neon.com/docs","output":128000,"provider":"Neon","provider_id":"neon","provider_model_id":"gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://platform.openai.com/docs/models","output":128000,"provider":"OpenAI","provider_id":"openai","provider_model_id":"gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1050000,"cost":{"input":10,"output":50},"doc":"https://doc.302.ai","output":128000,"provider":"302.AI","provider_id":"302ai","provider_model_id":"gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1050000,"cost":{"cache_read":1,"cache_write":12.5,"context_over_200k":{"cache_read":2,"cache_write":25,"input":20,"output":75},"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.edenai.co","output":128000,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"openai/gpt-6-astra","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":50.0,"release_date":"2026-09-04","slug":"openai/gpt-6-astra","source":"Models.dev","source_url":"https://models.dev/models/openai/gpt-6-astra/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.17,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding","developer":"Alibaba Qwen","input_price_per_million":1.71,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:10.552378","max_output_tokens":131072,"metadata":{"attachment":true,"family":"qwen","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"temperature":true,"tool_call":true},"modalities":"Image, Pdf, Text, Video","name":"Qwen3.8 Max 0902","offerings":[{"api":"https://nano-gpt.com/api/v1","context":991808,"cost":{"cache_read":0.17,"cache_write":2.5,"input":2,"output":6},"doc":"https://docs.nano-gpt.com","output":131072,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"alibaba/qwen3.8-max-0902","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":991000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"alibaba/qwen3.8-max-0902","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":1000000,"cost":{"cache_read":2,"input":2,"output":6},"doc":"https://docs.empiriolabs.ai","output":131072,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"qwen3-8-max-0902","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://kilo.ai","output":131072,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"qwen/qwen3.8-max-0902","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://openrouter.ai/models","output":131072,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"qwen/qwen3.8-max-0902","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.17,"cache_write":2.14,"input":1.71,"output":5.14},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"qwen/qwen3.8-max-0902","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"bailian/qwen3.8-max-0902","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://docs.edenai.co","output":131072,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"qwen/qwen3.8-max-0902","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":5.14,"release_date":"2026-09-02","slug":"alibaba/qwen3.8-max-0902","source":"Models.dev","source_url":"https://models.dev/models/alibaba/qwen3.8-max-0902/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.15,"coding_score":0.0,"confidence":"Medium","context_length":1048576,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","developer":"Meta","input_price_per_million":1.25,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:13.514282","max_output_tokens":131072,"metadata":{"attachment":true,"family":"muse","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Audio, Image, Pdf, Text, Video","name":"Muse Spark 1.3","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://docs.nano-gpt.com","output":943718,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"meta/muse-spark-1.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://llmgateway.io/docs","output":1048576,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"meta/muse-spark-1.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":1048576,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"meta/muse-spark-1.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.meta.ai/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://dev.meta.ai/docs","output":131072,"provider":"Meta","provider_id":"meta","provider_model_id":"muse-spark-1.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://llmgateway.io/docs","output":131072,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"muse-spark-1.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":1048576,"cost":{"cache_read":1,"input":1.25,"output":4.25},"doc":"https://docs.empiriolabs.ai","output":131072,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"muse-spark-1-3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://kilo.ai","output":943718,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"meta/muse-spark-1.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://opencode.ai/docs/zen","output":131072,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"muse-spark-1.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://openrouter.ai/models","output":943718,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"meta/muse-spark-1.3","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":4.25,"release_date":"2026-09-02","slug":"meta/muse-spark-1.3","source":"Models.dev","source_url":"https://models.dev/models/meta/muse-spark-1.3/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":41.1,"benchmark_data":[],"cached_input_price_per_million":0.075,"coding_score":76.3,"confidence":"Medium","context_length":1048576,"description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","developer":"Google","input_price_per_million":0.75,"intelligence_score":41.2,"last_verified":"2026-09-11T13:08:13.205858","max_output_tokens":65536,"metadata":{"attachment":true,"family":"gemini-flash","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Audio, Image, Pdf, Text, Video","name":"Gemini 3.8 Flash","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"output":3.75},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"google/gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.vivgrid.com/v1","context":1048576,"cost":{"cache_read":0.15,"input":0.75,"output":3.75},"doc":"https://docs.vivgrid.com/models","output":128000,"provider":"Vivgrid","provider_id":"vivgrid","provider_model_id":"gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"input_audio":0.75,"output":3.75},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","output":65536,"provider":"Vertex","provider_id":"google-vertex","provider_model_id":"gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://requesty.ai/solution/llm-routing/models","output":65535,"provider":"Requesty","provider_id":"requesty","provider_model_id":"gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.75,"input":0.75,"output":3.75},"doc":"https://www.crossmodel.ai/docs","output":65536,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"gemini/gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"input_audio":0.75,"output":3.75},"doc":"https://ai.google.dev/gemini-api/docs/models","output":65536,"provider":"Google","provider_id":"google","provider_model_id":"gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":65536,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"google/gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.09375,"input":0.9375,"output":4.6875},"doc":"https://docs.venice.ai","output":65536,"provider":"Venice AI","provider_id":"venice","provider_model_id":"gemini-3-8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1000000,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://docs.github.com/en/copilot","output":64000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"output":3.75,"reasoning":3.75},"doc":"https://kilo.ai","output":65536,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"google/gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://docs.merge.dev/merge-gateway","output":65536,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"google/gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":7.5},"doc":"https://opencode.ai/docs/zen","output":65536,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"output":3.75,"reasoning":3.75},"doc":"https://openrouter.ai/models","output":65536,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"google/gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.075,"cache_write":0.0415,"input":0.75,"input_audio":0.75,"output":3.75},"doc":"https://ofox.ai/docs","output":65536,"provider":"Ofox","provider_id":"ofox","provider_model_id":"google/gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1048576,"cost":{"input":0.75,"output":3.75},"doc":"https://doc.302.ai","output":65536,"provider":"302.AI","provider_id":"302ai","provider_model_id":"gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1048576,"cost":{"cache_read":0.082,"cache_write":0.084,"input":0.825,"output":4.125},"doc":"https://api.cortecs.ai/v1/models","output":65535,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"doc":"https://docs.edenai.co","output":65536,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"google/gemini-3.8-flash","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":3.75,"release_date":"2026-09-02","slug":"google/gemini-3.8-flash","source":"Models.dev","source_url":"https://models.dev/models/google/gemini-3.8-flash/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.25,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"Claude model for demanding reasoning and long-horizon agentic work","developer":"Anthropic","input_price_per_million":10.0,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:11.588754","max_output_tokens":128000,"metadata":{"attachment":true,"family":"claude-fable","knowledge":"2026-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"temperature":false,"tool_call":true},"modalities":"Image, Pdf, Text","name":"Claude Fable 5.1","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://docs.nano-gpt.com","output":128000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"anthropic/claude-fable-5.1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.vivgrid.com/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":12.5,"input":10,"output":50},"doc":"https://docs.vivgrid.com/models","output":128000,"provider":"Vivgrid","provider_id":"vivgrid","provider_model_id":"claude-fable-5-1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://llmgateway.io/docs","output":128000,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"anthropic/claude-fable-5-1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure Cognitive Services","provider_id":"azure-cognitive-services","provider_model_id":"claude-fable-5-1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","output":128000,"provider":"Vertex","provider_id":"google-vertex","provider_model_id":"claude-fable-5-1@default","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://requesty.ai/solution/llm-routing/models","output":128000,"provider":"Requesty","provider_id":"requesty","provider_model_id":"claude-fable-5.1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://www.crossmodel.ai/docs","output":128000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"anthropic/claude-fable-5-1","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://docs.anthropic.com/en/docs/about-claude/models","output":128000,"provider":"Anthropic","provider_id":"anthropic","provider_model_id":"claude-fable-5-1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"anthropic/claude-fable-5.1","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.3,"cache_write":15,"input":12,"output":60},"doc":"https://docs.venice.ai","output":128000,"provider":"Venice AI","provider_id":"venice","provider_model_id":"claude-fable-5-1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://llmgateway.io/docs","output":128000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"claude-fable-5-1","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://developers.cloudflare.com/ai-gateway/","output":128000,"provider":"Cloudflare AI Gateway","provider_id":"cloudflare-ai-gateway","provider_model_id":"anthropic/claude-fable-5.1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://docs.github.com/en/copilot","output":128000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"claude-fable-5.1","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"anthropic/claude-fable-5.1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure","provider_id":"azure","provider_model_id":"claude-fable-5-1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","output":128000,"provider":"Amazon Bedrock","provider_id":"amazon-bedrock","provider_model_id":"anthropic.claude-fable-5-1","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://docs.merge.dev/merge-gateway","output":128000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"anthropic/claude-fable-5-1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://opencode.ai/docs/zen","output":128000,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"claude-fable-5-1","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://openrouter.ai/models","output":128000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"anthropic/claude-fable-5.1","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://ofox.ai/docs","output":128000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"anthropic/claude-fable-5.1","reasoning":true,"structured_output":null,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://neon.com/docs","output":128000,"provider":"Neon","provider_id":"neon","provider_model_id":"claude-fable-5-1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://api.302.ai/v1","context":1000000,"cost":{"input":10,"output":50},"doc":"https://doc.302.ai","output":128000,"provider":"302.AI","provider_id":"302ai","provider_model_id":"claude-fable-5-1","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude","output":128000,"provider":"Vertex (Anthropic)","provider_id":"google-vertex-anthropic","provider_model_id":"claude-fable-5-1@default","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1000000,"cost":{"cache_read":0.25,"cache_write":12.5,"input":10,"output":50},"doc":"https://docs.edenai.co","output":128000,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"anthropic/claude-fable-5-1","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":50.0,"release_date":"2026-09-01","slug":"anthropic/claude-fable-5-1","source":"Models.dev","source_url":"https://models.dev/models/anthropic/claude-fable-5-1/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.034,"coding_score":0.0,"confidence":"Medium","context_length":1024000,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","developer":"Tencent","input_price_per_million":0.67,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:18.368034","max_output_tokens":64000,"metadata":{"attachment":false,"family":"Hy","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"temperature":true,"tool_call":true},"modalities":"Text","name":"Hy4 preview","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.042,"input":0.834,"output":2.501},"doc":"https://docs.nano-gpt.com","output":64000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"tencent/hy4-preview","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1048576,"cost":{"cache_read":0.048,"cache_write":0.96,"input":0.96,"output":2.88},"doc":"https://www.crossmodel.ai/docs","output":65536,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"tencent/hy4-preview","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1024000,"cost":{"cache_read":0.042,"input":0.834,"output":2.501},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":64000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"tencent/hy4-preview","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.042,"input":0.834,"output":2.501},"doc":"https://kilo.ai","output":64000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"tencent/hy4-preview","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.042,"input":0.834,"output":2.501},"doc":"https://openrouter.ai/models","output":64000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"tencent/hy4-preview","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://tokenhub.tencentmaas.com/v1","context":1024000,"cost":{"cache_read":0.042,"input":0.834,"output":2.501},"doc":"https://cloud.tencent.com/document/product/1823/130050","output":64000,"provider":"Tencent TokenHub","provider_id":"tencent-tokenhub","provider_model_id":"hy4-preview","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://vancine.com/v1","context":1024000,"cost":{"cache_read":0.034,"input":0.67,"output":2},"doc":"https://vancine.com/docs","output":64000,"provider":"Vancine","provider_id":"vancine","provider_model_id":"hy4-preview","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":1024000,"cost":{"cache_read":0.042,"input":0.834,"output":2.501},"doc":"https://opencode.ai/docs/zen","output":64000,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"hy4-preview","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.lkeap.cloud.tencent.com/plan/v3","context":1024000,"cost":{"cache_read":0.042,"input":0.834,"output":2.501},"doc":"https://cloud.tencent.com/document/product/1823/130060","output":64000,"provider":"Tencent Token Plan","provider_id":"tencent-token-plan","provider_model_id":"hy4-preview","reasoning":true,"structured_output":null,"tool_call":true}],"open_weights":true,"output_price_per_million":2.0,"release_date":"2026-08-28","slug":"tencent/hy4-preview","source":"Models.dev","source_url":"https://models.dev/models/tencent/hy4-preview/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.01,"coding_score":0.0,"confidence":"Medium","context_length":262144,"description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","developer":"Alibaba Qwen","input_price_per_million":0.12,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:09.757251","max_output_tokens":131072,"metadata":{"attachment":true,"family":"qwen","license":"qwen-community-1.0","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next"}]},"modalities":"Image, Text, Video","name":"Qwen3.8 Flash Next","offerings":[{"api":"https://router.requesty.ai/v1","context":262144,"cost":{"cache_read":0.05,"input":0.2,"output":0.5},"doc":"https://requesty.ai/solution/llm-routing/models","output":262144,"provider":"Requesty","provider_id":"requesty","provider_model_id":"qwen3.8-flash-next","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.01,"input":0.12,"output":0.4},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":1048576,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"alibaba/qwen3.8-flash-next","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://developer.amd.com.cn/radeon/api/v1","context":262144,"cost":{"cache_read":0.016,"input":0.15,"output":0.47},"doc":"https://developer.amd.com.cn/radeon/tokenfactory","output":131072,"provider":"AMD","provider_id":"amd","provider_model_id":"Qwen3.8-Flash-Next","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":262144,"cost":{"cache_read":0.05,"input":0.201,"output":0.5},"doc":"https://api.cortecs.ai/v1/models","output":64000,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"qwen3.8-flash-next","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":0.4,"release_date":"2026-08-27","slug":"alibaba/qwen3.8-flash-next","source":"Models.dev","source_url":"https://models.dev/models/alibaba/qwen3.8-flash-next/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.012,"coding_score":0.0,"confidence":"Medium","context_length":262144,"description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","developer":"Inclusionai","input_price_per_million":0.06,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:15.418313","max_output_tokens":32768,"metadata":{"attachment":false,"family":"ling","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"reasoning":true,"tool_call":true},"modalities":"Text","name":"Ling 3.0 Flash Fin","offerings":[{"api":"","context":256000,"cost":{"input":0,"output":0},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":32000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"inclusionai/ling-3.0-flash-fin","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":262144,"cost":{"cache_read":0.012,"input":0.06,"output":0.18},"doc":"https://kilo.ai","output":235929,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"inclusionai/ling-3.0-flash-fin","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":262144,"cost":{"cache_read":0.012,"input":0.06,"output":0.18},"doc":"https://openrouter.ai/models","output":235929,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"inclusionai/ling-3.0-flash-fin","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":0.18,"release_date":"2026-08-27","slug":"inclusionai/ling-3.0-flash-fin","source":"Models.dev","source_url":"https://models.dev/models/inclusionai/ling-3.0-flash-fin/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.016,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","developer":"Alibaba Qwen","input_price_per_million":0.15,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:10.717163","max_output_tokens":131072,"metadata":{"attachment":true,"family":"qwen","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"tool_call":true},"modalities":"Image, Text, Video","name":"Qwen3.8 Flash","offerings":[{"api":"https://nano-gpt.com/api/v1","context":991808,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.14,"output":0.42},"doc":"https://docs.nano-gpt.com","output":131072,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"alibaba/qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1000000,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.15,"output":0.47},"doc":"https://llmgateway.io/docs","output":131072,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"alibaba/qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/en/model-studio/token-plan-overview","output":131072,"provider":"Alibaba Token Plan","provider_id":"alibaba-token-plan","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://dashscope.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0.01187,"cache_write":0.14844,"input":0.11875,"output":0.40073},"doc":"https://www.alibabacloud.com/help/en/model-studio/models","output":131072,"provider":"Alibaba (China)","provider_id":"alibaba-cn","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1000000,"cost":{"cache_read":0.016,"input":0.15,"output":0.47},"doc":"https://hyper.charm.land","output":128000,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.16,"output":0.47},"doc":"https://requesty.ai/solution/llm-routing/models","output":131072,"provider":"Requesty","provider_id":"requesty","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1000000,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.13,"output":0.43},"doc":"https://www.crossmodel.ai/docs","output":131072,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"qwen/qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.15,"output":0.47},"doc":"https://www.alibabacloud.com/help/en/model-studio/models","output":131072,"provider":"Alibaba","provider_id":"alibaba","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":991000,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.16,"output":0.47},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"alibaba/qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1000000,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.15,"output":0.47},"doc":"https://llmgateway.io/docs","output":131072,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":1000000,"cost":{"cache_read":0.16,"input":0.16,"output":0.47},"doc":"https://docs.empiriolabs.ai","output":131072,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"qwen3-8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1000000,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.15,"output":0.47},"doc":"https://kilo.ai","output":131072,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"qwen/qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1000000,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.15,"output":0.47},"doc":"https://openrouter.ai/models","output":131072,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"qwen/qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.011,"cache_write":0.14,"input":0.11,"output":0.39},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"qwen/qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.scnet.cn/api/llm/v1","context":1000000,"cost":{"cache_read":0,"input":0,"output":0},"doc":"https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html","output":131072,"provider":"SCNet Token Plan","provider_id":"scnet-token-plan","provider_model_id":"Qwen3.8-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1000000,"cost":{"input":0.18,"output":0.564},"doc":"https://doc.302.ai","output":131072,"provider":"302.AI","provider_id":"302ai","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://vancine.com/v1","context":1000000,"cost":{"cache_read":0.013,"input":0.12,"output":0.38},"doc":"https://vancine.com/docs","output":131072,"provider":"Vancine","provider_id":"vancine","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.nan.builders/v1","context":262144,"cost":{"input":0,"output":0},"doc":"https://nan.builders/docs/models","output":131072,"provider":"NaN","provider_id":"nan","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview","output":131072,"provider":"Alibaba Token Plan (China)","provider_id":"alibaba-token-plan-cn","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":1000000,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.15,"output":0.47},"doc":"https://opencode.ai/docs/zen","output":131072,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1000000,"cost":{"cache_read":0.016,"cache_write":0.2,"input":0.15,"output":0.47},"doc":"https://docs.edenai.co","output":131072,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"qwen/qwen3.8-flash","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":0.47,"release_date":"2026-08-26","slug":"alibaba/qwen3.8-flash","source":"Models.dev","source_url":"https://models.dev/models/alibaba/qwen3.8-flash/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.015,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","developer":"Zhipu AI","input_price_per_million":0.075,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:14.234085","max_output_tokens":131072,"metadata":{"attachment":true,"family":"glm","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Image, Pdf, Text, Video","name":"GLM-5.3-Flash","offerings":[{"api":"https://api.tokengo.com/v1","context":1000000,"cost":{"cache_read":0.015,"input":0.075,"output":0.025},"doc":"https://www.tokengo.com/docs","output":131072,"provider":"TokenGo","provider_id":"tokengo","provider_model_id":"z-ai/glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openai.bothub.ru/v1","context":1000000,"cost":{"input":0.12,"output":0.44},"doc":"https://bothub.ru/models","output":131072,"provider":"Bothub","provider_id":"bothub","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.greenpt.ai/v1","context":1000000,"cost":{"cache_read":0.0255508,"input":0.127754,"output":0.511016},"doc":"https://docs.greenpt.ai","output":131072,"provider":"GreenPT","provider_id":"greenpt","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.vivgrid.com/v1","context":1000000,"cost":{"cache_read":0.04,"input":0.15,"output":0.5},"doc":"https://docs.vivgrid.com/models","output":131072,"provider":"Vivgrid","provider_id":"vivgrid","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://ollama.com/v1","context":1000000,"cost":{},"doc":"https://docs.ollama.com/cloud","output":131072,"provider":"Ollama Cloud","provider_id":"ollama-cloud","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.02817,"input":0.11268,"output":0.39438},"doc":"https://docs.aihubmix.com","output":128000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.z.ai/api/coding/paas/v4","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://docs.z.ai/devpack/overview","output":131072,"provider":"Z.AI Coding Plan","provider_id":"zai-coding-plan","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1000000,"cost":{"input":0.075,"output":0.25},"doc":"https://docs.orcarouter.ai","output":128000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"z-ai/glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":1000000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":131072,"provider":"Kenari","provider_id":"kenari","provider_model_id":"glm-5-3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.tokenfactory.nebius.com/v1","context":1024000,"cost":{"cache_read":0.15,"input":0.15,"output":0.5},"doc":"https://docs.tokenfactory.nebius.com/","output":1024000,"provider":"Nebius Token Factory","provider_id":"nebius","provider_model_id":"zai-org/GLM-5.3-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1048576,"cost":{"cache_read":0.031575,"input":0.16332,"output":0.5444},"doc":"https://hyper.charm.land","output":131072,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1000000,"cost":{"cache_read":0.07,"input":0.2,"output":0.6},"doc":"https://requesty.ai/solution/llm-routing/models","output":262144,"provider":"Requesty","provider_id":"requesty","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":1048576,"cost":{"input":0.15,"output":0.5},"doc":"https://huggingface.co/docs/inference-providers","output":131072,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"zai-org/GLM-5.3-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://open.bigmodel.cn/api/coding/paas/v4","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://docs.bigmodel.cn/cn/coding-plan/overview","output":131072,"provider":"Zhipu AI Coding Plan","provider_id":"zhipuai-coding-plan","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1000000,"cost":{"cache_read":0.03,"cache_write":0.15,"input":0.15,"output":0.5},"doc":"https://www.crossmodel.ai/docs","output":128000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"z-ai/glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.025,"input":0.088,"output":0.25},"doc":"https://llmgateway.io/docs","output":131072,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://open.bigmodel.cn/api/paas/v4","context":1000000,"cost":{"cache_read":0.015,"cache_write":0,"input":0.075,"output":0.25},"doc":"https://docs.z.ai/guides/overview/pricing","output":131072,"provider":"Zhipu AI","provider_id":"zhipuai","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.03,"input":0.15,"output":0.5},"doc":"https://deepinfra.com/models","output":131072,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"zai-org/GLM-5.3-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.03,"input":0.15,"output":0.5},"doc":"https://kilo.ai","output":131072,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"z-ai/glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1000000,"cost":{"cache_read":0.03,"input":0.15,"output":0.5},"doc":"https://opencode.ai/docs/zen","output":131072,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1310720,"cost":{"cache_read":0.03,"input":0.15,"output":0.5},"doc":"https://openrouter.ai/models","output":131072,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"z-ai/glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.03,"input":0.15,"output":0.5},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"z-ai/glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.scnet.cn/api/llm/v1","context":1000000,"cost":{"cache_read":0,"input":0,"output":0},"doc":"https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html","output":131072,"provider":"SCNet Token Plan","provider_id":"scnet-token-plan","provider_model_id":"GLM-5.3-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1000000,"cost":{"input":0.075,"output":0.25},"doc":"https://doc.302.ai","output":131072,"provider":"302.AI","provider_id":"302ai","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.z.ai/api/paas/v4","context":1000000,"cost":{"cache_read":0.015,"cache_write":0,"input":0.075,"output":0.25},"doc":"https://docs.z.ai/guides/overview/pricing","output":131072,"provider":"Z.AI","provider_id":"zai","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.runinfra.ai/v1","context":1048576,"cost":{"cache_read":0.01,"input":0.1,"output":0.4},"doc":"https://runinfra.ai/docs","output":32768,"provider":"RunInfra","provider_id":"runinfra","provider_model_id":"zai-org/GLM-5.3-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.berget.ai/v1","context":524288,"cost":{"input":0.29,"output":0.58},"doc":"https://api.berget.ai","output":16384,"provider":"Berget.AI","provider_id":"berget","provider_model_id":"zai-org/GLM-5.3-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.synthetic.new/openai/v1","context":524288,"cost":{"cache_read":0.04,"input":0.15,"output":0.5},"doc":"https://synthetic.new/pricing","output":65536,"provider":"Synthetic","provider_id":"synthetic","provider_model_id":"hf:zai-org/GLM-5.3-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048575,"cost":{"cache_read":0.03,"input":0.15,"output":0.5},"doc":"https://docs.together.ai/docs/serverless-models","output":400000,"provider":"Together AI","provider_id":"togetherai","provider_model_id":"zai-org/GLM-5.3-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://vancine.com/v1","context":1000000,"cost":{"cache_read":0.012,"input":0.06,"output":0.2},"doc":"https://vancine.com/docs","output":131072,"provider":"Vancine","provider_id":"vancine","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1048576,"cost":{"cache_read":0.05,"input":0.201,"output":0.5},"doc":"https://api.cortecs.ai/v1/models","output":1048576,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.nan.builders/v1","context":1000000,"cost":{"input":0,"output":0},"doc":"https://nan.builders/docs/models","output":131072,"provider":"NaN","provider_id":"nan","provider_model_id":"glm5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":1000000,"cost":{"cache_read":0.03,"input":0.15,"output":0.5},"doc":"https://opencode.ai/docs/zen","output":131072,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.tinfoil.sh/v1","context":1048576,"cost":{"cache_read":0.1,"input":0.4,"output":1.25},"doc":"https://docs.tinfoil.sh","output":131072,"provider":"Tinfoil","provider_id":"tinfoil","provider_model_id":"glm-5-3-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1048576,"cost":{"cache_read":0.03,"input":0.15,"output":0.5},"doc":"https://docs.edenai.co","output":131072,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"zai/glm-5.3-flash","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":0.25,"release_date":"2026-08-26","slug":"zhipuai/glm-5.3-flash","source":"Models.dev","source_url":"https://models.dev/models/zhipuai/glm-5.3-flash/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":null,"coding_score":0.0,"confidence":"Medium","context_length":0,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","developer":"Google","input_price_per_million":null,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:12.422711","max_output_tokens":0,"metadata":{"attachment":false,"family":"gemini","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"reasoning":false,"tool_call":false},"modalities":"Audio, Text","name":"Gemini 3.5 Transcribe Live","offerings":[{"api":"","context":0,"cost":{},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":0,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"google/gemini-3.5-transcribe-live","reasoning":false,"structured_output":null,"tool_call":false}],"open_weights":false,"output_price_per_million":null,"release_date":"2026-08-26","slug":"google/gemini-3.5-transcribe-live","source":"Models.dev","source_url":"https://models.dev/models/google/gemini-3.5-transcribe-live/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.003,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","developer":"DeepSeek","input_price_per_million":0.15,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:14.837674","max_output_tokens":384000,"metadata":{"attachment":true,"family":"deepseek-flash","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Image, Text","name":"DeepSeek V4 Flash Vision Exp","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://docs.nano-gpt.com","output":384000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"deepseek/deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1000000,"cost":{"cache_read":0.02,"input":0.147,"output":0.295},"doc":"https://docs.orcarouter.ai","output":384000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"deepseek/deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":1048576,"cost":{"input":0.44,"output":1.32},"doc":"https://huggingface.co/docs/inference-providers","output":384000,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1000000,"cost":{"cache_read":0.0054,"cache_write":0.27,"input":0.27,"output":1.08},"doc":"https://www.crossmodel.ai/docs","output":384000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"deepseek/deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":1048576,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"deepseek/deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":1000000,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://fireworks.ai/docs/","output":384000,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://crof.ai/v1","context":1000000,"cost":{"cache_read":0.007,"input":0.08,"output":0.2},"doc":"https://crof.ai/docs","output":131072,"provider":"CrofAI","provider_id":"crof","provider_model_id":"deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.014,"input":0.44,"output":1.32},"doc":"https://deepinfra.com/models","output":384000,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.028,"input":0.44,"output":1.32},"doc":"https://kilo.ai","output":943718,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"deepseek/deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.deepseek.com","context":1000000,"cost":{"cache_read":0.003,"input":0.15,"output":0.6,"reasoning":0.6},"doc":"https://api-docs.deepseek.com/quick_start/pricing","output":384000,"provider":"DeepSeek","provider_id":"deepseek","provider_model_id":"deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1000000,"cost":{"cache_read":0.028,"input":0.14,"output":0.28},"doc":"https://opencode.ai/docs/zen","output":384000,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://openrouter.ai/models","output":943718,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"deepseek/deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.014,"input":0.44,"output":1.32},"doc":"https://ofox.ai/docs","output":384000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"deepseek/deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://developer.amd.com.cn/radeon/api/v1","context":1000000,"cost":{"cache_read":0.0028,"input":0.14,"output":0.28},"doc":"https://developer.amd.com.cn/radeon/tokenfactory","output":384000,"provider":"AMD","provider_id":"amd","provider_model_id":"DeepSeek-V4-Flash-Vision-Exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://vancine.com/v1","context":1000000,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://vancine.com/docs","output":384000,"provider":"Vancine","provider_id":"vancine","provider_model_id":"deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":1000000,"cost":{"cache_read":0.003,"input":0.15,"output":0.6},"doc":"https://opencode.ai/docs/zen","output":384000,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1048576,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://docs.edenai.co","output":384000,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"deepseek/deepseek-v4-flash-vision-exp","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":0.6,"release_date":"2026-08-21","slug":"deepseek/deepseek-v4-flash-vision-exp","source":"Models.dev","source_url":"https://models.dev/models/deepseek/deepseek-v4-flash-vision-exp/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.01,"coding_score":0.0,"confidence":"Medium","context_length":262144,"description":"Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding","developer":"Deepreinforce","input_price_per_million":0.1,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:09.101017","max_output_tokens":0,"metadata":{"attachment":true,"family":"ornith","license":"MIT","links":[{"label":"Model card","type":"model_card","url":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B"}],"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B"}]},"modalities":"Image, Text","name":"Ornith 1.5 35B A3B","offerings":[{"api":"https://api.iteracompute.com/v1","context":327680,"cost":{"input":0.3,"output":3},"doc":"https://iteracompute.com/docs.html","output":65536,"provider":"IteraCompute","provider_id":"iteracompute","provider_model_id":"iteracompute/ornith-1.5-35b-a3b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.runinfra.ai/v1","context":262144,"cost":{"cache_read":0.01,"input":0.1,"output":0.4},"doc":"https://runinfra.ai/docs","output":32768,"provider":"RunInfra","provider_id":"runinfra","provider_model_id":"ornith-ai/Ornith-1.5-35B-A3B","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":0.4,"release_date":"2026-08-18","slug":"deepreinforce/ornith-1.5-35b-a3b","source":"Models.dev","source_url":"https://models.dev/models/deepreinforce/ornith-1.5-35b-a3b/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[{"metric":"resolved","name":"SWE-bench Pro","score":61.7,"source":"https://huggingface.co/Qwen/Qwen3.8-27B"}],"cached_input_price_per_million":0.01,"coding_score":0.0,"confidence":"Medium","context_length":262144,"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","developer":"Alibaba Qwen","input_price_per_million":0.1,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:10.167880","max_output_tokens":32768,"metadata":{"attachment":true,"family":"qwen","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/Qwen/Qwen3.8-27B"}]},"modalities":"Image, Text, Video","name":"Qwen3.8 27B","offerings":[{"api":"https://nano-gpt.com/api/v1","context":262144,"cost":{"cache_read":0.04,"input":0.15,"output":0.7},"doc":"https://docs.nano-gpt.com","output":32768,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.neuralwatt.com/v1","context":262128,"cost":{"cache_read":0.25,"input":0.45,"output":3.2},"doc":"https://portal.neuralwatt.com/docs","output":65536,"provider":"Neuralwatt","provider_id":"neuralwatt","provider_model_id":"qwen-3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":131042,"cost":{"input":0.8,"output":4},"doc":"https://console.groq.com/docs/models","output":16384,"provider":"Groq","provider_id":"groq","provider_model_id":"qwen/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":262144,"cost":{"input":0.33,"output":2.4},"doc":"https://docs.orcarouter.ai","output":32768,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"qwen/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmtech.eu/v1","context":262144,"cost":{"cache_read":0.04,"input":0.25,"output":2.09},"doc":"https://llmtech.eu/models/qwen3.8-27b","output":32768,"provider":"LLM Tech","provider_id":"llmtech","provider_model_id":"unsloth/Qwen3.8-27B-NVFP4","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.regolo.ai/v1","context":120000,"cost":{"input":0.58,"output":2.42},"doc":"https://docs.regolo.ai/","output":120000,"provider":"Regolo AI","provider_id":"regolo-ai","provider_model_id":"qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1000000,"cost":{"cache_read":0.1,"input":0.5,"output":3},"doc":"https://hyper.charm.land","output":128000,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":262144,"cost":{"input":0.4,"output":3},"doc":"https://huggingface.co/docs/inference-providers","output":32768,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"Qwen/Qwen3.8-27B","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://aki.io/v1","context":262144,"cost":{"cache_read":0.1,"input":0.3,"output":2.2},"doc":"https://aki.io/docs/","output":32768,"provider":"AKI.IO","provider_id":"aki-io","provider_model_id":"qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.1,"cache_write":0.625,"input":0.5,"output":3},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":131072,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"alibaba/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.inference.wandb.ai/v1","context":262144,"cost":{"cache_read":0.15,"input":0.4,"output":3},"doc":"https://docs.wandb.ai/guides/integrations/inference/","output":262144,"provider":"Weights & Biases","provider_id":"wandb","provider_model_id":"Qwen/Qwen3.8-27B","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://crof.ai/v1","context":262144,"cost":{"cache_read":0.03,"input":0.2,"output":1.5},"doc":"https://crof.ai/docs","output":262144,"provider":"CrofAI","provider_id":"crof","provider_model_id":"qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":262144,"cost":{"cache_read":0.08,"input":0.17,"output":0.5},"doc":"https://docs.empiriolabs.ai","output":32768,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"qwen3-8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":262144,"cost":{"cache_read":0.04,"input":0.4,"output":3},"doc":"https://deepinfra.com/models","output":32768,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"Qwen/Qwen3.8-27B","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1000000,"cost":{"cache_read":0.085,"cache_write":0.53125,"input":0.425,"output":2.55},"doc":"https://kilo.ai","output":131072,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"qwen/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.koscompute.com/v1","context":262144,"cost":{"cache_read":0.09,"input":0.35,"output":2.2},"doc":"https://api.koscompute.com/docs/","output":32768,"provider":"Kosmik Compute","provider_id":"kosmik","provider_model_id":"qwen/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1000000,"cost":{"cache_read":0.085,"input":0.42,"output":3},"doc":"https://openrouter.ai/models","output":131072,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"qwen/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.iteracompute.com/v1","context":327680,"cost":{"input":0.3,"output":2.5},"doc":"https://iteracompute.com/docs.html","output":65536,"provider":"IteraCompute","provider_id":"iteracompute","provider_model_id":"iteracompute/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1131072,"cost":{"cache_read":0.043,"cache_write":0.63,"input":0.5,"output":1.71},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"qwen/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1131072,"cost":{"cache_read":0.05,"cache_write":0.5625,"input":0.45,"output":3.2},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"bailian/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.aiand.com/v1","context":262144,"cost":{"cache_read":0.2,"input":0.4,"output":3},"doc":"https://docs.aiand.com/","output":32768,"provider":"ai&","provider_id":"aiand","provider_model_id":"qwen/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.runinfra.ai/v1","context":262144,"cost":{"cache_read":0.01,"input":0.1,"output":0.4},"doc":"https://runinfra.ai/docs","output":32768,"provider":"RunInfra","provider_id":"runinfra","provider_model_id":"Qwen/Qwen3.8-27B","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.berget.ai/v1","context":262144,"cost":{"input":0.46,"output":3.48},"doc":"https://api.berget.ai","output":65536,"provider":"Berget.AI","provider_id":"berget","provider_model_id":"Qwen/Qwen3.8-27B-FP8","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":65536,"cost":{"input":0.99,"output":1.49},"doc":"https://inference-docs.cerebras.ai/models/overview","output":32768,"provider":"Cerebras","provider_id":"cerebras","provider_model_id":"qwen-3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1","context":262144,"cost":{"cache_read":0.05,"input":0.45,"output":3.2},"doc":"https://developers.cloudflare.com/workers-ai/models/","output":262144,"provider":"Cloudflare Workers AI","provider_id":"cloudflare-workers-ai","provider_model_id":"@cf/qwen/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":262144,"cost":{"cache_read":0.111,"input":0.334,"output":2.451},"doc":"https://api.cortecs.ai/v1/models","output":262144,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1000000,"cost":{"cache_read":0.1,"cache_write":0.625,"input":0.5,"output":3},"doc":"https://docs.edenai.co","output":32768,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"qwen/qwen3.8-27b","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":0.4,"release_date":"2026-08-14","slug":"alibaba/qwen3.8-27b","source":"Models.dev","source_url":"https://models.dev/models/alibaba/qwen3.8-27b/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.26,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","developer":"Zhipu AI","input_price_per_million":1.4,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:14.549774","max_output_tokens":131072,"metadata":{"attachment":false,"family":"glm","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Text","name":"GLM-5.3","offerings":[{"api":"https://api.tokengo.com/v1","context":1000000,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://www.tokengo.com/docs","output":131072,"provider":"TokenGo","provider_id":"tokengo","provider_model_id":"z-ai/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openai.bothub.ru/v1","context":1000000,"cost":{"input":1.72,"output":5.41},"doc":"https://bothub.ru/models","output":131072,"provider":"Bothub","provider_id":"bothub","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.greenpt.ai/v1","context":1000000,"cost":{"cache_read":0.319385,"input":1.27754,"output":5.11016},"doc":"https://docs.greenpt.ai","output":131072,"provider":"GreenPT","provider_id":"greenpt","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.vivgrid.com/v1","context":1000000,"cost":{"cache_read":0.26,"input":1.2,"output":4.2},"doc":"https://docs.vivgrid.com/models","output":131072,"provider":"Vivgrid","provider_id":"vivgrid","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://ollama.com/v1","context":1048576,"cost":{},"doc":"https://docs.ollama.com/cloud","output":131072,"provider":"Ollama Cloud","provider_id":"ollama-cloud","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.2817,"input":1.1268,"output":3.9438},"doc":"https://docs.aihubmix.com","output":128000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.z.ai/api/coding/paas/v4","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://docs.z.ai/devpack/overview","output":131072,"provider":"Z.AI Coding Plan","provider_id":"zai-coding-plan","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1000000,"cost":{"cache_read":0.234,"input":1.26,"output":3.96},"doc":"https://docs.orcarouter.ai","output":131072,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"z-ai/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":1000000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":131072,"provider":"Kenari","provider_id":"kenari","provider_model_id":"glm-5-3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1048576,"cost":{"cache_read":0.283088,"input":1.52432,"output":4.79072},"doc":"https://hyper.charm.land","output":262144,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.26,"input":1.2,"output":4.2},"doc":"https://requesty.ai/solution/llm-routing/models","output":1048576,"provider":"Requesty","provider_id":"requesty","provider_model_id":"glm-5.3","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":1048576,"cost":{"input":1.4,"output":4.4},"doc":"https://huggingface.co/docs/inference-providers","output":131072,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"zai-org/GLM-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://open.bigmodel.cn/api/coding/paas/v4","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://docs.bigmodel.cn/cn/coding-plan/overview","output":131072,"provider":"Zhipu AI Coding Plan","provider_id":"zhipuai-coding-plan","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1000000,"cost":{"cache_read":0.3,"cache_write":1.2,"input":1.2,"output":4.4},"doc":"https://www.crossmodel.ai/docs","output":128000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"z-ai/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.friendli.ai/serverless/v1","context":1048576,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","output":1048576,"provider":"Friendli","provider_id":"friendli","provider_model_id":"zai-org/GLM-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.2,"input":1.2,"output":4},"doc":"https://llmgateway.io/docs","output":131072,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://open.bigmodel.cn/api/paas/v4","context":1000000,"cost":{"cache_read":0.26,"cache_write":0,"input":1.4,"output":4.4},"doc":"https://docs.z.ai/guides/overview/pricing","output":131072,"provider":"Zhipu AI","provider_id":"zhipuai","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://crof.ai/v1","context":1000000,"cost":{"cache_read":0.06,"input":0.4,"output":1.4},"doc":"https://crof.ai/docs","output":131072,"provider":"CrofAI","provider_id":"crof","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"http://localhost:8080/v1","context":256000,"cost":{"cache_read":0.1733,"input":1.791,"output":8.9436},"doc":"https://docs.privatemode.ai/api/overview","output":131072,"provider":"Privatemode AI","provider_id":"privatemode-ai","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.12,"input":1.2,"output":4},"doc":"https://deepinfra.com/models","output":131072,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"zai-org/GLM-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://kilo.ai","output":943718,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"z-ai/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1000000,"cost":{"cache_read":0.13,"input":0.7,"output":2.2},"doc":"https://docs.merge.dev/merge-gateway","output":131072,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"zai/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1000000,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://opencode.ai/docs/zen","output":131072,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1310720,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://openrouter.ai/models","output":943718,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"z-ai/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cline.bot/api/v1","context":1000000,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://docs.cline.bot/getting-started/clinepass","output":131072,"provider":"ClinePass","provider_id":"cline-pass","provider_model_id":"cline-pass/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"z-ai/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.scnet.cn/api/llm/v1","context":1000000,"cost":{"cache_read":0,"input":0,"output":0},"doc":"https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html","output":131072,"provider":"SCNet Token Plan","provider_id":"scnet-token-plan","provider_model_id":"GLM-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.aiand.com/v1","context":1048576,"cost":{"cache_read":0.3,"input":1,"output":4},"doc":"https://docs.aiand.com/","output":131072,"provider":"ai&","provider_id":"aiand","provider_model_id":"zai-org/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://ark.cn-beijing.volces.com/api/coding/v3","context":1000000,"cost":{"cache_read":0,"input":0,"output":0},"doc":"https://www.volcengine.com/docs/82379/1928261","output":131072,"provider":"Volcengine Ark Coding Plan","provider_id":"volcengine-coding-plan","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1000000,"cost":{"input":1.4,"output":4.4},"doc":"https://doc.302.ai","output":131072,"provider":"302.AI","provider_id":"302ai","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.z.ai/api/paas/v4","context":1000000,"cost":{"cache_read":0.26,"cache_write":0,"input":1.4,"output":4.4},"doc":"https://docs.z.ai/guides/overview/pricing","output":131072,"provider":"Z.AI","provider_id":"zai","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://docs.together.ai/docs/serverless-models","output":262144,"provider":"Together AI","provider_id":"togetherai","provider_model_id":"zai-org/GLM-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://vancine.com/v1","context":1000000,"cost":{"cache_read":0.208,"input":1.12,"output":3.52},"doc":"https://vancine.com/docs","output":131072,"provider":"Vancine","provider_id":"vancine","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1048576,"cost":{"cache_read":0.279,"input":1.114,"output":3.899},"doc":"https://api.cortecs.ai/v1/models","output":1048576,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":1000000,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://opencode.ai/docs/zen","output":131072,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"glm-5.3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1048576,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"doc":"https://docs.edenai.co","output":131072,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"zai/glm-5.3","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":4.4,"release_date":"2026-08-14","slug":"zhipuai/glm-5.3","source":"Models.dev","source_url":"https://models.dev/models/zhipuai/glm-5.3/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.075,"coding_score":0.0,"confidence":"Medium","context_length":1048576,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","developer":"Google","input_price_per_million":0.75,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:13.352657","max_output_tokens":65536,"metadata":{"attachment":true,"family":"gemini-flash","knowledge":"2026-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Audio, Image, Pdf, Text, Video","name":"Gemini Flash Latest","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.075,"input":0.75,"output":3.75},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"google/gemini-flash-latest","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1048576,"cost":{"cache_read":0.1,"input":0.5,"output":3},"doc":"https://docs.orcarouter.ai","output":65536,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"google/gemini-flash-latest","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":9},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","output":65536,"provider":"Vertex","provider_id":"google-vertex","provider_model_id":"gemini-flash-latest","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"input_audio":0.75,"output":3.75},"doc":"https://ai.google.dev/gemini-api/docs/models","output":65536,"provider":"Google","provider_id":"google","provider_model_id":"gemini-flash-latest","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":9},"doc":"https://docs.merge.dev/merge-gateway","output":65536,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"google/gemini-flash-latest","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"doc":"https://docs.edenai.co","output":65536,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"google/gemini-flash-latest","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":3.75,"release_date":"2026-08-13","slug":"google/gemini-flash-latest","source":"Models.dev","source_url":"https://models.dev/models/google/gemini-flash-latest/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":36.4,"benchmark_data":[{"date":"2026-08-13","metric":"score","name":"FrontierCode","score":43.6,"source":"https://deepmind.google/models/model-cards/gemini-3-7-flash/","version":"1.1 Main"},{"date":"2026-08-13","metric":"resolve rate","name":"DeepSWE","score":65.3,"source":"https://deepmind.google/models/model-cards/gemini-3-7-flash/","version":"1.1"},{"date":"2026-08-13","metric":"accuracy","name":"Terminal-Bench","score":85.8,"source":"https://deepmind.google/models/model-cards/gemini-3-7-flash/","version":"2.1"},{"dataset":"private set","date":"2026-08-13","metric":"accuracy","name":"AutomationBench","score":30.4,"source":"https://deepmind.google/models/model-cards/gemini-3-7-flash/"},{"date":"2026-08-13","metric":"accuracy","name":"GDP.pdf","score":34,"source":"https://deepmind.google/models/model-cards/gemini-3-7-flash/"},{"date":"2026-08-13","metric":"accuracy","name":"GDM-MRCR","score":97,"source":"https://deepmind.google/models/model-cards/gemini-3-7-flash/","variant":"128k average, 8-needle","version":"v2"}],"cached_input_price_per_million":0.075,"coding_score":76.1,"confidence":"Medium","context_length":1048576,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","developer":"Google","input_price_per_million":0.75,"intelligence_score":39.4,"last_verified":"2026-09-11T13:08:13.242203","max_output_tokens":65536,"metadata":{"attachment":true,"family":"gemini-flash","knowledge":"2026-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Audio, Image, Pdf, Text, Video","name":"Gemini 3.7 Flash","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"output":3.75},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"google/gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.vivgrid.com/v1","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://docs.vivgrid.com/models","output":65536,"provider":"Vivgrid","provider_id":"vivgrid","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://docs.aihubmix.com","output":65536,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":1048576,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":65536,"provider":"Kenari","provider_id":"kenari","provider_model_id":"gemini-3-7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"input_audio":0.75,"output":3.75},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","output":65536,"provider":"Vertex","provider_id":"google-vertex","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://requesty.ai/solution/llm-routing/models","output":65535,"provider":"Requesty","provider_id":"requesty","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.75,"input":0.75,"output":3.75},"doc":"https://www.crossmodel.ai/docs","output":65536,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"gemini/gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"input_audio":0.75,"output":3.75},"doc":"https://ai.google.dev/gemini-api/docs/models","output":65536,"provider":"Google","provider_id":"google","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":65536,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"google/gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.09375,"input":0.9375,"output":4.6875},"doc":"https://docs.venice.ai","output":65536,"provider":"Venice AI","provider_id":"venice","provider_model_id":"gemini-3-7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.08333,"input":0.75,"output":3.75},"doc":"https://llmgateway.io/docs","output":65536,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1000000,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://docs.github.com/en/copilot","output":64000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://opper.ai/models","output":65536,"provider":"Opper","provider_id":"opper","provider_model_id":"vertexai/gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"output":3.75,"reasoning":3.75},"doc":"https://kilo.ai","output":65536,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"google/gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://docs.merge.dev/merge-gateway","output":65536,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"google/gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://abacus.ai/help/api","output":65536,"provider":"Abacus","provider_id":"abacus","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":7.5},"doc":"https://opencode.ai/docs/zen","output":65536,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"output":3.75,"reasoning":3.75},"doc":"https://openrouter.ai/models","output":65536,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"google/gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.0415,"input":0.75,"input_audio":1.5,"output":3.75},"doc":"https://ofox.ai/docs","output":65536,"provider":"Ofox","provider_id":"ofox","provider_model_id":"google/gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1048576,"cost":{"input":0.75,"output":3.75},"doc":"https://doc.302.ai","output":65536,"provider":"302.AI","provider_id":"302ai","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.038,"input":0.75,"output":3.75},"doc":"https://api.cortecs.ai/v1/models","output":65535,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"doc":"https://docs.edenai.co","output":65536,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"google/gemini-3.7-flash","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":3.75,"release_date":"2026-08-13","slug":"google/gemini-3.7-flash","source":"Models.dev","source_url":"https://models.dev/models/google/gemini-3.7-flash/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.5,"coding_score":0.0,"confidence":"Medium","context_length":262144,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","developer":"Alibaba Qwen","input_price_per_million":2.0,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:10.608680","max_output_tokens":131072,"metadata":{"attachment":false,"family":"qwen","license":"qwen3.8-max","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"}]},"modalities":"Text","name":"Qwen3.8 2.4T A95B","offerings":[{"api":"","context":262000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://docs.aihubmix.com","output":262000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"qwen3.8-2.4t-a95b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1000000,"cost":{"cache_read":0.25,"input":2,"output":6},"doc":"https://hyper.charm.land","output":128000,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"qwen3.8-2.4t-a95b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":262144,"cost":{"cache_read":0.2,"input":2,"output":6},"doc":"https://requesty.ai/solution/llm-routing/models","output":262144,"provider":"Requesty","provider_id":"requesty","provider_model_id":"qwen3.8-2.4T-A95B","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":262144,"cost":{"input":2.5,"output":6.25},"doc":"https://huggingface.co/docs/inference-providers","output":131072,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"Qwen/Qwen3.8-2.4T-A95B","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":262144,"cost":{"cache_read":0.25,"input":2,"output":6},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"alibaba/qwen3.8-2.4t-a95b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":262144,"cost":{"cache_read":0.25,"input":2,"output":6},"doc":"https://fireworks.ai/docs/","output":131072,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/qwen3p8-2p4t-a95b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":262144,"cost":{"cache_read":0.2,"input":2,"output":6},"doc":"https://deepinfra.com/models","output":131072,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"Qwen/Qwen3.8-2.4T-A95B","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://kilo.ai","output":131072,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"qwen/qwen3.8-2.4t-a95b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":262144,"cost":{"cache_read":0.5,"input":2.5,"output":6.25},"doc":"https://docs.merge.dev/merge-gateway","output":1010000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"qwen/qwen3.8-2.4t-a95b","reasoning":true,"structured_output":false,"tool_call":false},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.25,"input":2,"output":6},"doc":"https://openrouter.ai/models","output":131072,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"qwen/qwen3.8-2.4t-a95b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":262144,"cost":{"cache_read":0.625,"input":2.5,"output":6},"doc":"https://api.cortecs.ai/v1/models","output":262144,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"qwen3.8-2.4t-a95b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://docs.edenai.co","output":131072,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"qwen/qwen3.8-2.4t-a95b","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":6.0,"release_date":"2026-08-12","slug":"alibaba/qwen3.8-2.4t-a95b","source":"Models.dev","source_url":"https://models.dev/models/alibaba/qwen3.8-2.4t-a95b/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.5,"coding_score":0.0,"confidence":"Medium","context_length":500000,"description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","developer":"xAI","input_price_per_million":2.0,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:18.687665","max_output_tokens":500000,"metadata":{"attachment":true,"family":"grok","knowledge":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Image, Text","name":"Grok 4.6","offerings":[{"api":"https://nano-gpt.com/api/v1","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://docs.nano-gpt.com","output":450000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"x-ai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://docs.aihubmix.com","output":500000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://docs.orcarouter.ai","output":500000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"grok/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":500000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":500000,"provider":"Kenari","provider_id":"kenari","provider_model_id":"grok-4-6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":524288,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","output":500000,"provider":"Vertex","provider_id":"google-vertex","provider_model_id":"xai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":500000,"cost":{"cache_read":0.5,"cache_write":2,"context_over_200k":{"cache_read":1,"cache_write":4,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"cache_write":4,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://requesty.ai/solution/llm-routing/models","output":500000,"provider":"Requesty","provider_id":"requesty","provider_model_id":"grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":500000,"cost":{"cache_read":0.5,"cache_write":2,"context_over_200k":{"cache_read":1,"cache_write":4,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"cache_write":4,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://www.crossmodel.ai/docs","output":500000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"x-ai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":500000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"spacexai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.57,"context_over_200k":{"cache_read":1.13,"input":4.53,"output":13.6},"input":2.27,"output":6.8,"tiers":[{"cache_read":1.13,"input":4.53,"output":13.6,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.venice.ai","output":200000,"provider":"Venice AI","provider_id":"venice","provider_model_id":"grok-4-6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://llmgateway.io/docs","output":500000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"grok-4-6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://developers.cloudflare.com/ai-gateway/","output":500000,"provider":"Cloudflare AI Gateway","provider_id":"cloudflare-ai-gateway","provider_model_id":"xai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.github.com/en/copilot","output":128000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.perplexity.ai/v1","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.perplexity.ai/docs/agent-api/models","output":500000,"provider":"Perplexity Agent","provider_id":"perplexity-agent","provider_model_id":"xai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://opper.ai/models","output":500000,"provider":"Opper","provider_id":"opper","provider_model_id":"xai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://kilo.ai","output":450000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"x-ai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":200000,"cost":{},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure","provider_id":"azure","provider_model_id":"grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.55,"input":2.2,"output":6.6},"doc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","output":500000,"provider":"Amazon Bedrock","provider_id":"amazon-bedrock","provider_model_id":"xai.grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://docs.merge.dev/merge-gateway","output":500000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"xai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://abacus.ai/help/api","output":32768,"provider":"Abacus","provider_id":"abacus","provider_model_id":"grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://opencode.ai/docs/zen","output":500000,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://openrouter.ai/models","output":450000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"x-ai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://ofox.ai/docs","output":65536,"provider":"Ofox","provider_id":"ofox","provider_model_id":"x-ai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":500000,"cost":{},"doc":"https://neon.com/docs","output":524288,"provider":"Neon","provider_id":"neon","provider_model_id":"grok-4-6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":500000,"cost":{"input":2,"output":6},"doc":"https://doc.302.ai","output":500000,"provider":"302.AI","provider_id":"302ai","provider_model_id":"grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.x.ai/docs/models","output":500000,"provider":"xAI","provider_id":"xai","provider_model_id":"grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://opencode.ai/docs/zen","output":500000,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"grok-4.6","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.edenai.co","output":500000,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"xai/grok-4.6","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":6.0,"release_date":"2026-08-12","slug":"xai/grok-4.6","source":"Models.dev","source_url":"https://models.dev/models/xai/grok-4.6/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":42.3,"benchmark_data":[],"cached_input_price_per_million":0.06,"coding_score":68.8,"confidence":"Medium","context_length":1000000,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","developer":"DeepSeek","input_price_per_million":0.442,"intelligence_score":36.3,"last_verified":"2026-09-11T13:08:14.866047","max_output_tokens":384000,"metadata":{"attachment":false,"family":"deepseek-thinking","license":"MIT","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"}]},"modalities":"Text","name":"DeepSeek V4 Pro 0813","offerings":[{"api":"https://openai.bothub.ru/v1","context":1000000,"cost":{"input":1.61,"output":4.84},"doc":"https://bothub.ru/models","output":384000,"provider":"Bothub","provider_id":"bothub","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.04,"input":1.1,"output":2.5},"doc":"https://docs.nano-gpt.com","output":384000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"deepseek/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.do-ai.run/v1","context":1048576,"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"doc":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","output":1048576,"provider":"DigitalOcean","provider_id":"digitalocean","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.vivgrid.com/v1","context":1000000,"cost":{"cache_read":0.05,"input":1.35,"output":3,"reasoning":3},"doc":"https://docs.vivgrid.com/models","output":384000,"provider":"Vivgrid","provider_id":"vivgrid","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/en/model-studio/token-plan-overview","output":384000,"provider":"Alibaba Token Plan","provider_id":"alibaba-token-plan","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.023058,"input":0.6918,"output":2.0754},"doc":"https://docs.aihubmix.com","output":384000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://ark.cn-beijing.volces.com/api/v3","context":1000000,"cost":{"cache_read":0.04453,"input":1.3359,"output":4.00771},"doc":"https://www.volcengine.com/docs/82379/1330310","output":384000,"provider":"Volcengine Ark","provider_id":"volcengine","provider_model_id":"deepseek-v4-pro-ga-260813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1000000,"cost":{"cache_read":0.06,"input":0.442,"output":0.884},"doc":"https://docs.orcarouter.ai","output":384000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"deepseek/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1048576,"cost":{"cache_read":0.047907,"input":1.437216,"output":4.311648},"doc":"https://hyper.charm.land","output":262144,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1000000,"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"doc":"https://requesty.ai/solution/llm-routing/models","output":131072,"provider":"Requesty","provider_id":"requesty","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":1000000,"cost":{"input":1.32,"output":3.96},"doc":"https://huggingface.co/docs/inference-providers","output":384000,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://integrate.api.nvidia.com/v1","context":1000000,"cost":{"input":0,"output":0},"doc":"https://docs.api.nvidia.com/nim/","output":384000,"provider":"Nvidia","provider_id":"nvidia","provider_model_id":"deepseek-ai/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.baseten.co/v1","context":1048576,"cost":{"input":1.32,"output":3.96},"doc":"https://docs.baseten.co/inference/model-apis/overview","output":262144,"provider":"Baseten","provider_id":"baseten","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.066,"input":0.66,"output":1.98},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":384000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"deepseek/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.165,"input":1.65,"output":4.95},"doc":"https://docs.venice.ai","output":32768,"provider":"Venice AI","provider_id":"venice","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":1000000,"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"doc":"https://fireworks.ai/docs/","output":384000,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":1000000,"cost":{"cache_read":1.32,"input":1.32,"output":3.96},"doc":"https://docs.empiriolabs.ai","output":393216,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.1,"input":1.3,"output":2.6},"doc":"https://deepinfra.com/models","output":384000,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"doc":"https://kilo.ai","output":943718,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"deepseek/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1000000,"cost":{"cache_read":0.022,"input":0.66,"output":1.98},"doc":"https://docs.merge.dev/merge-gateway","output":384000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"deepseek/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.066,"input":0.66,"output":1.98},"doc":"https://openrouter.ai/models","output":943718,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"deepseek/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"doc":"https://ofox.ai/docs","output":384000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"deepseek/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.arcee.ai/api/v1","context":1048576,"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"doc":"https://docs.arcee.ai","output":384000,"provider":"Arcee","provider_id":"arcee","provider_model_id":"deepseek/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.scnet.cn/api/llm/v1","context":1000000,"cost":{"cache_read":0,"input":0,"output":0},"doc":"https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html","output":384000,"provider":"SCNet Token Plan","provider_id":"scnet-token-plan","provider_model_id":"DeepSeek-V4-Pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.runinfra.ai/v1","context":1048576,"cost":{"cache_read":0.03,"input":0.6,"output":1.9},"doc":"https://runinfra.ai/docs","output":32768,"provider":"RunInfra","provider_id":"runinfra","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.13,"input":1.32,"output":3.96},"doc":"https://docs.together.ai/docs/serverless-models","output":384000,"provider":"Together AI","provider_id":"togetherai","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1","context":1048576,"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"doc":"https://developers.cloudflare.com/workers-ai/models/","output":1048576,"provider":"Cloudflare Workers AI","provider_id":"cloudflare-workers-ai","provider_model_id":"@cf/deepseek-ai/deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1048576,"cost":{"cache_read":0.5,"input":2,"output":3.999},"doc":"https://api.cortecs.ai/v1/models","output":64000,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview","output":384000,"provider":"Alibaba Token Plan (China)","provider_id":"alibaba-token-plan-cn","provider_model_id":"deepseek-v4-pro-0813","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":0.884,"release_date":"2026-08-12","slug":"deepseek/deepseek-v4-pro-0813","source":"Models.dev","source_url":"https://models.dev/models/deepseek/deepseek-v4-pro-0813/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.02,"coding_score":0.0,"confidence":"Medium","context_length":256000,"description":"Microsoft coding model with native vision support, optimized for fast and efficient software development","developer":"Microsoft","input_price_per_million":0.2,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:14.670278","max_output_tokens":128000,"metadata":{"attachment":true,"family":"mai","links":[{"label":"Announcement","type":"announcement","url":"https://microsoft.ai/news/mai-code-1-1-flash-br-better-faster-at-a-quarter-of-the-cost/"}],"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"tool_call":true},"modalities":"Image, Text","name":"MAI-Code-1.1-Flash","offerings":[{"api":"https://api.githubcopilot.com","context":256000,"cost":{"cache_read":0.02,"input":0.2,"output":1.2},"doc":"https://docs.github.com/en/copilot","output":128000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"mai-code-1.1-flash","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":1.2,"release_date":"2026-08-11","slug":"microsoft/mai-code-1.1-flash","source":"Models.dev","source_url":"https://models.dev/models/microsoft/mai-code-1.1-flash/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":6.1,"benchmark_data":[],"cached_input_price_per_million":0.01,"coding_score":26.8,"confidence":"Medium","context_length":262144,"description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","developer":"NVIDIA","input_price_per_million":0.05,"intelligence_score":13.6,"last_verified":"2026-09-11T13:08:10.962875","max_output_tokens":262144,"metadata":{"attachment":false,"family":"nemotron","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Text","name":"Nemotron 3.5 Lightning 30B A3B","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1000000,"cost":{"cache_read":0.01,"input":0.05,"output":0.2},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"nvidia/nemotron-3.5-lightning","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://api.tokenfactory.nebius.com/v1","context":1048576,"cost":{"cache_read":0.06,"input":0.06,"output":0.24},"doc":"https://docs.tokenfactory.nebius.com/","output":1048576,"provider":"Nebius Token Factory","provider_id":"nebius","provider_model_id":"nvidia/Nemotron-3_5-Lightning","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":8192,"cost":{"cache_read":0.5,"cache_write":0.5,"input":0.5,"output":0.5},"doc":"https://agent.pioneer.ai/llms.txt","output":4096,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://integrate.api.nvidia.com/v1","context":262144,"cost":{"input":0,"output":0},"doc":"https://docs.api.nvidia.com/nim/","output":262144,"provider":"Nvidia","provider_id":"nvidia","provider_model_id":"nvidia/nemotron-3.5-lightning-30b-a3b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":262144,"cost":{"cache_read":0.01,"input":0.05,"output":0.2},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":131072,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"nvidia/nemotron-3.5-lightning","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":262144,"cost":{"cache_read":0.01,"input":0.05,"output":0.2},"doc":"https://fireworks.ai/docs/","output":262144,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":262144,"cost":{"cache_read":0.04,"input":0.08,"output":0.2},"doc":"https://kilo.ai","output":131072,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"nvidia/nemotron-3.5-lightning","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1000000,"cost":{"input":0,"output":0},"doc":"https://docs.merge.dev/merge-gateway","output":262144,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"nvidia/nemotron-3.5-lightning-30b-a3b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":262144,"cost":{"cache_read":0.04,"input":0.08,"output":0.2},"doc":"https://openrouter.ai/models","output":131072,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"nvidia/nemotron-3.5-lightning","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.runinfra.ai/v1","context":262144,"cost":{"cache_read":0.01,"input":0.05,"output":0.15},"doc":"https://runinfra.ai/docs","output":32768,"provider":"RunInfra","provider_id":"runinfra","provider_model_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":0.2,"release_date":"2026-08-11","slug":"nvidia/nemotron-3.5-lightning","source":"Models.dev","source_url":"https://models.dev/models/nvidia/nemotron-3.5-lightning/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":null,"coding_score":0.0,"confidence":"Medium","context_length":262144,"description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","developer":"NVIDIA","input_price_per_million":null,"intelligence_score":0.0,"last_verified":"2026-08-11T18:23:25.203507","max_output_tokens":262144,"metadata":{"attachment":false,"family":"nemotron","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Text","name":"Nemotron 3.5 Lightning 30B A3B","offerings":[{"api":"https://integrate.api.nvidia.com/v1","context":262144,"cost":{"input":0,"output":0},"doc":"https://docs.api.nvidia.com/nim/","output":262144,"provider":"Nvidia","provider_id":"nvidia","provider_model_id":"nvidia/nemotron-3.5-lightning-30b-a3b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"input":0,"output":0},"doc":"https://docs.merge.dev/merge-gateway","output":262144,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"nvidia/nemotron-3.5-lightning-30b-a3b","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":null,"release_date":"2026-08-11","slug":"nvidia/nemotron-3.5-lightning-30b-a3b","source":"Models.dev","source_url":"https://models.dev/models/nvidia/nemotron-3.5-lightning-30b-a3b/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[{"date":"2026-08-10","metric":"success rate","name":"MCP Atlas","score":75.5,"source":"https://huggingface.co/meta-models/Muse-Glimmer-30B","variant":"public"},{"date":"2026-08-10","name":"DeepSearch QA","score":74.6,"source":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"date":"2026-08-10","metric":"resolve rate","name":"SWE-Bench Pro","score":51.2,"source":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"date":"2026-08-10","metric":"resolve rate","name":"SWE-Bench Verified","score":76,"source":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"date":"2026-08-10","metric":"success rate","name":"Terminal-Bench","score":51.7,"source":"https://huggingface.co/meta-models/Muse-Glimmer-30B","variant":"with terminus2","version":"2.1"},{"date":"2026-08-10","metric":"success rate","name":"OSWorld-Verified","score":65.9,"source":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"date":"2026-08-10","metric":"accuracy","name":"AIME 2026","score":94.7,"source":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"date":"2026-08-10","metric":"accuracy","name":"GPQA Diamond","score":83.5,"source":"https://huggingface.co/meta-models/Muse-Glimmer-30B","variant":"AA"},{"date":"2026-08-10","metric":"accuracy","name":"CharXiv Reasoning","score":78.8,"source":"https://huggingface.co/meta-models/Muse-Glimmer-30B"}],"cached_input_price_per_million":0.05,"coding_score":0.0,"confidence":"Medium","context_length":131072,"description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","developer":"Meta","input_price_per_million":0.2,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:13.636514","max_output_tokens":131072,"metadata":{"attachment":true,"family":"muse","knowledge":"2026-01-04","license":"Apache 2.0","links":[{"label":"Announcement","type":"announcement","url":"https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model"},{"label":"Model card","type":"model_card","url":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"label":"Developer docs","type":"docs","url":"https://developer.meta.com/ai/models/muse-glimmer/"}],"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/meta-models/Muse-Glimmer-30B"}]},"modalities":"Image, Text","name":"Muse Glimmer 30B","offerings":[{"api":"https://nano-gpt.com/api/v1","context":131072,"cost":{"cache_read":0.04,"input":0.35,"output":1.5},"doc":"https://docs.nano-gpt.com","output":117964,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"meta/muse-glimmer-30b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":131072,"cost":{"input":0,"output":0},"doc":"https://requesty.ai/solution/llm-routing/models","output":20480,"provider":"Requesty","provider_id":"requesty","provider_model_id":"muse-glimmer-30b","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://integrate.api.nvidia.com/v1","context":131072,"cost":{"input":0,"output":0},"doc":"https://docs.api.nvidia.com/nim/","output":131072,"provider":"Nvidia","provider_id":"nvidia","provider_model_id":"meta/muse-glimmer-30b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":131072,"cost":{"cache_read":0.04,"input":0.35,"output":1.5},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":131072,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"meta/muse-glimmer-30b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":131072,"cost":{"cache_read":0.04,"input":0.35,"output":1.5},"doc":"https://fireworks.ai/docs/","output":131072,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/muse-glimmer-30b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":131072,"cost":{"cache_read":0.05,"input":0.2,"output":0.8},"doc":"https://docs.empiriolabs.ai","output":32768,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"muse-glimmer-30b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":131072,"cost":{"cache_read":0.04,"input":0.3,"output":1.1},"doc":"https://kilo.ai","output":117964,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"meta/muse-glimmer-30b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":131072,"cost":{"cache_read":0.04,"input":0.3,"output":1.1},"doc":"https://openrouter.ai/models","output":117964,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"meta/muse-glimmer-30b","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":0.8,"release_date":"2026-08-10","slug":"meta/muse-glimmer-30b","source":"Models.dev","source_url":"https://models.dev/models/meta/muse-glimmer-30b/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":null,"coding_score":0.0,"confidence":"Medium","context_length":8000,"description":"Image model for prompt-driven generation, editing, and visual design workflows","developer":"xAI","input_price_per_million":null,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:18.680057","max_output_tokens":0,"metadata":{"attachment":true,"family":"grok","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"reasoning":false,"temperature":false,"tool_call":false},"modalities":"Image, Text","name":"Grok Imagine Image 2.0","offerings":[{"api":"https://kenari.id/v1","context":8000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":0,"provider":"Kenari","provider_id":"kenari","provider_model_id":"grok-imagine-image-2-0","reasoning":false,"structured_output":null,"tool_call":false},{"api":"","context":0,"cost":{},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":0,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"spacexai/grok-imagine-image-2.0","reasoning":false,"structured_output":null,"tool_call":false},{"api":"","context":64000,"cost":{},"doc":"https://docs.x.ai/docs/models","output":0,"provider":"xAI","provider_id":"xai","provider_model_id":"grok-imagine-image-2.0","reasoning":false,"structured_output":null,"tool_call":false}],"open_weights":false,"output_price_per_million":null,"release_date":"2026-08-07","slug":"xai/grok-imagine-image-2.0","source":"Models.dev","source_url":"https://models.dev/models/xai/grok-imagine-image-2.0/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":33.6,"benchmark_data":[],"cached_input_price_per_million":0.06,"coding_score":52.7,"confidence":"Medium","context_length":524288,"description":"Upstage's flagship model, specialized for agentic use","developer":"Upstage","input_price_per_million":0.3,"intelligence_score":41.6,"last_verified":"2026-09-11T13:08:18.293775","max_output_tokens":131072,"metadata":{"attachment":false,"family":"solar-pro","knowledge":"2026-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Text","name":"Solar Pro 4","offerings":[{"api":"https://nano-gpt.com/api/v1","context":524288,"cost":{"cache_read":0.006,"input":0.03,"output":0.12},"doc":"https://docs.nano-gpt.com","output":131072,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"upstage/solar-pro4","reasoning":false,"structured_output":true,"tool_call":true},{"api":"https://llmtr.com/v1","context":524288,"cost":{"input":0.03,"output":0.12},"doc":"https://llmtr.com/docs","output":131072,"provider":"LLMTR","provider_id":"llmtr","provider_model_id":"upstage/solar-pro4","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":524288,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"doc":"https://kilo.ai","output":131072,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"upstage/solar-pro4","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":524288,"cost":{"cache_read":0.018,"input":0.09,"output":0.36},"doc":"https://openrouter.ai/models","output":131072,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"upstage/solar-pro4","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.upstage.ai/v1/solar","context":524288,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"doc":"https://developers.upstage.ai/docs/apis/chat","output":131072,"provider":"Upstage","provider_id":"upstage","provider_model_id":"solar-pro4","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":1.2,"release_date":"2026-08-06","slug":"upstage/solar-pro4","source":"Models.dev","source_url":"https://models.dev/models/upstage/solar-pro4/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":44.0,"benchmark_data":[],"cached_input_price_per_million":0.15,"coding_score":72.2,"confidence":"Medium","context_length":1048576,"description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","developer":"Meta","input_price_per_million":1.25,"intelligence_score":39.8,"last_verified":"2026-09-11T13:08:13.533547","max_output_tokens":131072,"metadata":{"attachment":true,"family":"muse","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Audio, Image, Pdf, Text, Video","name":"Muse Spark 1.2","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1000000,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"meta/muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://llmgateway.io/docs","output":131072,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"meta/muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://docs.orcarouter.ai","output":131072,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"meta/muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":1048576,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"meta/muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.meta.ai/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://dev.meta.ai/docs","output":131072,"provider":"Meta","provider_id":"meta","provider_model_id":"muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://llmgateway.io/docs","output":131072,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://opper.ai/models","output":131072,"provider":"Opper","provider_id":"opper","provider_model_id":"meta/muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":1048576,"cost":{"cache_read":1,"input":1.25,"output":4.25},"doc":"https://docs.empiriolabs.ai","output":131072,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"muse-spark-1-2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://kilo.ai","output":943718,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"meta/muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://docs.merge.dev/merge-gateway","output":262144,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"meta/muse-spark-1.2","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://abacus.ai/help/api","output":131072,"provider":"Abacus","provider_id":"abacus","provider_model_id":"muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://opencode.ai/docs/zen","output":131072,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"doc":"https://openrouter.ai/models","output":943718,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"meta/muse-spark-1.2","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":4.25,"release_date":"2026-08-05","slug":"meta/muse-spark-1.2","source":"Models.dev","source_url":"https://models.dev/models/meta/muse-spark-1.2/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[{"name":"AIME26","score":96.67,"source":"https://console.sakana.ai/models?model=sakana-namazu"},{"name":"MMLU-Pro","score":90.33,"source":"https://console.sakana.ai/models?model=sakana-namazu"},{"name":"LiveCodeBench v6","score":90.33,"source":"https://console.sakana.ai/models?model=sakana-namazu"},{"name":"JFBench","score":37.4,"source":"https://console.sakana.ai/models?model=sakana-namazu"},{"name":"Translation","score":52.2,"source":"https://console.sakana.ai/models?model=sakana-namazu"},{"name":"FairPoliticsQA","score":56.3,"source":"https://console.sakana.ai/models?model=sakana-namazu"}],"cached_input_price_per_million":0.15,"coding_score":0.0,"confidence":"Medium","context_length":262144,"description":"Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows","developer":"Sakana","input_price_per_million":0.95,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:14.798858","max_output_tokens":65536,"metadata":{"attachment":true,"family":"sakana-namazu","links":[{"label":"Official product page","type":"announcement","url":"https://sakana.ai/namazu/"},{"label":"Official model documentation","type":"docs","url":"https://console.sakana.ai/models?model=sakana-namazu"}],"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Image, Pdf, Text","name":"Sakana Namazu","offerings":[{"api":"https://api.sakana.ai/v1","context":262144,"cost":{"cache_read":0.15,"input":0.95,"output":4},"doc":"https://console.sakana.ai/models","output":65536,"provider":"Sakana AI","provider_id":"sakana","provider_model_id":"sakana-namazu","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":262144,"cost":{"cache_read":0.15,"input":0.95,"output":4},"doc":"https://kilo.ai","output":65536,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"sakana/sakana-namazu","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":262144,"cost":{"cache_read":0.15,"input":0.95,"output":4},"doc":"https://docs.merge.dev/merge-gateway","output":65536,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"sakana/sakana-namazu","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":262144,"cost":{"cache_read":0.15,"input":0.95,"output":4},"doc":"https://openrouter.ai/models","output":65536,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"sakana/sakana-namazu","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":4.0,"release_date":"2026-08-03","slug":"sakana/sakana-namazu","source":"Models.dev","source_url":"https://models.dev/models/sakana/sakana-namazu/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.25,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","developer":"Alibaba Qwen","input_price_per_million":2.0,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:10.768127","max_output_tokens":131072,"metadata":{"attachment":true,"family":"qwen","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"temperature":true,"tool_call":true},"modalities":"Image, Pdf, Text, Video","name":"Qwen3.8 Max","offerings":[{"api":"https://nano-gpt.com/api/v1","context":991000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"qwen3.8-max","reasoning":false,"structured_output":true,"tool_call":true},{"api":"https://api.scx.ai/v1","context":1000000,"cost":{"cache_read":0.17,"cache_write":2.5,"input":1.815,"output":5.4461},"doc":"https://platform.scx.ai/docs","output":131072,"provider":"SCX.ai","provider_id":"scx-ai","provider_model_id":"Qwen3.8-Max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://llmgateway.io/docs","output":131072,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"alibaba/qwen3.8-max","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/en/model-studio/token-plan-overview","output":131072,"provider":"Alibaba Token Plan","provider_id":"alibaba-token-plan","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":991000,"cost":{"cache_read":0.169,"cache_write":2.1125,"input":1.69,"output":5.07},"doc":"https://docs.aihubmix.com","output":128000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://docs.orcarouter.ai","output":131072,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"qwen/qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://kenari.id/v1","context":1000000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":131072,"provider":"Kenari","provider_id":"kenari","provider_model_id":"qwen3-8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://dashscope.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0.22218,"cache_write":2.22179,"input":1.77744,"output":5.33231},"doc":"https://www.alibabacloud.com/help/en/model-studio/models","output":131072,"provider":"Alibaba (China)","provider_id":"alibaba-cn","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://requesty.ai/solution/llm-routing/models","output":131072,"provider":"Requesty","provider_id":"requesty","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1000000,"cost":{"cache_read":0.23,"cache_write":2.35,"input":1.88,"output":5.63},"doc":"https://www.crossmodel.ai/docs","output":131072,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"qwen/qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://www.alibabacloud.com/help/en/model-studio/models","output":131072,"provider":"Alibaba","provider_id":"alibaba","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"alibaba/qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"input":2,"output":6},"doc":"https://developers.cloudflare.com/ai-gateway/","output":131072,"provider":"Cloudflare AI Gateway","provider_id":"cloudflare-ai-gateway","provider_model_id":"alibaba/qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":262144,"cost":{"cache_read":0.25,"input":2,"output":6},"doc":"https://fireworks.ai/docs/","output":131072,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/qwen3p8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":1000000,"cost":{"cache_read":2,"input":2,"output":6},"doc":"https://docs.empiriolabs.ai","output":131072,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"qwen3-8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":256000,"cost":{"cache_read":0.206,"input":1.65,"output":4.951},"doc":"https://deepinfra.com/models","output":131072,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"Qwen/Qwen3.8-Max","reasoning":false,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1000000,"cost":{"cache_read":0.25,"input":2,"output":6},"doc":"https://docs.merge.dev/merge-gateway","output":131072,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"qwen/qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1000000,"cost":{"input":2,"output":6},"doc":"https://abacus.ai/help/api","output":131072,"provider":"Abacus","provider_id":"abacus","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.cline.bot/api/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://docs.cline.bot/getting-started/clinepass","output":131072,"provider":"ClinePass","provider_id":"cline-pass","provider_model_id":"cline-pass/qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.17,"cache_write":2.14,"input":1.71,"output":5.14},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"qwen/qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"bailian/qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.scnet.cn/api/llm/v1","context":1000000,"cost":{"cache_read":0,"input":0,"output":0},"doc":"https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html","output":131072,"provider":"SCNet Token Plan","provider_id":"scnet-token-plan","provider_model_id":"Qwen3.8-Max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.302.ai/v1","context":1000000,"cost":{"input":2.16,"output":6.36},"doc":"https://doc.302.ai","output":131072,"provider":"302.AI","provider_id":"302ai","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://vancine.com/v1","context":1000000,"cost":{"cache_read":0.2,"input":1.6,"output":4.8},"doc":"https://vancine.com/docs","output":131072,"provider":"Vancine","provider_id":"vancine","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview","output":131072,"provider":"Alibaba Token Plan (China)","provider_id":"alibaba-token-plan-cn","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://docs.edenai.co","output":131072,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"qwen/qwen3.8-max","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":6.0,"release_date":"2026-08-03","slug":"alibaba/qwen3.8-max","source":"Models.dev","source_url":"https://models.dev/models/alibaba/qwen3.8-max/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":41.7,"benchmark_data":[{"metric":"pass@1","name":"Terminal-Bench","score":82.7,"source":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731","variant":"max","version":"2.1"},{"date":"2026-07-31","harness":"DeepSeek Harness minimal mode","metric":"resolve rate","name":"NL2Repo","score":54.2,"source":"https://api-docs.deepseek.com/updates/","variant":"max effort"},{"date":"2026-07-31","harness":"DeepSeek Harness minimal mode","metric":"score","name":"CyberGym","score":76.7,"source":"https://api-docs.deepseek.com/updates/","variant":"max effort"},{"date":"2026-07-31","harness":"DeepSeek Harness minimal mode","metric":"resolve rate","name":"DeepSWE","score":54.4,"source":"https://api-docs.deepseek.com/updates/","variant":"max effort"},{"date":"2026-07-31","harness":"DeepSeek Harness minimal mode","metric":"score","name":"Toolathlon-Verified","score":70.3,"source":"https://api-docs.deepseek.com/updates/","variant":"max effort"},{"date":"2026-07-31","harness":"DeepSeek Harness minimal mode","metric":"score","name":"Agents' Last Exam","score":25.2,"source":"https://api-docs.deepseek.com/updates/","variant":"max effort"},{"dataset":"public","date":"2026-07-31","metric":"success rate","name":"AutomationBench","score":25.1,"source":"https://api-docs.deepseek.com/updates/","variant":"max effort"},{"dataset":"internal","date":"2026-07-31","metric":"score","name":"DSBench-FullStack","score":68.7,"source":"https://api-docs.deepseek.com/updates/","variant":"max effort"},{"dataset":"internal","date":"2026-07-31","metric":"score","name":"DSBench-Hard","score":59.6,"source":"https://api-docs.deepseek.com/updates/","variant":"max effort"}],"cached_input_price_per_million":0.013,"coding_score":69.1,"confidence":"Medium","context_length":1000000,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","developer":"DeepSeek","input_price_per_million":0.05,"intelligence_score":34.5,"last_verified":"2026-09-11T13:08:14.910747","max_output_tokens":384000,"metadata":{"attachment":false,"family":"deepseek-flash","knowledge":"2025-05","license":"MIT","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731"}]},"modalities":"Text","name":"DeepSeek V4 Flash 0731","offerings":[{"api":"https://openai.bothub.ru/v1","context":1000000,"cost":{"input":0.1,"output":0.28},"doc":"https://bothub.ru/models","output":384000,"provider":"Bothub","provider_id":"bothub","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.greenpt.ai/v1","context":1000000,"cost":{"cache_read":0.0456,"input":0.1596,"output":0.399},"doc":"https://docs.greenpt.ai","output":384000,"provider":"GreenPT","provider_id":"greenpt","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ambient.xyz/v1","context":1048576,"cost":{"cache_read":0.016,"cache_write":0,"input":0.08,"output":0.18},"doc":"https://ambient.xyz","output":1048576,"provider":"Ambient","provider_id":"ambient","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://nano-gpt.com/api/v1","context":1000000,"cost":{"cache_read":0.013,"input":0.05,"output":0.16},"doc":"https://docs.nano-gpt.com","output":131072,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.do-ai.run/v1","context":1048576,"cost":{"cache_read":0.0252,"input":0.08,"output":0.252},"doc":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","output":1048576,"provider":"DigitalOcean","provider_id":"digitalocean","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.inceptron.io/v1","context":1048576,"cost":{"cache_read":0.03,"cache_write":0,"input":0.13,"output":0.28},"doc":"https://docs.inceptron.io","output":1048576,"provider":"Inceptron","provider_id":"inceptron","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://ollama.com/v1","context":1048576,"cost":{},"doc":"https://docs.ollama.com/cloud","output":1048576,"provider":"Ollama Cloud","provider_id":"ollama-cloud","provider_model_id":"deepseek-v4-flash:0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/en/model-studio/token-plan-overview","output":384000,"provider":"Alibaba Token Plan","provider_id":"alibaba-token-plan","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.0284,"input":0.142,"output":0.284},"doc":"https://docs.aihubmix.com","output":384000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://ark.cn-beijing.volces.com/api/v3","context":1000000,"cost":{"cache_read":0.01484,"input":0.4453,"output":1.3359},"doc":"https://www.volcengine.com/docs/82379/1330310","output":384000,"provider":"Volcengine Ark","provider_id":"volcengine","provider_model_id":"deepseek-v4-flash-ga-260731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1000000,"cost":{"cache_read":0.02,"input":0.147,"output":0.295},"doc":"https://docs.orcarouter.ai","output":384000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.scaleway.ai/v1","context":256000,"cost":{"cache_read":0.0936,"input":0.468,"output":0.936,"reasoning":0.936},"doc":"https://www.scaleway.com/en/docs/generative-apis/","output":16384,"provider":"Scaleway","provider_id":"scaleway","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.tokenfactory.nebius.com/v1","context":1024000,"cost":{"cache_read":0.14,"input":0.14,"output":0.28},"doc":"https://docs.tokenfactory.nebius.com/","output":1024000,"provider":"Nebius Token Factory","provider_id":"nebius","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1000000,"cost":{"cache_read":0.044,"input":0.44,"output":1.32},"doc":"https://hyper.charm.land","output":384000,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.07,"input":0.28,"output":0.56},"doc":"https://requesty.ai/solution/llm-routing/models","output":131072,"provider":"Requesty","provider_id":"requesty","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":1048576,"cost":{"input":0.14,"output":0.28},"doc":"https://huggingface.co/docs/inference-providers","output":384000,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://aki.io/v1","context":1048576,"cost":{"cache_read":0.1,"input":0.2,"output":0.5},"doc":"https://aki.io/docs/","output":81920,"provider":"AKI.IO","provider_id":"aki-io","provider_model_id":"deepseek-v4-flash-0731-284b","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0.04,"input":0.2,"output":0.4},"doc":"https://www.alibabacloud.com/help/en/model-studio/models","output":384000,"provider":"Alibaba","provider_id":"alibaba","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://integrate.api.nvidia.com/v1","context":1000000,"cost":{"input":0,"output":0},"doc":"https://docs.api.nvidia.com/nim/","output":384000,"provider":"Nvidia","provider_id":"nvidia","provider_model_id":"deepseek-ai/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.baseten.co/v1","context":1048576,"cost":{"cache_read":0.028,"input":0.13,"output":0.26},"doc":"https://docs.baseten.co/inference/model-apis/overview","output":384000,"provider":"Baseten","provider_id":"baseten","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.014,"input":0.076,"output":0.153},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":384000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.tensorx.ai/v1","context":1048576,"cost":{"cache_read":0.06,"input":0.25,"output":0.3},"doc":"https://docs.tensorx.ai/","output":384000,"provider":"TensorX","provider_id":"tensorx","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.035,"input":0.175,"output":0.35},"doc":"https://docs.venice.ai","output":32768,"provider":"Venice AI","provider_id":"venice","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.perplexity.ai/v1","context":1000000,"cost":{"cache_read":0.028,"input":0.13,"output":0.26},"doc":"https://docs.perplexity.ai/docs/agent-api/models","output":384000,"provider":"Perplexity Agent","provider_id":"perplexity-agent","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":1000000,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://fireworks.ai/docs/","output":384000,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":1000000,"cost":{"cache_read":0.424,"input":0.424,"output":1.272},"doc":"https://docs.empiriolabs.ai","output":393216,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.015,"input":0.06,"output":0.18},"doc":"https://deepinfra.com/models","output":384000,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.028,"input":0.44,"output":1.32},"doc":"https://kilo.ai","output":943718,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.openreason.app/v1","context":1000000,"cost":{"input":0.1371,"output":0.2743},"doc":"https://openreason.app/docs","output":384000,"provider":"OpenReason","provider_id":"openreason","provider_model_id":"deepseek-ai/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1000000,"cost":{"cache_read":0.07,"input":0.28,"output":0.56},"doc":"https://docs.merge.dev/merge-gateway","output":384000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"deepseek/deepseek-v4-flash-0731-fast","reasoning":true,"structured_output":false,"tool_call":false},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1000000,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"doc":"https://docs.merge.dev/merge-gateway","output":384000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1310720,"cost":{"cache_read":0.016,"input":0.065,"output":0.18},"doc":"https://openrouter.ai/models","output":943718,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.014,"input":0.44,"output":1.32},"doc":"https://ofox.ai/docs","output":384000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"deepseek/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://developer.amd.com.cn/radeon/api/v1","context":1000000,"cost":{"cache_read":0.0028,"input":0.14,"output":0.28},"doc":"https://developer.amd.com.cn/radeon/tokenfactory","output":384000,"provider":"AMD","provider_id":"amd","provider_model_id":"DeepSeek-V4-Flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.scnet.cn/api/llm/v1","context":1000000,"cost":{"cache_read":0,"input":0,"output":0},"doc":"https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html","output":384000,"provider":"SCNet Token Plan","provider_id":"scnet-token-plan","provider_model_id":"DeepSeek-V4-Flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.runinfra.ai/v1","context":1048576,"cost":{"cache_read":0.01,"input":0.13,"output":0.27},"doc":"https://runinfra.ai/docs","output":32768,"provider":"RunInfra","provider_id":"runinfra","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.03,"input":0.14,"output":0.28},"doc":"https://docs.together.ai/docs/serverless-models","output":384000,"provider":"Together AI","provider_id":"togetherai","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1","context":1310720,"cost":{"cache_read":0.014,"input":0.44,"output":1.32},"doc":"https://developers.cloudflare.com/workers-ai/models/","output":1048576,"provider":"Cloudflare Workers AI","provider_id":"cloudflare-workers-ai","provider_model_id":"@cf/deepseek-ai/deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1048576,"cost":{"cache_read":0.03,"input":0.13,"output":0.28},"doc":"https://api.cortecs.ai/v1/models","output":1048576,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview","output":384000,"provider":"Alibaba Token Plan (China)","provider_id":"alibaba-token-plan-cn","provider_model_id":"deepseek-v4-flash-0731","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.tinfoil.sh/v1","context":1048576,"cost":{"cache_read":0.06,"input":0.3,"output":0.7},"doc":"https://docs.tinfoil.sh","output":384000,"provider":"Tinfoil","provider_id":"tinfoil","provider_model_id":"deepseek-v4-flash","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":0.16,"release_date":"2026-07-31","slug":"deepseek/deepseek-v4-flash-0731","source":"Models.dev","source_url":"https://models.dev/models/deepseek/deepseek-v4-flash-0731/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":25.0,"benchmark_data":[],"cached_input_price_per_million":0.1,"coding_score":52.9,"confidence":"Medium","context_length":1048576,"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","developer":"Thinkingmachines","input_price_per_million":0.45,"intelligence_score":26.1,"last_verified":"2026-09-11T13:08:13.453197","max_output_tokens":1048576,"metadata":{"attachment":true,"family":"ling","license":"Apache-2.0","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"reasoning":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/thinkingmachines/Inkling-Small"}]},"modalities":"Audio, Image, Text","name":"Inkling Small","offerings":[{"api":"https://nano-gpt.com/api/v1","context":524288,"cost":{"cache_read":0.1,"input":0.5,"output":1.2},"doc":"https://docs.nano-gpt.com","output":32768,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"thinkingmachines/Inkling-Small","reasoning":false,"structured_output":false,"tool_call":true},{"api":"https://llmtr.com/v1","context":262144,"cost":{"input":0.58,"output":1.44},"doc":"https://llmtr.com/docs","output":262144,"provider":"LLMTR","provider_id":"llmtr","provider_model_id":"thinkingmachines/inkling-small","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":524288,"cost":{"input":0.5,"output":1.2},"doc":"https://huggingface.co/docs/inference-providers","output":1048576,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"thinkingmachines/Inkling-Small","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://inference.baseten.co/v1","context":1048576,"cost":{"cache_read":0.1,"input":0.5,"output":1.2},"doc":"https://docs.baseten.co/inference/model-apis/overview","output":32768,"provider":"Baseten","provider_id":"baseten","provider_model_id":"thinkingmachines/inkling-small","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.1,"input":0.5,"output":1.2},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":1000000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"thinkingmachines/inkling-small","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":524288,"cost":{"cache_read":0.1,"input":0.45,"output":1.2},"doc":"https://deepinfra.com/models","output":1048576,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"thinkingmachines/Inkling-Small","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":524288,"cost":{"cache_read":0.1,"input":0.45,"output":1.2},"doc":"https://kilo.ai","output":262144,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"thinkingmachines/inkling-small","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.1,"input":0.45,"output":1.2},"doc":"https://openrouter.ai/models","output":262144,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"thinkingmachines/inkling-small","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://api.arcee.ai/api/v1","context":262144,"cost":{"cache_read":0.1,"input":0.5,"output":1.2},"doc":"https://docs.arcee.ai","output":262144,"provider":"Arcee","provider_id":"arcee","provider_model_id":"thinkingmachines/inkling-small","reasoning":true,"structured_output":null,"tool_call":true}],"open_weights":true,"output_price_per_million":1.2,"release_date":"2026-07-30","slug":"thinkingmachines/inkling-small","source":"Models.dev","source_url":"https://models.dev/models/thinkingmachines/inkling-small/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":56.2,"benchmark_data":[{"date":"2026-07-24","metric":"resolved","name":"SWE-Bench Verified","score":96,"source":"https://www.anthropic.com/claude-opus-5-system-card"},{"date":"2026-07-24","metric":"resolve rate","name":"SWE-Bench Pro","score":79.2,"source":"https://www.anthropic.com/claude-opus-5-system-card"},{"date":"2026-07-24","metric":"resolve rate","name":"SWE-Bench Multilingual","score":89.5,"source":"https://www.anthropic.com/claude-opus-5-system-card"},{"date":"2026-07-24","metric":"resolve rate","name":"SWE-Bench Multimodal","score":59.4,"source":"https://www.anthropic.com/claude-opus-5-system-card"},{"date":"2026-07-24","metric":"resolve rate","name":"DeepSWE","score":68.8,"source":"https://www.anthropic.com/claude-opus-5-system-card","version":"1.1"},{"dataset":"Main","date":"2026-07-24","metric":"mean@5","name":"FrontierCode","score":53.4,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"medium effort","version":"1.1"},{"date":"2026-07-24","harness":"mini-SWE-agent","metric":"mean reward","name":"Frontier-Bench","score":43.3,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"max effort","version":"v0.1"},{"date":"2026-07-24","metric":"accuracy","name":"BrowseComp","score":90.8,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"single agent"},{"date":"2026-07-24","metric":"accuracy","name":"Humanity's Last Exam","score":56.3,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"no tools"},{"date":"2026-07-24","metric":"accuracy","name":"Humanity's Last Exam","score":64.7,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"with tools"},{"date":"2026-07-24","metric":"F1","name":"DeepSearchQA","score":95,"source":"https://www.anthropic.com/news/claude-opus-5","variant":"max effort"},{"date":"2026-07-24","metric":"success rate","name":"OSWorld","score":70.6,"source":"https://www.anthropic.com/claude-opus-5-system-card","version":"2.0"},{"date":"2026-07-24","metric":"Elo","name":"GDPval-AA","score":1861,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"max effort","version":"v2"},{"date":"2026-07-24","metric":"Elo","name":"AA-Briefcase","score":1720,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"max effort"},{"date":"2026-07-24","metric":"success rate","name":"AutomationBench","score":26,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"max effort"},{"date":"2026-07-24","metric":"accuracy","name":"ARC-AGI-1","score":97.5,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"max effort"},{"date":"2026-07-24","metric":"accuracy","name":"ARC-AGI-2","score":90.4,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"max effort"},{"date":"2026-07-24","metric":"RHAE","name":"ARC-AGI-3","score":30.2,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"high effort"},{"date":"2026-07-24","metric":"score","name":"HealthBench Professional","score":59.8,"source":"https://www.anthropic.com/claude-opus-5-system-card","variant":"max effort"}],"cached_input_price_per_million":0.5,"coding_score":78.0,"confidence":"Medium","context_length":1000000,"description":"Strongest Claude Opus model for coding, agents, and professional work","developer":"Anthropic","input_price_per_million":5.0,"intelligence_score":50.7,"last_verified":"2026-09-11T13:08:11.398577","max_output_tokens":128000,"metadata":{"attachment":true,"family":"claude-opus","knowledge":"2026-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"temperature":false,"tool_call":true},"modalities":"Image, Pdf, Text","name":"Claude Opus 5","offerings":[{"api":"https://agentrouter.org/v1","context":1000000,"cost":{},"doc":"https://agentrouter.org/docs/opencode.html","output":128000,"provider":"AgentRouter","provider_id":"agentrouter","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://nano-gpt.com/api/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://docs.nano-gpt.com","output":128000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://llmgateway.io/docs","output":128000,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://docs.aihubmix.com","output":128000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":10,"input":5,"output":25},"doc":"https://docs.orcarouter.ai","output":128000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure Cognitive Services","provider_id":"azure-cognitive-services","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://kenari.id/v1","context":1000000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":128000,"provider":"Kenari","provider_id":"kenari","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","output":128000,"provider":"Vertex","provider_id":"google-vertex","provider_model_id":"claude-opus-5@default","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://agent.pioneer.ai/llms.txt","output":128000,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://requesty.ai/solution/llm-routing/models","output":128000,"provider":"Requesty","provider_id":"requesty","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://www.crossmodel.ai/docs","output":128000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://docs.anthropic.com/en/docs/about-claude/models","output":128000,"provider":"Anthropic","provider_id":"anthropic","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"doc":"https://docs.venice.ai","output":128000,"provider":"Venice AI","provider_id":"venice","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://llmgateway.io/docs","output":128000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://developers.cloudflare.com/ai-gateway/","output":128000,"provider":"Cloudflare AI Gateway","provider_id":"cloudflare-ai-gateway","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://docs.github.com/en/copilot","output":64000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://opper.ai/models","output":128000,"provider":"Opper","provider_id":"opper","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure","provider_id":"azure","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","output":128000,"provider":"Amazon Bedrock","provider_id":"amazon-bedrock","provider_model_id":"anthropic.claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://docs.merge.dev/merge-gateway","output":128000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1000000,"cost":{"input":5,"output":25},"doc":"https://abacus.ai/help/api","output":128000,"provider":"Abacus","provider_id":"abacus","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://opencode.ai/docs/zen","output":128000,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://openrouter.ai/models","output":128000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://ofox.ai/docs","output":128000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://neon.com/docs","output":128000,"provider":"Neon","provider_id":"neon","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1","context":1000000,"cost":{},"doc":"https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api","output":128000,"provider":"Snowflake Cortex","provider_id":"snowflake-cortex","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.302.ai/v1","context":1000000,"cost":{"input":5,"output":25},"doc":"https://doc.302.ai","output":128000,"provider":"302.AI","provider_id":"302ai","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1000000,"cost":{"cache_read":0.55,"cache_write":6.874,"input":5.5,"output":27.498},"doc":"https://api.cortecs.ai/v1/models","output":128000,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude","output":128000,"provider":"Vertex (Anthropic)","provider_id":"google-vertex-anthropic","provider_model_id":"claude-opus-5@default","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1000000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"doc":"https://docs.edenai.co","output":128000,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"anthropic/claude-opus-5","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":25.0,"release_date":"2026-07-24","slug":"anthropic/claude-opus-5","source":"Models.dev","source_url":"https://models.dev/models/anthropic/claude-opus-5/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.009,"coding_score":0.0,"confidence":"Medium","context_length":1048576,"description":"Agentic coding model from Poolside in the XS size class for local deployment","developer":"Poolside","input_price_per_million":0.09,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:08.961931","max_output_tokens":32768,"metadata":{"attachment":false,"family":"laguna","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":false,"temperature":true,"tool_call":true},"modalities":"Text","name":"Laguna S 2.1","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.01,"input":0.1,"output":0.2},"doc":"https://docs.nano-gpt.com","output":131072,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"poolside/laguna-s-2.1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://inference.poolside.ai/v1","context":1048576,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://platform.poolside.ai","output":32768,"provider":"Poolside","provider_id":"poolside","provider_model_id":"poolside/laguna-s-2.1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":1000000,"cost":{"cache_read":0.01,"cache_write":0.1,"input":0.1,"output":0.2},"doc":"https://agent.pioneer.ai/llms.txt","output":131072,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"poolside/laguna-s-2.1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.01,"input":0.1,"output":0.2},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":131072,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"poolside/laguna-s-2.1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.01,"input":0.1,"output":0.2},"doc":"https://kilo.ai","output":131072,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"poolside/laguna-s-2.1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.009,"input":0.09,"output":0.18},"doc":"https://openrouter.ai/models","output":131072,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"poolside/laguna-s-2.1","reasoning":true,"structured_output":false,"tool_call":true}],"open_weights":true,"output_price_per_million":0.18,"release_date":"2026-07-21","slug":"poolside/laguna-s-2.1","source":"Models.dev","source_url":"https://models.dev/models/poolside/laguna-s-2.1/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":30.2,"benchmark_data":[{"date":"2026-07-21","harness":"Antigravity","metric":"resolve rate","name":"SWE-Bench Pro","score":58.7,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/"},{"date":"2026-07-21","metric":"resolve rate","name":"DeepSWE","score":49,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/","variant":"high reasoning","version":"1.1"},{"date":"2026-07-21","harness":"Terminus 2","metric":"accuracy","name":"Terminal-Bench","score":78,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/","version":"2.1"},{"dataset":"Partial 30","date":"2026-07-21","metric":"average position score","name":"MLE-Bench","score":63.9,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/"},{"date":"2026-07-21","metric":"Elo","name":"GDPval-AA","score":1421,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/","version":"v2"},{"date":"2026-07-21","metric":"success rate","name":"OSWorld-Verified","score":83,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/"},{"date":"2026-07-21","metric":"accuracy","name":"CharXiv Reasoning","score":85.2,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/","variant":"no tools"},{"date":"2026-07-21","metric":"accuracy","name":"CharXiv Reasoning","score":89.4,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/","variant":"with tools"},{"date":"2026-07-21","metric":"accuracy","name":"GDM-MRCR","score":91.8,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/","variant":"128k average, 8-needle","version":"v2"},{"date":"2026-07-21","metric":"accuracy","name":"GDM-MRCR","score":54,"source":"https://deepmind.google/models/evals-methodology/gemini-3-6-flash/","variant":"1M pointwise, 8-needle","version":"v2"}],"cached_input_price_per_million":0.075,"coding_score":69.2,"confidence":"Medium","context_length":1048576,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","developer":"Google","input_price_per_million":0.75,"intelligence_score":34.3,"last_verified":"2026-09-11T13:08:12.749111","max_output_tokens":65536,"metadata":{"attachment":true,"family":"gemini-flash","knowledge":"2026-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Audio, Image, Pdf, Text, Video","name":"Gemini 3.6 Flash","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"output":3.75},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"google/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.impossibl.com/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"output":7.5},"doc":"https://impossibl.com/docs/models","output":65536,"provider":"Impossibl","provider_id":"impossibl","provider_model_id":"google/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"output":7.5},"doc":"https://docs.orcarouter.ai","output":65536,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"google/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":1048576,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":65536,"provider":"Kenari","provider_id":"kenari","provider_model_id":"gemini-3-6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"input_audio":0.75,"output":3.75},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","output":65536,"provider":"Vertex","provider_id":"google-vertex","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":1000000,"cost":{"cache_read":0.15,"cache_write":1.5,"input":1.5,"output":7.5},"doc":"https://agent.pioneer.ai/llms.txt","output":64000,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"output":7},"doc":"https://requesty.ai/solution/llm-routing/models","output":65535,"provider":"Requesty","provider_id":"requesty","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.75,"input":0.75,"output":3.75},"doc":"https://www.crossmodel.ai/docs","output":65536,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"gemini/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.075,"input":0.75,"input_audio":0.75,"output":3.75},"doc":"https://ai.google.dev/gemini-api/docs/models","output":65536,"provider":"Google","provider_id":"google","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":64000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"google/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.09375,"input":0.9375,"output":4.6875},"doc":"https://docs.venice.ai","output":65536,"provider":"Venice AI","provider_id":"venice","provider_model_id":"gemini-3-6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.08333,"input":0.75,"output":3.75},"doc":"https://llmgateway.io/docs","output":65536,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1000000,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"doc":"https://docs.github.com/en/copilot","output":64000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.0375,"cache_write":0.020833,"input":0.375,"output":1.875,"reasoning":1.875},"doc":"https://kilo.ai","output":65536,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"google/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"output":7.5},"doc":"https://docs.merge.dev/merge-gateway","output":65536,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"google/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"output":7.5},"doc":"https://abacus.ai/help/api","output":65536,"provider":"Abacus","provider_id":"abacus","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":7.5},"doc":"https://opencode.ai/docs/zen","output":65536,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"output":3.75,"reasoning":3.75},"doc":"https://openrouter.ai/models","output":65536,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"google/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.0415,"input":0.75,"input_audio":1.5,"output":3.75},"doc":"https://ofox.ai/docs","output":65536,"provider":"Ofox","provider_id":"ofox","provider_model_id":"google/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1048576,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":7.5},"doc":"https://neon.com/docs","output":65536,"provider":"Neon","provider_id":"neon","provider_model_id":"gemini-3-6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1048576,"cost":{"input":1.5,"output":7.5},"doc":"https://doc.302.ai","output":65536,"provider":"302.AI","provider_id":"302ai","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.038,"input":0.75,"output":3.75},"doc":"https://api.cortecs.ai/v1/models","output":65535,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1048576,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"doc":"https://docs.edenai.co","output":65536,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"google/gemini-3.6-flash","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":3.75,"release_date":"2026-07-21","slug":"google/gemini-3.6-flash","source":"Models.dev","source_url":"https://models.dev/models/google/gemini-3.6-flash/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.03,"coding_score":0.0,"confidence":"Medium","context_length":1048576,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","developer":"Google","input_price_per_million":0.3,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:13.093180","max_output_tokens":65536,"metadata":{"attachment":true,"family":"gemini-flash-lite","knowledge":"2026-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Audio, Image, Pdf, Text, Video","name":"Gemini Flash-Lite Latest","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.03,"cache_write":0.08333,"input":0.3,"output":2.5},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"google/gemini-flash-lite-latest","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1048576,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"output":1.5},"doc":"https://docs.orcarouter.ai","output":65536,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"google/gemini-flash-lite-latest","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"output":1.5},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","output":65536,"provider":"Vertex","provider_id":"google-vertex","provider_model_id":"gemini-flash-lite-latest","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://ai.google.dev/gemini-api/docs/models","output":65536,"provider":"Google","provider_id":"google","provider_model_id":"gemini-flash-lite-latest","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1048576,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"output":1.5},"doc":"https://docs.merge.dev/merge-gateway","output":65536,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"google/gemini-flash-lite-latest","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":2.5,"release_date":"2026-07-21","slug":"google/gemini-flash-lite-latest","source":"Models.dev","source_url":"https://models.dev/models/google/gemini-flash-lite-latest/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":15.9,"benchmark_data":[{"date":"2026-07-21","metric":"resolve rate","name":"SWE-Bench Pro","score":54.2,"source":"https://deepmind.google/models/model-cards/gemini-3-5-flash-lite/"},{"date":"2026-07-21","harness":"Terminus 2","metric":"accuracy","name":"Terminal-Bench","score":54,"source":"https://deepmind.google/models/model-cards/gemini-3-5-flash-lite/","version":"2.1"},{"date":"2026-07-21","metric":"average position score","name":"MLE-Bench","score":39.2,"source":"https://deepmind.google/models/model-cards/gemini-3-5-flash-lite/"},{"date":"2026-07-21","metric":"Elo","name":"GDPval-AA","score":1140,"source":"https://deepmind.google/models/model-cards/gemini-3-5-flash-lite/","version":"v2"},{"date":"2026-07-21","metric":"success rate","name":"OSWorld-Verified","score":74,"source":"https://deepmind.google/models/model-cards/gemini-3-5-flash-lite/"},{"date":"2026-07-21","metric":"accuracy","name":"CharXiv Reasoning","score":74.5,"source":"https://deepmind.google/models/model-cards/gemini-3-5-flash-lite/","variant":"no tools"},{"date":"2026-07-21","metric":"accuracy","name":"CharXiv Reasoning","score":76.5,"source":"https://deepmind.google/models/model-cards/gemini-3-5-flash-lite/","variant":"with tools"},{"date":"2026-07-21","metric":"accuracy","name":"GDM-MRCR","score":72.2,"source":"https://deepmind.google/models/model-cards/gemini-3-5-flash-lite/","variant":"128k average, 8-needle","version":"v2"},{"date":"2026-07-21","metric":"accuracy","name":"GDM-MRCR","score":21.3,"source":"https://deepmind.google/models/model-cards/gemini-3-5-flash-lite/","variant":"1M pointwise, 8-needle","version":"v2"}],"cached_input_price_per_million":0.03,"coding_score":49.3,"confidence":"Medium","context_length":1048576,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","developer":"Google","input_price_per_million":0.3,"intelligence_score":22.7,"last_verified":"2026-09-11T13:08:13.005239","max_output_tokens":65536,"metadata":{"attachment":true,"family":"gemini-flash-lite","knowledge":"2026-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Audio, Image, Pdf, Text, Video","name":"Gemini 3.5 Flash Lite","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.03,"cache_write":0.08333,"input":0.3,"output":2.5},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"google/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.impossibl.com/v1","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://impossibl.com/docs/models","output":65536,"provider":"Impossibl","provider_id":"impossibl","provider_model_id":"google/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://docs.orcarouter.ai","output":65536,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"google/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{},"doc":"https://help.sap.com/docs/sap-ai-core","output":65536,"provider":"SAP AI Core","provider_id":"sap-ai-core","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","output":65536,"provider":"Vertex","provider_id":"google-vertex","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":1000000,"cost":{"cache_read":0.03,"cache_write":0.3,"input":0.3,"output":2.5},"doc":"https://agent.pioneer.ai/llms.txt","output":65000,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://requesty.ai/solution/llm-routing/models","output":65535,"provider":"Requesty","provider_id":"requesty","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1048576,"cost":{"cache_read":0.03,"cache_write":0.3,"input":0.3,"output":2.5},"doc":"https://www.crossmodel.ai/docs","output":65536,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"gemini/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://ai.google.dev/gemini-api/docs/models","output":65536,"provider":"Google","provider_id":"google","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":65000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"google/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.03,"cache_write":0.08333,"input":0.3,"output":2.5},"doc":"https://llmgateway.io/docs","output":65536,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://opper.ai/models","output":65536,"provider":"Opper","provider_id":"opper","provider_model_id":"gemini/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.015,"cache_write":0.041667,"input":0.15,"output":1.25,"reasoning":1.25},"doc":"https://kilo.ai","output":65536,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"google/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://docs.merge.dev/merge-gateway","output":65536,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"google/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://abacus.ai/help/api","output":65536,"provider":"Abacus","provider_id":"abacus","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://opencode.ai/docs/zen","output":65536,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"output":2.5,"reasoning":2.5},"doc":"https://openrouter.ai/models","output":65536,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"google/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1048576,"cost":{"cache_read":0.03,"cache_write":0.083,"input":0.3,"output":2.5},"doc":"https://ofox.ai/docs","output":65536,"provider":"Ofox","provider_id":"ofox","provider_model_id":"google/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1048576,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"doc":"https://neon.com/docs","output":65536,"provider":"Neon","provider_id":"neon","provider_model_id":"gemini-3-5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1048576,"cost":{"input":0.3,"output":2.5},"doc":"https://doc.302.ai","output":65536,"provider":"302.AI","provider_id":"302ai","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1048576,"cost":{"cache_read":0.033,"input":0.33,"output":2.749},"doc":"https://api.cortecs.ai/v1/models","output":65535,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1048576,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"input_audio":0.3,"output":2.5,"reasoning":2.5},"doc":"https://docs.edenai.co","output":65536,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"google/gemini-3.5-flash-lite","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":2.5,"release_date":"2026-07-21","slug":"google/gemini-3.5-flash-lite","source":"Models.dev","source_url":"https://models.dev/models/google/gemini-3.5-flash-lite/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[{"date":"2026-08-03","metric":"accuracy","name":"Terminal-Bench","score":86.6,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh","version":"2.1"},{"date":"2026-08-03","harness":"Claude Code","metric":"resolve rate","name":"SWE-Bench Pro","score":67.7,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"date":"2026-08-03","harness":"Claude Code","metric":"resolve rate","name":"DeepSWE","score":56.6,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh","version":"1.1"},{"date":"2026-08-03","harness":"Claude Code","metric":"resolve rate","name":"NL2Repo","score":55.9,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"date":"2026-08-03","harness":"Claude Code","metric":"dominance score","name":"FrontierSWE","score":73.5,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"date":"2026-08-03","harness":"Claude Code","metric":"score","name":"MLS-Bench-Lite","score":41,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"dataset":"600-task public subset","date":"2026-08-03","metric":"pass@1","name":"AutomationBench","score":27.3,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"date":"2026-08-03","metric":"pass@1","name":"Toolathlon Verified","score":72.5,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"date":"2026-08-03","metric":"F1","name":"WideSearch","score":81.9,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"date":"2026-08-03","metric":"accuracy","name":"Humanity's Last Exam","score":56.2,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh, with tools"},{"date":"2026-08-03","metric":"accuracy","name":"GPQA Diamond","score":92.6,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"date":"2026-08-03","metric":"accuracy","name":"Humanity's Last Exam","score":43.6,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh, no tools"},{"date":"2026-08-03","metric":"score","name":"IFBench","score":82.8,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"date":"2026-08-03","metric":"success rate","name":"OSWorld-Verified","score":86.1,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"},{"date":"2026-08-03","metric":"accuracy","name":"MMMU Pro","score":82.3,"source":"https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421","variant":"xhigh"}],"cached_input_price_per_million":0.25,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","developer":"Alibaba Qwen","input_price_per_million":2.0,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:09.875637","max_output_tokens":131072,"metadata":{"attachment":true,"family":"qwen","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"reasoning":true,"temperature":true,"tool_call":true},"modalities":"Image, Text, Video","name":"Qwen3.8 Max Preview","offerings":[{"api":"https://api.impossibl.com/v1","context":1000000,"cost":{"input":2.5,"output":7.5},"doc":"https://impossibl.com/docs/models","output":131072,"provider":"Impossibl","provider_id":"impossibl","provider_model_id":"qwen/qwen3.8-max-preview","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/en/model-studio/token-plan-overview","output":131072,"provider":"Alibaba Token Plan","provider_id":"alibaba-token-plan","provider_model_id":"qwen3.8-max-preview","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1000000,"cost":{"cache_read":0.25,"input":2,"output":6},"doc":"https://hyper.charm.land","output":65536,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1000000,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"doc":"https://llmgateway.io/docs","output":1000000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"qwen3.8-max","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview","output":131072,"provider":"Alibaba Token Plan (China)","provider_id":"alibaba-token-plan-cn","provider_model_id":"qwen3.8-max-preview","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":6.0,"release_date":"2026-07-19","slug":"alibaba/qwen3.8-max-preview","source":"Models.dev","source_url":"https://models.dev/models/alibaba/qwen3.8-max-preview/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":50.6,"benchmark_data":[{"date":"2026-07-16","harness":"Kimi Code","metric":"resolve rate","name":"DeepSWE","score":67.5,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort","version":"1.1"},{"date":"2026-07-16","harness":"Kimi Code","metric":"accuracy","name":"Terminal-Bench","score":88.3,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort","version":"2.1"},{"date":"2026-07-16","harness":"Kimi Code","metric":"dominance score","name":"FrontierSWE","score":81.2,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort"},{"date":"2026-07-16","harness":"Kimi Code","metric":"score","name":"Program Bench","score":77.8,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort"},{"date":"2026-07-16","harness":"Claude Code","metric":"resolve rate","name":"SWE Marathon","score":42,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort","version":"1.1"},{"date":"2026-07-16","metric":"Elo","name":"GDPval-AA","score":1668,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort","version":"v2"},{"date":"2026-07-16","metric":"Elo","name":"AA-Briefcase","score":1548,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort"},{"dataset":"600-task public subset","date":"2026-07-16","metric":"success rate","name":"AutomationBench","score":30.8,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort"},{"date":"2026-07-16","metric":"score","name":"JobBench","score":52.9,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort"},{"date":"2026-07-16","harness":"Claude Code","metric":"score","name":"SpreadsheetBench","score":34.8,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort","version":"2"},{"date":"2026-07-16","metric":"accuracy","name":"BrowseComp","score":91.2,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort, context compaction"},{"date":"2026-07-16","metric":"accuracy","name":"CharXiv Reasoning","score":91.3,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort, with tools"},{"date":"2026-07-16","metric":"pass@5","name":"ZeroBench","score":41,"source":"https://www.kimi.com/blog/kimi-k3","variant":"max effort, with tools"}],"cached_input_price_per_million":0.3,"coding_score":76.2,"confidence":"Medium","context_length":1048576,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","developer":"Moonshot AI","input_price_per_million":3.0,"intelligence_score":43.8,"last_verified":"2026-09-11T13:08:17.977179","max_output_tokens":131072,"metadata":{"attachment":true,"family":"kimi-k3","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":true,"temperature":false,"tool_call":true},"modalities":"Image, Text, Video","name":"Kimi K3","offerings":[{"api":"https://api.tokengo.com/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://www.tokengo.com/docs","output":131072,"provider":"TokenGo","provider_id":"tokengo","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.greenpt.ai/v1","context":1048576,"cost":{"cache_read":0.9405,"input":3.762,"output":18.81},"doc":"https://docs.greenpt.ai","output":131072,"provider":"GreenPT","provider_id":"greenpt","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://nano-gpt.com/api/v1","context":1048576,"cost":{"cache_read":0.2,"input":2,"output":10},"doc":"https://docs.nano-gpt.com","output":943718,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.do-ai.run/v1","context":1048576,"cost":{"cache_read":0.285,"input":2.55,"output":12.95},"doc":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","output":131072,"provider":"DigitalOcean","provider_id":"digitalocean","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.vivgrid.com/v1","context":1000000,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://docs.vivgrid.com/models","output":131072,"provider":"Vivgrid","provider_id":"vivgrid","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.impossibl.com/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://impossibl.com/docs/models","output":131072,"provider":"Impossibl","provider_id":"impossibl","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.neuralwatt.com/v1","context":1048560,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://portal.neuralwatt.com/docs","output":1048560,"provider":"Neuralwatt","provider_id":"neuralwatt","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://docs.aihubmix.com","output":131072,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://token.sensenova.cn/v1","context":1048576,"cost":{"cache_read":0,"input":0,"output":0},"doc":"https://platform.sensenova.cn/docs","output":65536,"provider":"SenseNova (China)","provider_id":"sensenova","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1048576,"cost":{"cache_read":0.33,"input":3.3,"output":16.5},"doc":"https://docs.orcarouter.ai","output":131072,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"kimi/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":1048576,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":131072,"provider":"Kenari","provider_id":"kenari","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.novita.ai/openai","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://novita.ai/docs/guides/introduction","output":1048576,"provider":"NovitaAI","provider_id":"novita-ai","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.tokenfactory.nebius.com/v1","context":1048576,"cost":{"cache_read":3,"input":3,"output":15},"doc":"https://docs.tokenfactory.nebius.com/","output":8000,"provider":"Nebius Token Factory","provider_id":"nebius","provider_model_id":"moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":1000000,"cost":{"cache_read":0.3,"cache_write":3,"input":3,"output":15},"doc":"https://agent.pioneer.ai/llms.txt","output":131072,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.coralbricks.ai/v1","context":1048576,"cost":{"cache_read":0,"input":3,"output":15},"doc":"https://www.coralbricks.ai/docs","output":131072,"provider":"CoralBricks","provider_id":"coralbricks","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1048576,"cost":{"cache_read":0.32664,"input":3.2664,"output":16.332},"doc":"https://hyper.charm.land","output":16000,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1048576,"cost":{"cache_read":0.45,"input":3,"output":15},"doc":"https://requesty.ai/solution/llm-routing/models","output":262144,"provider":"Requesty","provider_id":"requesty","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":1000000,"cost":{"input":3,"output":15},"doc":"https://huggingface.co/docs/inference-providers","output":131072,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1048576,"cost":{"cache_read":0.3,"cache_write":3,"input":3,"output":15},"doc":"https://www.crossmodel.ai/docs","output":1048576,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"moonshot/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://integrate.api.nvidia.com/v1","context":1048576,"cost":{"input":0,"output":0},"doc":"https://docs.api.nvidia.com/nim/","output":131072,"provider":"Nvidia","provider_id":"nvidia","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.baseten.co/v1","context":1048576,"cost":{"input":3,"output":15},"doc":"https://docs.baseten.co/inference/model-apis/overview","output":262144,"provider":"Baseten","provider_id":"baseten","provider_model_id":"moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":131072,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.tensorx.ai/v1","context":1048576,"cost":{"cache_read":0.75,"input":3,"output":15},"doc":"https://docs.tensorx.ai/","output":131072,"provider":"TensorX","provider_id":"tensorx","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.375,"input":3.75,"output":18.75},"doc":"https://docs.venice.ai","output":131072,"provider":"Venice AI","provider_id":"venice","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://llmgateway.io/docs","output":131072,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1040384,"cost":{"cache_read":0.45,"input":4.5,"output":22.5},"doc":"https://llmgateway.io/docs","output":131072,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"kimi-k3-fast","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://developers.cloudflare.com/ai-gateway/","output":131072,"provider":"Cloudflare AI Gateway","provider_id":"cloudflare-ai-gateway","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://docs.github.com/en/copilot","output":131072,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.jalapeno-cloud.ai/v1","context":1048576,"cost":{"input":3,"output":15},"doc":"https://www.jalapeno-cloud.ai/docs/","output":131072,"provider":"Jalapeno Cloud","provider_id":"jalapeno","provider_model_id":"Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.perplexity.ai/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://docs.perplexity.ai/docs/agent-api/models","output":131072,"provider":"Perplexity Agent","provider_id":"perplexity-agent","provider_model_id":"moonshot-ai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://fireworks.ai/docs/","output":131072,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://opper.ai/models","output":131072,"provider":"Opper","provider_id":"opper","provider_model_id":"moonshot/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://crof.ai/v1","context":1000000,"cost":{"cache_read":0.25,"input":2,"output":8},"doc":"https://crof.ai/docs","output":262144,"provider":"CrofAI","provider_id":"crof","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":1000000,"cost":{"cache_read":3,"input":3,"output":15},"doc":"https://docs.empiriolabs.ai","output":131072,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.code.umans.ai/v1","context":1048576,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://app.umans.ai/offers/code/docs","output":131072,"provider":"Umans AI Coding Plan","provider_id":"umans-ai-coding-plan","provider_model_id":"umans-kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.us-west.modal.direct/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15,"reasoning":15},"doc":"https://modal.com/docs/guide/endpoints","output":131072,"provider":"Modal","provider_id":"modal","provider_model_id":"moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.code.umans.ai/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://app.umans.ai/offers/code/docs/orgs","output":131072,"provider":"Umans AI","provider_id":"umans-ai","provider_model_id":"umans-kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.285,"input":2.85,"output":14.25},"doc":"https://deepinfra.com/models","output":131072,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://kilo.ai","output":943718,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1048576,"cost":{"cache_read":0.3,"input":2.9,"output":14},"doc":"https://docs.merge.dev/merge-gateway","output":1048576,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"moonshot/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://abacus.ai/help/api","output":131072,"provider":"Abacus","provider_id":"abacus","provider_model_id":"moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://opencode.ai/docs/zen","output":131072,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.moonshot.cn/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://platform.moonshot.cn/docs/api/chat","output":131072,"provider":"Moonshot AI (China)","provider_id":"moonshotai-cn","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.261,"input":2.34,"output":11.7},"doc":"https://openrouter.ai/models","output":943718,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cline.bot/api/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://docs.cline.bot/getting-started/clinepass","output":131072,"provider":"ClinePass","provider_id":"cline-pass","provider_model_id":"cline-pass/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://ofox.ai/docs","output":131072,"provider":"Ofox","provider_id":"ofox","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.arcee.ai/api/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://docs.arcee.ai","output":131072,"provider":"Arcee","provider_id":"arcee","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://neon.com/docs","output":65536,"provider":"Neon","provider_id":"neon","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.scnet.cn/api/llm/v1","context":1048576,"cost":{"cache_read":0,"input":0,"output":0},"doc":"https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html","output":131072,"provider":"SCNet Token Plan","provider_id":"scnet-token-plan","provider_model_id":"Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.aiand.com/v1","context":1048576,"cost":{"cache_read":0.5,"input":3,"output":12.5},"doc":"https://docs.aiand.com/","output":131072,"provider":"ai&","provider_id":"aiand","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.moonshot.ai/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://platform.moonshot.ai/docs/api/chat","output":131072,"provider":"Moonshot AI","provider_id":"moonshotai","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1048576,"cost":{"input":3,"output":15},"doc":"https://doc.302.ai","output":131072,"provider":"302.AI","provider_id":"302ai","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.berget.ai/v1","context":327680,"cost":{"input":3,"output":15},"doc":"https://api.berget.ai","output":32768,"provider":"Berget.AI","provider_id":"berget","provider_model_id":"moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.synthetic.new/openai/v1","context":524288,"cost":{"cache_read":0.45,"input":3,"output":15},"doc":"https://synthetic.new/pricing","output":65536,"provider":"Synthetic","provider_id":"synthetic","provider_model_id":"hf:moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://docs.together.ai/docs/serverless-models","output":131072,"provider":"Together AI","provider_id":"togetherai","provider_model_id":"moonshotai/Kimi-K3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://zenmux.ai/api/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://docs.zenmux.ai","output":131072,"provider":"ZenMux","provider_id":"zenmux","provider_model_id":"moonshotai/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://vancine.com/v1","context":1048576,"cost":{"cache_read":0.24,"input":2.4,"output":12},"doc":"https://vancine.com/docs","output":131072,"provider":"Vancine","provider_id":"vancine","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1048576,"cost":{"input":3,"output":14.999},"doc":"https://api.cortecs.ai/v1/models","output":1048576,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kimi.com/coding/v1","context":1048576,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://www.kimi.com/code/docs/en/kimi-code/models.html","output":131072,"provider":"Kimi For Coding","provider_id":"kimi-for-coding","provider_model_id":"k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://opencode.ai/docs/zen","output":131072,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://inference.tinfoil.sh/v1","context":262144,"cost":{"cache_read":0.8,"input":4,"output":20},"doc":"https://docs.tinfoil.sh","output":131072,"provider":"Tinfoil","provider_id":"tinfoil","provider_model_id":"kimi-k3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1048576,"cost":{"cache_read":0.3,"input":3,"output":15},"doc":"https://docs.edenai.co","output":131072,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"moonshot/kimi-k3","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":15.0,"release_date":"2026-07-16","slug":"moonshotai/kimi-k3","source":"Models.dev","source_url":"https://models.dev/models/moonshotai/kimi-k3/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":24.3,"benchmark_data":[],"cached_input_price_per_million":0.374,"coding_score":52.1,"confidence":"Medium","context_length":1048576,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","developer":"Thinkingmachines","input_price_per_million":1.87,"intelligence_score":25.5,"last_verified":"2026-09-11T13:08:13.468874","max_output_tokens":1048576,"metadata":{"attachment":true,"family":"ling","license":"Apache-2.0","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"reasoning":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/thinkingmachines/Inkling"}]},"modalities":"Audio, Image, Text","name":"Inkling","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1048000,"cost":{"cache_read":0.17,"input":1,"output":4.05},"doc":"https://docs.nano-gpt.com","output":32768,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"thinkingmachines/inkling","reasoning":false,"structured_output":true,"tool_call":true},{"api":"https://api.impossibl.com/v1","context":65536,"cost":{"cache_read":0.374,"input":1.87,"output":4.68},"doc":"https://impossibl.com/docs/models","output":65536,"provider":"Impossibl","provider_id":"impossibl","provider_model_id":"thinkingmachines/inkling","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1048576,"cost":{"cache_read":0.185096,"input":1.0888,"output":4.40964},"doc":"https://hyper.charm.land","output":32768,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"inkling","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":65536,"cost":{"cache_read":0.374,"input":1.87,"output":4.68},"doc":"https://requesty.ai/solution/llm-routing/models","output":32768,"provider":"Requesty","provider_id":"requesty","provider_model_id":"inkling","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://llmtr.com/v1","context":262144,"cost":{"input":1.87,"output":4.68},"doc":"https://llmtr.com/docs","output":262144,"provider":"LLMTR","provider_id":"llmtr","provider_model_id":"thinkingmachines/inkling","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":1048576,"cost":{"input":1,"output":4.05},"doc":"https://huggingface.co/docs/inference-providers","output":1048576,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"thinkingmachines/Inkling","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://integrate.api.nvidia.com/v1","context":1048576,"cost":{"input":0,"output":0},"doc":"https://docs.api.nvidia.com/nim/","output":16384,"provider":"Nvidia","provider_id":"nvidia","provider_model_id":"thinkingmachines/inkling","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://inference.baseten.co/v1","context":1048576,"cost":{"input":1,"output":4.05},"doc":"https://docs.baseten.co/inference/model-apis/overview","output":32768,"provider":"Baseten","provider_id":"baseten","provider_model_id":"thinkingmachines/inkling","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":256000,"cost":{"cache_read":0.17,"input":1,"output":4.05},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":256000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"thinkingmachines/inkling","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://tinker.thinkingmachines.dev/services/tinker-prod/anthropic/api/v1","context":65536,"cost":{"cache_read":0.374,"input":1.87,"output":4.68},"doc":"https://tinker-docs.thinkingmachines.ai/tinker/compatible-apis/anthropic/","output":65536,"provider":"Thinking Machines","provider_id":"thinkingmachines","provider_model_id":"thinkingmachines/Inkling","reasoning":true,"structured_output":null,"tool_call":true},{"api":"","context":524288,"cost":{"cache_read":0.2125,"input":1.25,"output":5.0625},"doc":"https://docs.venice.ai","output":65536,"provider":"Venice AI","provider_id":"venice","provider_model_id":"inkling","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.fireworks.ai/inference/v1/","context":1048576,"cost":{"cache_read":0.17,"input":1,"output":4.05},"doc":"https://fireworks.ai/docs/","output":1048576,"provider":"Fireworks AI","provider_id":"fireworks-ai","provider_model_id":"accounts/fireworks/models/inkling","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://inference.us-west.modal.direct/v1","context":1048576,"cost":{"cache_read":0.27,"input":1.2,"output":5},"doc":"https://modal.com/docs/guide/endpoints","output":262144,"provider":"Modal","provider_id":"modal","provider_model_id":"thinkingmachines/Inkling-NVFP4","reasoning":true,"structured_output":false,"tool_call":true},{"api":"","context":524288,"cost":{"cache_read":0.16,"input":0.95,"output":4.05},"doc":"https://deepinfra.com/models","output":1048576,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"thinkingmachines/Inkling","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1048576,"cost":{"cache_read":0.16,"input":0.95,"output":4.05},"doc":"https://kilo.ai","output":32768,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"thinkingmachines/inkling","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1048000,"cost":{"cache_read":0.17,"input":1,"output":4.05},"doc":"https://docs.merge.dev/merge-gateway","output":32000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"thinkingmachines/inkling","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":262144,"cost":{"cache_read":0.748,"input":3.74,"output":9.36},"doc":"https://abacus.ai/help/api","output":131072,"provider":"Abacus","provider_id":"abacus","provider_model_id":"thinkingmachines/Inkling","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1048576,"cost":{"cache_read":0.17,"input":1,"output":4.05},"doc":"https://openrouter.ai/models","output":32768,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"thinkingmachines/inkling","reasoning":true,"structured_output":false,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1048576,"cost":{"cache_read":0.17,"input":1,"output":4.05},"doc":"https://neon.com/docs","output":65536,"provider":"Neon","provider_id":"neon","provider_model_id":"inkling","reasoning":true,"structured_output":false,"tool_call":true},{"api":"","context":524288,"cost":{"cache_read":0.17,"input":1,"output":4.05},"doc":"https://docs.together.ai/docs/serverless-models","output":131072,"provider":"Together AI","provider_id":"togetherai","provider_model_id":"thinkingmachines/Inkling","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":true,"output_price_per_million":4.68,"release_date":"2026-07-15","slug":"thinkingmachines/inkling","source":"Models.dev","source_url":"https://models.dev/models/thinkingmachines/inkling/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.00564,"coding_score":0.0,"confidence":"Medium","context_length":1000000,"description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","developer":"Alibaba Qwen","input_price_per_million":0.0282,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:10.498838","max_output_tokens":65536,"metadata":{"attachment":true,"family":"qwen","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Image, Text, Video","name":"Qwen3.7 Flash","offerings":[{"api":"https://nano-gpt.com/api/v1","context":991808,"cost":{"cache_read":0.006,"cache_write":0.038,"input":0.03,"output":0.13},"doc":"https://docs.nano-gpt.com","output":65536,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"qwen3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1000000,"cost":{"cache_read":0.006,"cache_write":0.0375,"input":0.03,"output":0.13},"doc":"https://llmgateway.io/docs","output":65536,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"alibaba/qwen3.7-flash","reasoning":true,"structured_output":false,"tool_call":true},{"api":"","context":991000,"cost":{"cache_read":0.00564,"cache_write":0.03525,"input":0.0282,"output":0.1128},"doc":"https://docs.aihubmix.com","output":64000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"qwen3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1000000,"cost":{"cache_read":0.006,"cache_write":0.038,"input":0.03,"output":0.13},"doc":"https://docs.orcarouter.ai","output":65536,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"qwen/qwen3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://dashscope.aliyuncs.com/compatible-mode/v1","context":1000000,"cost":{"cache_read":0.002962,"cache_write":0.03703,"input":0.02962,"output":0.1185,"tiers":[{"cache_read":0.008887,"cache_write":0.11109,"input":0.08887,"output":0.35549,"tier":{"size":32000,"type":"context"}},{"cache_read":0.017774,"cache_write":0.22218,"input":0.17774,"output":0.71098,"tier":{"size":256000,"type":"context"}}]},"doc":"https://www.alibabacloud.com/help/en/model-studio/models","output":65536,"provider":"Alibaba (China)","provider_id":"alibaba-cn","provider_model_id":"qwen3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://hyper.charm.land/v1","context":1000000,"cost":{"cache_read":0.04,"input":0.2,"output":0.8},"doc":"https://hyper.charm.land","output":64000,"provider":"Charm Hyper","provider_id":"hyper","provider_model_id":"qwen3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1000000,"cost":{"cache_read":0.01,"cache_write":0.04,"input":0.04,"output":0.13,"tiers":[{"cache_read":0.02,"cache_write":0.12,"input":0.1,"output":0.37,"tier":{"size":32000,"type":"context"}},{"cache_read":0.04,"cache_write":0.24,"input":0.19,"output":0.74,"tier":{"size":256000,"type":"context"}}]},"doc":"https://www.crossmodel.ai/docs","output":65536,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"qwen/qwen3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":991000,"cost":{"cache_read":0.006,"cache_write":0.038,"input":0.03,"output":0.13},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":64000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"alibaba/qwen3.7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.empiriolabs.ai/v1","context":1000000,"cost":{"cache_read":0.006,"input":0.03,"output":0.13,"tiers":[{"cache_read":0.02,"input":0.1,"output":0.4,"tier":{"size":32000,"type":"context"}},{"cache_read":0.04,"input":0.2,"output":0.8,"tier":{"size":256000,"type":"context"}}]},"doc":"https://docs.empiriolabs.ai","output":65536,"provider":"EmpirioLabs AI","provider_id":"empiriolabs","provider_model_id":"qwen3-7-flash","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1000000,"cost":{"cache_read":0.006,"cache_write":0.038,"input":0.03,"output":0.13},"doc":"https://kilo.ai","output":65536,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"qwen/qwen3.7-flash","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1000000,"cost":{"cache_read":0.006,"cache_write":0.038,"input":0.03,"output":0.13,"tiers":[{"cache_read":0.02,"cache_write":0.125,"input":0.1,"output":0.4,"tier":{"size":32000,"type":"context"}},{"cache_read":0.04,"cache_write":0.25,"input":0.2,"output":0.8,"tier":{"size":256000,"type":"context"}}]},"doc":"https://openrouter.ai/models","output":65536,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"qwen/qwen3.7-flash","reasoning":true,"structured_output":false,"tool_call":true}],"open_weights":false,"output_price_per_million":0.1128,"release_date":"2026-07-15","slug":"alibaba/qwen3.7-flash","source":"Models.dev","source_url":"https://models.dev/models/alibaba/qwen3.7-flash/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":42.7,"benchmark_data":[{"date":"2026-07-09","metric":"resolve rate","name":"SWE-Bench Pro","score":62.7,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"success rate","name":"Terminal-Bench","score":84.7,"source":"https://openai.com/index/gpt-5-6/","version":"2.1"},{"date":"2026-07-09","metric":"resolve rate","name":"DeepSWE","score":67.2,"source":"https://openai.com/index/gpt-5-6/","version":"1.1"},{"date":"2026-07-09","metric":"accuracy","name":"GPQA Diamond","score":92.3,"source":"https://openai.com/index/gpt-5-6/"},{"dataset":"Tier 1-3","date":"2026-07-09","metric":"accuracy","name":"FrontierMath","score":78.6,"source":"https://openai.com/index/gpt-5-6/","version":"v2"},{"date":"2026-07-09","metric":"accuracy","name":"BrowseComp","score":83.3,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"success rate","name":"OSWorld","score":45.6,"source":"https://openai.com/index/gpt-5-6/","version":"2.0"},{"date":"2026-07-09","metric":"accuracy","name":"MMMU Pro","score":78.4,"source":"https://openai.com/index/gpt-5-6/","variant":"no tools"},{"date":"2026-07-09","name":"Agents' Last Exam","score":50.3,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"success rate","name":"Toolathlon","score":53.4,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"index score","name":"Artificial Analysis Intelligence Index","score":51.2,"source":"https://artificialanalysis.ai/articles/gpt-5-6-has-landed","variant":"max","version":"4.1"},{"date":"2026-07-09","harness":"Codex","metric":"index score","name":"Artificial Analysis Coding Agent Index","score":74.6,"source":"https://artificialanalysis.ai/articles/gpt-5-6-has-landed","variant":"max","version":"1.1"}],"cached_input_price_per_million":0.02,"coding_score":71.4,"confidence":"Medium","context_length":1050000,"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","developer":"OpenAI","input_price_per_million":0.2,"intelligence_score":37.5,"last_verified":"2026-09-11T13:08:16.340587","max_output_tokens":128000,"metadata":{"attachment":true,"family":"gpt-luna","knowledge":"2026-02-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":false,"tool_call":true},"modalities":"Image, Pdf, Text","name":"GPT-5.6 Luna","offerings":[{"api":"https://openai.bothub.ru/v1","context":1050000,"cost":{"input":0.06,"output":0.37},"doc":"https://bothub.ru/models","output":128000,"provider":"Bothub","provider_id":"bothub","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://nano-gpt.com/api/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://docs.nano-gpt.com","output":128000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.impossibl.com/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://impossibl.com/docs/models","output":128000,"provider":"Impossibl","provider_id":"impossibl","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://llmgateway.io/docs","output":128000,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":6},"doc":"https://docs.aihubmix.com","output":128000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://docs.orcarouter.ai","output":128000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.routing.run/v1","context":1000000,"cost":{"input":0.7,"output":4.2},"doc":"https://docs.routing.run/api-reference/models","output":128000,"provider":"routing.run","provider_id":"routing-run","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.1,"cache_write":1.25,"context_over_200k":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":9},"input":1,"output":6,"tiers":[{"cache_read":0.2,"cache_write":2.5,"input":2,"output":9,"tier":{"size":272000,"type":"context"}}]},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure Cognitive Services","provider_id":"azure-cognitive-services","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":1050000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":128000,"provider":"Kenari","provider_id":"kenari","provider_model_id":"gpt-5-6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":1050000,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":6},"doc":"https://agent.pioneer.ai/llms.txt","output":128000,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1050000,"cost":{"cache_read":0.02,"context_over_200k":{"cache_read":0.04,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://requesty.ai/solution/llm-routing/models","output":128000,"provider":"Requesty","provider_id":"requesty","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://www.crossmodel.ai/docs","output":128000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.025,"cache_write":0.3125,"context_over_200k":{"cache_read":0.05,"cache_write":0.625,"input":0.5,"output":2.25},"input":0.25,"output":1.5,"tiers":[{"cache_read":0.05,"cache_write":0.625,"input":0.5,"output":2.25,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.venice.ai","output":128000,"provider":"Venice AI","provider_id":"venice","provider_model_id":"openai-gpt-56-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://llmgateway.io/docs","output":128000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://developers.cloudflare.com/ai-gateway/","output":128000,"provider":"Cloudflare AI Gateway","provider_id":"cloudflare-ai-gateway","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.github.com/en/copilot","output":128000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://opper.ai/models","output":128000,"provider":"Opper","provider_id":"opper","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1","context":400000,"cost":{"cache_read":0.1,"context_over_200k":{"cache_read":0.2,"input":2,"output":9},"input":1,"output":6,"tiers":[{"cache_read":0.2,"input":2,"output":9,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.databricks.com/aws/en/machine-learning/foundation-models/","output":128000,"provider":"Databricks","provider_id":"databricks","provider_model_id":"databricks-gpt-5-6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"openai/gpt-5.6-luna-pro","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure","provider_id":"azure","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.022,"cache_write":0.275,"context_over_200k":{"cache_read":0.044,"cache_write":0.55,"input":0.44,"output":1.98},"input":0.22,"output":1.32,"tiers":[{"cache_read":0.044,"cache_write":0.55,"input":0.44,"output":1.98,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","output":128000,"provider":"Amazon Bedrock","provider_id":"amazon-bedrock","provider_model_id":"openai.gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://docs.merge.dev/merge-gateway","output":128000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1000000,"cost":{"cache_read":0.1,"input":1,"output":6},"doc":"https://abacus.ai/help/api","output":128000,"provider":"Abacus","provider_id":"abacus","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://opencode.ai/docs/zen","output":128000,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://openrouter.ai/models","output":128000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"doc":"https://ofox.ai/docs","output":128000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://neon.com/docs","output":128000,"provider":"Neon","provider_id":"neon","provider_model_id":"gpt-5-6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://platform.openai.com/docs/models","output":128000,"provider":"OpenAI","provider_id":"openai","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1","context":1050000,"cost":{},"doc":"https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api","output":128000,"provider":"Snowflake Cortex","provider_id":"snowflake-cortex","provider_model_id":"openai-gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1050000,"cost":{"input":0.2,"output":1.2},"doc":"https://doc.302.ai","output":128000,"provider":"302.AI","provider_id":"302ai","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ai-router.dev/v1","context":1050000,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":6},"doc":"https://ai-router.dev/openai-compatible-api-gateway/","output":128000,"provider":"AI-ROUTER","provider_id":"ai-router","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://zenmux.ai/api/v1","context":1050000,"cost":{"cache_read":0.1,"cache_write":1.25,"context_over_200k":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":9},"input":1,"output":6,"tiers":[{"cache_read":0.2,"cache_write":2.5,"input":2,"output":9,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.zenmux.ai","output":128000,"provider":"ZenMux","provider_id":"zenmux","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1050000,"cost":{"cache_read":0.022,"cache_write":0.275,"input":0.219,"output":1.32},"doc":"https://api.cortecs.ai/v1/models","output":128000,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://opencode.ai/docs/zen","output":128000,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1050000,"cost":{"cache_read":0.02,"cache_write":0.25,"context_over_200k":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8},"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.edenai.co","output":128000,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"openai/gpt-5.6-luna","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":1.2,"release_date":"2026-07-09","slug":"openai/gpt-5.6-luna","source":"Models.dev","source_url":"https://models.dev/models/openai/gpt-5.6-luna/","speed_tps":104.0,"verification_status":"Source-linked"},{"agentic_score":50.5,"benchmark_data":[{"date":"2026-07-09","metric":"resolve rate","name":"SWE-Bench Pro","score":64.6,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"success rate","name":"Terminal-Bench","score":88.8,"source":"https://openai.com/index/gpt-5-6/","version":"2.1"},{"date":"2026-07-09","metric":"resolve rate","name":"DeepSWE","score":72.7,"source":"https://openai.com/index/gpt-5-6/","version":"1.1"},{"date":"2026-07-09","metric":"accuracy","name":"GPQA Diamond","score":94.6,"source":"https://openai.com/index/gpt-5-6/"},{"dataset":"Tier 1-3","date":"2026-07-09","metric":"accuracy","name":"FrontierMath","score":89,"source":"https://openai.com/index/gpt-5-6/","version":"v2"},{"date":"2026-07-09","metric":"accuracy","name":"BrowseComp","score":90.4,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"success rate","name":"OSWorld","score":62.6,"source":"https://openai.com/index/gpt-5-6/","version":"2.0"},{"date":"2026-07-09","metric":"accuracy","name":"MMMU Pro","score":83,"source":"https://openai.com/index/gpt-5-6/","variant":"no tools"},{"date":"2026-07-09","name":"Agents' Last Exam","score":52.7,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"success rate","name":"Toolathlon","score":58,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"index score","name":"Artificial Analysis Intelligence Index","score":58.9,"source":"https://artificialanalysis.ai/articles/gpt-5-6-has-landed","variant":"max","version":"4.1"},{"date":"2026-07-09","harness":"Codex","metric":"index score","name":"Artificial Analysis Coding Agent Index","score":80,"source":"https://artificialanalysis.ai/articles/gpt-5-6-has-landed","variant":"max","version":"1.1"}],"cached_input_price_per_million":0.4,"coding_score":77.4,"confidence":"Medium","context_length":1050000,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","developer":"OpenAI","input_price_per_million":4.0,"intelligence_score":47.1,"last_verified":"2026-09-11T13:08:15.603291","max_output_tokens":128000,"metadata":{"attachment":true,"family":"gpt-sol","knowledge":"2026-02-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":false,"tool_call":true},"modalities":"Image, Pdf, Text","name":"GPT-5.6 Sol","offerings":[{"api":"https://agentrouter.org/v1","context":1050000,"cost":{},"doc":"https://agentrouter.org/docs/opencode.html","output":128000,"provider":"AgentRouter","provider_id":"agentrouter","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://nano-gpt.com/api/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"doc":"https://docs.nano-gpt.com","output":128000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.impossibl.com/v1","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"context_over_200k":{"cache_read":1,"cache_write":12.5,"input":10,"output":45},"input":5,"output":30,"tiers":[{"cache_read":1,"cache_write":12.5,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"doc":"https://impossibl.com/docs/models","output":128000,"provider":"Impossibl","provider_id":"impossibl","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"doc":"https://llmgateway.io/docs","output":128000,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"doc":"https://docs.aihubmix.com","output":128000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1050000,"cost":{"cache_read":0.4,"cache_write":5,"input":4,"output":20},"doc":"https://docs.orcarouter.ai","output":128000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.routing.run/v1","context":1000000,"cost":{"input":2.5,"output":15},"doc":"https://docs.routing.run/api-reference/models","output":128000,"provider":"routing.run","provider_id":"routing-run","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":10,"output":45},"input":5,"output":30,"tiers":[{"cache_read":1,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure Cognitive Services","provider_id":"azure-cognitive-services","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":1050000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":128000,"provider":"Kenari","provider_id":"kenari","provider_model_id":"gpt-5-6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"doc":"https://agent.pioneer.ai/llms.txt","output":128000,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1050000,"cost":{"cache_read":0.4,"cache_write":5,"context_over_200k":{"cache_read":0.8,"cache_write":10,"input":8,"output":30},"input":4,"output":20,"tiers":[{"cache_read":0.8,"cache_write":10,"input":8,"output":30,"tier":{"size":272000,"type":"context"}}]},"doc":"https://requesty.ai/solution/llm-routing/models","output":128000,"provider":"Requesty","provider_id":"requesty","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1050000,"cost":{"cache_read":0.4,"cache_write":5,"context_over_200k":{"cache_read":0.8,"cache_write":10,"input":8,"output":30},"input":4,"output":20,"tiers":[{"cache_read":0.8,"cache_write":10,"input":8,"output":30,"tier":{"size":272000,"type":"context"}}]},"doc":"https://www.crossmodel.ai/docs","output":128000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://www.xpersona.co/v1","context":372000,"cost":{"cache_read":0.15,"input":1.5,"output":12,"reasoning":12},"doc":"https://www.xpersona.co/docs","output":128000,"provider":"Xpersona","provider_id":"xpersona","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":3.125,"context_over_200k":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":18.75},"input":2.5,"output":12.5,"tiers":[{"cache_read":0.5,"cache_write":6.25,"input":5,"output":18.75,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.venice.ai","output":128000,"provider":"Venice AI","provider_id":"venice","provider_model_id":"openai-gpt-56-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"doc":"https://llmgateway.io/docs","output":128000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.25,"cache_write":3.125,"input":2,"output":10},"doc":"https://developers.cloudflare.com/ai-gateway/","output":128000,"provider":"Cloudflare AI Gateway","provider_id":"cloudflare-ai-gateway","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1050000,"cost":{"cache_read":0.4,"cache_write":5,"context_over_200k":{"cache_read":0.8,"cache_write":10,"input":8,"output":30},"input":4,"output":20,"tiers":[{"cache_read":0.8,"cache_write":10,"input":8,"output":30,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.github.com/en/copilot","output":128000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"context_over_200k":{"cache_read":1,"cache_write":12.5,"input":10,"output":45},"input":5,"output":30,"tiers":[{"cache_read":1,"cache_write":12.5,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"doc":"https://opper.ai/models","output":128000,"provider":"Opper","provider_id":"opper","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1","context":1050000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":10,"output":45},"input":5,"output":30,"tiers":[{"cache_read":1,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.databricks.com/aws/en/machine-learning/foundation-models/","output":128000,"provider":"Databricks","provider_id":"databricks","provider_model_id":"databricks-gpt-5-6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1050000,"cost":{"cache_read":0.4,"cache_write":5,"input":4,"output":20},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1050000,"cost":{"cache_read":0.4,"cache_write":5,"input":4,"output":20},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"openai/gpt-5.6-sol-pro","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"context_over_200k":{"cache_read":1,"cache_write":12.5,"input":10,"output":45},"input":4,"output":20,"tiers":[{"cache_read":1,"cache_write":12.5,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure","provider_id":"azure","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.44,"cache_write":5.5,"context_over_200k":{"cache_read":0.88,"cache_write":11,"input":8.8,"output":33},"input":4.4,"output":22,"tiers":[{"cache_read":0.88,"cache_write":11,"input":8.8,"output":33,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","output":128000,"provider":"Amazon Bedrock","provider_id":"amazon-bedrock","provider_model_id":"openai.gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1050000,"cost":{"cache_read":0.5,"cache_write":5,"input":5,"output":30},"doc":"https://docs.merge.dev/merge-gateway","output":128000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1000000,"cost":{"cache_read":0.5,"input":5,"output":30},"doc":"https://abacus.ai/help/api","output":128000,"provider":"Abacus","provider_id":"abacus","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":15},"input":2,"output":10,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":15,"tier":{"size":272000,"type":"context"}}]},"doc":"https://openrouter.ai/models","output":128000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1050000,"cost":{"cache_read":0.25,"cache_write":3.125,"input":2.5,"output":15},"doc":"https://ofox.ai/docs","output":128000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"context_over_200k":{"cache_read":1,"cache_write":12.5,"input":10,"output":45},"input":5,"output":30,"tiers":[{"cache_read":1,"cache_write":12.5,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"doc":"https://neon.com/docs","output":128000,"provider":"Neon","provider_id":"neon","provider_model_id":"gpt-5-6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.4,"cache_write":5,"context_over_200k":{"cache_read":0.8,"cache_write":10,"input":8,"output":30},"input":4,"output":20,"tiers":[{"cache_read":0.8,"cache_write":10,"input":8,"output":30,"tier":{"size":272000,"type":"context"}}]},"doc":"https://platform.openai.com/docs/models","output":128000,"provider":"OpenAI","provider_id":"openai","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1","context":1050000,"cost":{},"doc":"https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api","output":128000,"provider":"Snowflake Cortex","provider_id":"snowflake-cortex","provider_model_id":"openai-gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1050000,"cost":{"input":5,"output":30},"doc":"https://doc.302.ai","output":128000,"provider":"302.AI","provider_id":"302ai","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ai-router.dev/v1","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"doc":"https://ai-router.dev/openai-compatible-api-gateway/","output":128000,"provider":"AI-ROUTER","provider_id":"ai-router","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://zenmux.ai/api/v1","context":1050000,"cost":{"cache_read":0.5,"cache_write":6.25,"context_over_200k":{"cache_read":1,"cache_write":12.5,"input":10,"output":45},"input":5,"output":30,"tiers":[{"cache_read":1,"cache_write":12.5,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.zenmux.ai","output":128000,"provider":"ZenMux","provider_id":"zenmux","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1050000,"cost":{"cache_read":0.55,"cache_write":6.879,"input":5.5,"output":32.998},"doc":"https://api.cortecs.ai/v1/models","output":128000,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1050000,"cost":{"cache_read":0.4,"cache_write":5,"context_over_200k":{"cache_read":0.8,"cache_write":10,"input":8,"output":30},"input":4,"output":20,"tiers":[{"cache_read":0.8,"cache_write":10,"input":8,"output":30,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.edenai.co","output":128000,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"openai/gpt-5.6-sol","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":20.0,"release_date":"2026-07-09","slug":"openai/gpt-5.6-sol","source":"Models.dev","source_url":"https://models.dev/models/openai/gpt-5.6-sol/","speed_tps":48.0,"verification_status":"Source-linked"},{"agentic_score":43.7,"benchmark_data":[{"date":"2026-07-09","metric":"resolve rate","name":"SWE-Bench Pro","score":63.4,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"success rate","name":"Terminal-Bench","score":87.4,"source":"https://openai.com/index/gpt-5-6/","version":"2.1"},{"date":"2026-07-09","metric":"resolve rate","name":"DeepSWE","score":69.6,"source":"https://openai.com/index/gpt-5-6/","version":"1.1"},{"date":"2026-07-09","metric":"accuracy","name":"GPQA Diamond","score":92.9,"source":"https://openai.com/index/gpt-5-6/"},{"dataset":"Tier 1-3","date":"2026-07-09","metric":"accuracy","name":"FrontierMath","score":84.9,"source":"https://openai.com/index/gpt-5-6/","version":"v2"},{"date":"2026-07-09","metric":"accuracy","name":"BrowseComp","score":87.5,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"success rate","name":"OSWorld","score":50.2,"source":"https://openai.com/index/gpt-5-6/","version":"2.0"},{"date":"2026-07-09","metric":"accuracy","name":"MMMU Pro","score":80.7,"source":"https://openai.com/index/gpt-5-6/","variant":"no tools"},{"date":"2026-07-09","name":"Agents' Last Exam","score":50.4,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"success rate","name":"Toolathlon","score":53.1,"source":"https://openai.com/index/gpt-5-6/"},{"date":"2026-07-09","metric":"index score","name":"Artificial Analysis Intelligence Index","score":55,"source":"https://artificialanalysis.ai/articles/gpt-5-6-has-landed","variant":"max","version":"4.1"},{"date":"2026-07-09","harness":"Codex","metric":"index score","name":"Artificial Analysis Coding Agent Index","score":77.4,"source":"https://artificialanalysis.ai/articles/gpt-5-6-has-landed","variant":"max","version":"1.1"}],"cached_input_price_per_million":0.2,"coding_score":76.7,"confidence":"Medium","context_length":1050000,"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","developer":"OpenAI","input_price_per_million":2.0,"intelligence_score":42.3,"last_verified":"2026-09-11T13:08:17.132329","max_output_tokens":128000,"metadata":{"attachment":true,"family":"gpt-terra","knowledge":"2026-02-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":false,"tool_call":true},"modalities":"Image, Pdf, Text","name":"GPT-5.6 Terra","offerings":[{"api":"https://nano-gpt.com/api/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://docs.nano-gpt.com","output":128000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.impossibl.com/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://impossibl.com/docs/models","output":128000,"provider":"Impossibl","provider_id":"impossibl","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://llmgateway.io/docs","output":128000,"provider":"LLM Gateway","provider_id":"llmgateway-providers","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.25,"cache_write":3.125,"input":2.5,"output":15},"doc":"https://docs.aihubmix.com","output":128000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://docs.orcarouter.ai","output":128000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.routing.run/v1","context":1000000,"cost":{"input":1.5,"output":9},"doc":"https://docs.routing.run/api-reference/models","output":128000,"provider":"routing.run","provider_id":"routing-run","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.25,"cache_write":3.125,"context_over_200k":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":22.5},"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"cache_write":6.25,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure Cognitive Services","provider_id":"azure-cognitive-services","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":1050000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":128000,"provider":"Kenari","provider_id":"kenari","provider_model_id":"gpt-5-6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":1050000,"cost":{"cache_read":0.25,"cache_write":3.125,"input":2.5,"output":15},"doc":"https://agent.pioneer.ai/llms.txt","output":128000,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":1050000,"cost":{"cache_read":0.2,"context_over_200k":{"cache_read":0.4,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://requesty.ai/solution/llm-routing/models","output":128000,"provider":"Requesty","provider_id":"requesty","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://www.crossmodel.ai/docs","output":128000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://www.xpersona.co/v1","context":372000,"cost":{"cache_read":0.15,"input":1.5,"output":2,"reasoning":2},"doc":"https://www.xpersona.co/docs","output":128000,"provider":"Xpersona","provider_id":"xpersona","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":128000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.25,"cache_write":3.125,"context_over_200k":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":22.5},"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"cache_write":6.25,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.venice.ai","output":128000,"provider":"Venice AI","provider_id":"venice","provider_model_id":"openai-gpt-56-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://llmgateway.io/docs","output":128000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://developers.cloudflare.com/ai-gateway/","output":128000,"provider":"Cloudflare AI Gateway","provider_id":"cloudflare-ai-gateway","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.github.com/en/copilot","output":128000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://opper.ai/models","output":128000,"provider":"Opper","provider_id":"opper","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1","context":1050000,"cost":{"cache_read":0.25,"context_over_200k":{"cache_read":0.5,"input":5,"output":22.5},"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.databricks.com/aws/en/machine-learning/foundation-models/","output":128000,"provider":"Databricks","provider_id":"databricks","provider_model_id":"databricks-gpt-5-6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"openai/gpt-5.6-terra-pro","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","output":128000,"provider":"Azure","provider_id":"azure","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.22,"cache_write":2.75,"context_over_200k":{"cache_read":0.44,"cache_write":5.5,"input":4.4,"output":19.8},"input":2.2,"output":13.2,"tiers":[{"cache_read":0.44,"cache_write":5.5,"input":4.4,"output":19.8,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","output":128000,"provider":"Amazon Bedrock","provider_id":"amazon-bedrock","provider_model_id":"openai.gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://docs.merge.dev/merge-gateway","output":128000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":1000000,"cost":{"cache_read":0.25,"input":2.5,"output":15},"doc":"https://abacus.ai/help/api","output":128000,"provider":"Abacus","provider_id":"abacus","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":1050000,"cost":{"cache_read":0.25,"cache_write":3.125,"context_over_200k":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":22.5},"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"cache_write":6.25,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"doc":"https://opencode.ai/docs/zen","output":128000,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://openrouter.ai/models","output":128000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"doc":"https://ofox.ai/docs","output":128000,"provider":"Ofox","provider_id":"ofox","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"${NEON_AI_GATEWAY_BASE_URL}/v1","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://neon.com/docs","output":128000,"provider":"Neon","provider_id":"neon","provider_model_id":"gpt-5-6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://platform.openai.com/docs/models","output":128000,"provider":"OpenAI","provider_id":"openai","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1","context":1050000,"cost":{},"doc":"https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api","output":128000,"provider":"Snowflake Cortex","provider_id":"snowflake-cortex","provider_model_id":"openai-gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":1050000,"cost":{"input":2,"output":12},"doc":"https://doc.302.ai","output":128000,"provider":"302.AI","provider_id":"302ai","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ai-router.dev/v1","context":1050000,"cost":{"cache_read":0.25,"cache_write":3.125,"input":2.5,"output":15},"doc":"https://ai-router.dev/openai-compatible-api-gateway/","output":128000,"provider":"AI-ROUTER","provider_id":"ai-router","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://zenmux.ai/api/v1","context":1050000,"cost":{"cache_read":0.25,"cache_write":3.125,"context_over_200k":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":22.5},"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"cache_write":6.25,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.zenmux.ai","output":128000,"provider":"ZenMux","provider_id":"zenmux","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.cortecs.ai/v1","context":1050000,"cost":{"cache_read":0.219,"cache_write":2.749,"input":2.2,"output":13.199},"doc":"https://api.cortecs.ai/v1/models","output":128000,"provider":"Cortecs","provider_id":"cortecs","provider_model_id":"gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":1050000,"cost":{"cache_read":0.2,"cache_write":2.5,"context_over_200k":{"cache_read":0.4,"cache_write":5,"input":4,"output":18},"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"doc":"https://docs.edenai.co","output":128000,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"openai/gpt-5.6-terra","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":12.0,"release_date":"2026-07-09","slug":"openai/gpt-5.6-terra","source":"Models.dev","source_url":"https://models.dev/models/openai/gpt-5.6-terra/","speed_tps":113.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[{"date":"2026-07-08","metric":"resolve rate","name":"SWE-Bench Pro","score":64.7,"source":"https://x.ai/news/grok-4-5"},{"date":"2026-07-08","metric":"resolve rate","name":"SWE-Bench Multilingual","score":78,"source":"https://x.ai/news/grok-4-5"},{"date":"2026-07-08","metric":"success rate","name":"Terminal-Bench","score":83.3,"source":"https://x.ai/news/grok-4-5","version":"2.1"},{"date":"2026-07-08","metric":"resolve rate","name":"DeepSWE","score":62,"source":"https://x.ai/news/grok-4-5","version":"1.0"},{"date":"2026-07-08","harness":"mini-swe-agent","metric":"resolve rate","name":"DeepSWE","score":53,"source":"https://x.ai/news/grok-4-5","version":"1.1"},{"date":"2026-07-08","metric":"pass@1","name":"SWE Marathon","score":29,"source":"https://x.ai/news/grok-4-5"}],"cached_input_price_per_million":0.3,"coding_score":0.0,"confidence":"Medium","context_length":500000,"description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","developer":"xAI","input_price_per_million":2.0,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:18.562215","max_output_tokens":500000,"metadata":{"attachment":true,"family":"grok","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"reasoning":true,"structured_output":true,"temperature":true,"tool_call":true},"modalities":"Image, Text","name":"Grok 4.5","offerings":[{"api":"https://nano-gpt.com/api/v1","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://docs.nano-gpt.com","output":450000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"x-ai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.impossibl.com/v1","context":500000,"cost":{"cache_read":0.3,"input":2,"output":6},"doc":"https://impossibl.com/docs/models","output":500000,"provider":"Impossibl","provider_id":"impossibl","provider_model_id":"xai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":1000000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://docs.aihubmix.com","output":1000000,"provider":"AIHubMix","provider_id":"aihubmix","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://docs.orcarouter.ai","output":500000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"grok/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://kenari.id/v1","context":500000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":500000,"provider":"Kenari","provider_id":"kenari","provider_model_id":"grok-4-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.pioneer.ai/v1","context":500000,"cost":{"cache_read":0.5,"cache_write":2,"input":2,"output":6},"doc":"https://agent.pioneer.ai/llms.txt","output":131072,"provider":"Pioneer","provider_id":"pioneer","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":500000,"cost":{"cache_read":0.5,"cache_write":2,"context_over_200k":{"cache_read":1,"cache_write":4,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"cache_write":4,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://requesty.ai/solution/llm-routing/models","output":500000,"provider":"Requesty","provider_id":"requesty","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://daoxe.com/v1","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://daoxe.com/pricing","output":500000,"provider":"DaoXE","provider_id":"daoxe","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":500000,"cost":{"cache_read":0.3,"cache_write":2,"context_over_200k":{"cache_read":0.6,"cache_write":4,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":0.6,"cache_write":4,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://www.crossmodel.ai/docs","output":500000,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"x-ai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.3,"input":2,"output":6},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":500000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"spacexai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.34,"context_over_200k":{"cache_read":0.68,"input":4.53,"output":13.6},"input":2.27,"output":6.8,"tiers":[{"cache_read":0.68,"input":4.53,"output":13.6,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.venice.ai","output":32000,"provider":"Venice AI","provider_id":"venice","provider_model_id":"grok-4-5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":500000,"cost":{"cache_read":0.3,"input":2,"output":6},"doc":"https://llmgateway.io/docs","output":500000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"grok-4-5","reasoning":true,"structured_output":false,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.3,"input":2,"output":6},"doc":"https://developers.cloudflare.com/ai-gateway/","output":500000,"provider":"Cloudflare AI Gateway","provider_id":"cloudflare-ai-gateway","provider_model_id":"xai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.githubcopilot.com","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.github.com/en/copilot","output":128000,"provider":"GitHub Copilot","provider_id":"github-copilot","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.opper.ai/v3/compat","context":500000,"cost":{"cache_read":0.3,"context_over_200k":{"cache_read":0.6,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":0.6,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://opper.ai/models","output":500000,"provider":"Opper","provider_id":"opper","provider_model_id":"xai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":500000,"cost":{"cache_read":0.3,"input":2,"output":6},"doc":"https://kilo.ai","output":450000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"x-ai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api-gateway.merge.dev/v1/ai-sdk","context":500000,"cost":{"cache_read":0.5,"input":2,"output":6},"doc":"https://docs.merge.dev/merge-gateway","output":500000,"provider":"Merge Gateway","provider_id":"merge-gateway","provider_model_id":"xai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://routellm.abacus.ai/v1","context":500000,"cost":{"input":2,"output":6},"doc":"https://abacus.ai/help/api","output":32768,"provider":"Abacus","provider_id":"abacus","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/v1","context":500000,"cost":{"cache_read":0.3,"context_over_200k":{"cache_read":0.6,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":0.6,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://opencode.ai/docs/zen","output":500000,"provider":"OpenCode Zen","provider_id":"opencode","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":500000,"cost":{"cache_read":0.3,"context_over_200k":{"cache_read":0.6,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":0.6,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://openrouter.ai/models","output":450000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"x-ai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.ofox.ai/v1","context":500000,"cost":{"cache_read":0.3,"input":2,"output":6},"doc":"https://ofox.ai/docs","output":65536,"provider":"Ofox","provider_id":"ofox","provider_model_id":"x-ai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.302.ai/v1","context":500000,"cost":{"input":2,"output":6},"doc":"https://doc.302.ai","output":500000,"provider":"302.AI","provider_id":"302ai","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":500000,"cost":{"cache_read":0.3,"context_over_200k":{"cache_read":0.6,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":0.6,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.x.ai/docs/models","output":500000,"provider":"xAI","provider_id":"xai","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://zenmux.ai/api/v1","context":500000,"cost":{"cache_read":0.5,"context_over_200k":{"cache_read":1,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.zenmux.ai","output":500000,"provider":"ZenMux","provider_id":"zenmux","provider_model_id":"x-ai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":500000,"cost":{"cache_read":0.3,"context_over_200k":{"cache_read":0.6,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":0.6,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://opencode.ai/docs/zen","output":500000,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"grok-4.5","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.edenai.run/v3","context":500000,"cost":{"cache_read":0.3,"context_over_200k":{"cache_read":0.6,"input":4,"output":12},"input":2,"output":6,"tiers":[{"cache_read":0.6,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"doc":"https://docs.edenai.co","output":500000,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"xai/grok-4.5","reasoning":true,"structured_output":true,"tool_call":true}],"open_weights":false,"output_price_per_million":6.0,"release_date":"2026-07-08","slug":"xai/grok-4.5","source":"Models.dev","source_url":"https://models.dev/models/xai/grok-4.5/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[{"metric":"resolved","name":"SWE-Bench Verified","score":78,"source":"https://huggingface.co/tencent/Hy3"}],"cached_input_price_per_million":0.029,"coding_score":0.0,"confidence":"Medium","context_length":256000,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","developer":"Tencent","input_price_per_million":0.066,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:18.337798","max_output_tokens":128000,"metadata":{"attachment":false,"family":"Hy","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"temperature":true,"tool_call":true,"weights":[{"label":"Hugging Face","url":"https://huggingface.co/tencent/Hy3"}]},"modalities":"Text","name":"Hy3","offerings":[{"api":"https://nano-gpt.com/api/v1","context":262144,"cost":{"cache_read":0.029,"input":0.066,"output":0.26},"doc":"https://docs.nano-gpt.com","output":128000,"provider":"NanoGPT","provider_id":"nano-gpt","provider_model_id":"tencent/hy3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.orcarouter.ai/v1","context":256000,"cost":{"cache_read":0.059,"input":0.18,"output":0.59},"doc":"https://docs.orcarouter.ai","output":128000,"provider":"OrcaRouter","provider_id":"orcarouter","provider_model_id":"tencent/hy3","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://kenari.id/v1","context":256000,"cost":{"input":0,"output":0},"doc":"https://kenari.id/docs","output":128000,"provider":"Kenari","provider_id":"kenari","provider_model_id":"hy3","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://router.requesty.ai/v1","context":262144,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"doc":"https://requesty.ai/solution/llm-routing/models","output":262144,"provider":"Requesty","provider_id":"requesty","provider_model_id":"hy3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://router.huggingface.co/v1","context":262144,"cost":{"input":0.14,"output":0.58},"doc":"https://huggingface.co/docs/inference-providers","output":128000,"provider":"Hugging Face","provider_id":"huggingface","provider_model_id":"tencent/Hy3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.crossmodel.ai/v1","context":262144,"cost":{"cache_read":0.04,"cache_write":0.16,"input":0.16,"output":0.64},"doc":"https://www.crossmodel.ai/docs","output":131072,"provider":"CrossModel","provider_id":"crossmodel","provider_model_id":"tencent/hy3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":262144,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":262144,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"tencent/hy3","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.llmgateway.io/v1","context":262144,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"doc":"https://llmgateway.io/docs","output":128000,"provider":"DevPass (LLM Gateway)","provider_id":"llmgateway","provider_model_id":"hy3","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.jalapeno-cloud.ai/v1","context":202752,"cost":{"input":0.14,"output":0.58},"doc":"https://www.jalapeno-cloud.ai/docs/","output":128000,"provider":"Jalapeno Cloud","provider_id":"jalapeno","provider_model_id":"Hy3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"","context":262144,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"doc":"https://deepinfra.com/models","output":128000,"provider":"Deep Infra","provider_id":"deepinfra","provider_model_id":"tencent/Hy3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":262144,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"doc":"https://kilo.ai","output":128000,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"tencent/hy3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":262144,"cost":{"cache_read":0.033,"input":0.132,"output":0.528},"doc":"https://openrouter.ai/models","output":128000,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"tencent/hy3","reasoning":true,"structured_output":true,"tool_call":true},{"api":"https://tokenhub.tencentmaas.com/v1","context":256000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://cloud.tencent.com/document/product/1823/130050","output":128000,"provider":"Tencent TokenHub","provider_id":"tencent-tokenhub","provider_model_id":"hy3","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://opencode.ai/zen/go/v1","context":256000,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"doc":"https://opencode.ai/docs/zen","output":128000,"provider":"OpenCode Go","provider_id":"opencode-go","provider_model_id":"hy3","reasoning":true,"structured_output":null,"tool_call":true},{"api":"https://api.lkeap.cloud.tencent.com/plan/v3","context":256000,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://cloud.tencent.com/document/product/1823/130060","output":128000,"provider":"Tencent Token Plan","provider_id":"tencent-token-plan","provider_model_id":"hy3","reasoning":true,"structured_output":null,"tool_call":true}],"open_weights":true,"output_price_per_million":0.26,"release_date":"2026-07-06","slug":"tencent/hy3","source":"Models.dev","source_url":"https://models.dev/models/tencent/hy3/","speed_tps":59.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":0.4,"coding_score":0.0,"confidence":"Medium","context_length":128000,"description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","developer":"OpenAI","input_price_per_million":4.0,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:17.391814","max_output_tokens":32000,"metadata":{"attachment":true,"family":"gpt","knowledge":"2024-09-30","modalities":{"input":["text","audio","image"],"output":["text","audio"]},"open_weights":false,"reasoning":true,"structured_output":false,"temperature":false,"tool_call":true},"modalities":"Audio, Image, Text","name":"GPT-Realtime-2.1","offerings":[{"api":"","context":128000,"cost":{"cache_read":0.4,"input":4,"output":24},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":32000,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"openai/gpt-realtime-2.1","reasoning":true,"structured_output":false,"tool_call":false},{"api":"","context":128000,"cost":{"cache_read":0.4,"input":4,"input_audio":32,"output":24,"output_audio":64},"doc":"https://platform.openai.com/docs/models","output":32000,"provider":"OpenAI","provider_id":"openai","provider_model_id":"gpt-realtime-2.1","reasoning":true,"structured_output":false,"tool_call":true}],"open_weights":false,"output_price_per_million":24.0,"release_date":"2026-07-06","slug":"openai/gpt-realtime-2.1","source":"Models.dev","source_url":"https://models.dev/models/openai/gpt-realtime-2.1/","speed_tps":0.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[{"date":"2026-07-02","harness":"Harbor","metric":"resolved","name":"SWE-Bench Verified","score":70.9,"source":"https://poolside.ai/blog/introducing-laguna-xs-2-1"},{"date":"2026-07-02","harness":"Harbor","metric":"resolve rate","name":"SWE-Bench Multilingual","score":63.1,"source":"https://poolside.ai/blog/introducing-laguna-xs-2-1"},{"date":"2026-07-02","harness":"Harbor","metric":"resolve rate","name":"SWE-Bench Pro","score":47.6,"source":"https://poolside.ai/blog/introducing-laguna-xs-2-1"},{"date":"2026-07-02","harness":"Harbor","metric":"success rate","name":"Terminal-Bench","score":37.5,"source":"https://poolside.ai/blog/introducing-laguna-xs-2-1","version":"2.0"}],"cached_input_price_per_million":0.03,"coding_score":0.0,"confidence":"Medium","context_length":262144,"description":"Agentic coding model from Poolside in the XS size class for local deployment","developer":"Poolside","input_price_per_million":0.06,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:08.929022","max_output_tokens":32768,"metadata":{"attachment":false,"family":"laguna","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"reasoning":true,"structured_output":false,"temperature":true,"tool_call":true},"modalities":"Text","name":"Laguna XS 2.1","offerings":[{"api":"https://inference.poolside.ai/v1","context":262144,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0},"doc":"https://platform.poolside.ai","output":32768,"provider":"Poolside","provider_id":"poolside","provider_model_id":"poolside/laguna-xs-2.1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://llmtr.com/v1","context":262144,"cost":{"input":0,"output":0},"doc":"https://llmtr.com/docs","output":32768,"provider":"LLMTR","provider_id":"llmtr","provider_model_id":"poolside/laguna-xs-2.1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://integrate.api.nvidia.com/v1","context":262144,"cost":{"input":0,"output":0},"doc":"https://docs.api.nvidia.com/nim/","output":16384,"provider":"Nvidia","provider_id":"nvidia","provider_model_id":"poolside/laguna-xs-2.1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://api.kilo.ai/api/gateway","context":262144,"cost":{"cache_read":0.05,"input":0.1,"output":0.2},"doc":"https://kilo.ai","output":32768,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"poolside/laguna-xs-2.1","reasoning":true,"structured_output":false,"tool_call":true},{"api":"https://openrouter.ai/api/v1","context":262144,"cost":{"cache_read":0.03,"input":0.06,"output":0.12},"doc":"https://openrouter.ai/models","output":32768,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"poolside/laguna-xs-2.1","reasoning":true,"structured_output":false,"tool_call":true}],"open_weights":true,"output_price_per_million":0.12,"release_date":"2026-07-02","slug":"poolside/laguna-xs-2.1","source":"Models.dev","source_url":"https://models.dev/models/poolside/laguna-xs-2.1/","speed_tps":130.0,"verification_status":"Source-linked"},{"agentic_score":0.0,"benchmark_data":[],"cached_input_price_per_million":null,"coding_score":0.0,"confidence":"Medium","context_length":65536,"description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","developer":"Google","input_price_per_million":0.25,"intelligence_score":0.0,"last_verified":"2026-09-11T13:08:12.389174","max_output_tokens":4096,"metadata":{"attachment":true,"family":"gemini-flash-lite","knowledge":"2025-01","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"reasoning":true,"structured_output":false,"temperature":true,"tool_call":true},"modalities":"Image, Text","name":"Nano Banana 2 Lite","offerings":[{"api":"","context":65536,"cost":{"input":0.25,"output":30},"doc":"https://ai.google.dev/gemini-api/docs/models","output":65536,"provider":"Google","provider_id":"google","provider_model_id":"gemini-3.1-flash-lite-image","reasoning":true,"structured_output":false,"tool_call":true},{"api":"","context":65536,"cost":{"cache_read":0.03,"input":0.25,"output":1.5},"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","output":4096,"provider":"Vercel AI Gateway","provider_id":"vercel","provider_model_id":"google/gemini-3.1-flash-lite-image","reasoning":true,"structured_output":false,"tool_call":false},{"api":"https://api.kilo.ai/api/gateway","context":65536,"cost":{"input":0.25,"output":1.5},"doc":"https://kilo.ai","output":58982,"provider":"Kilo Gateway","provider_id":"kilo","provider_model_id":"google/gemini-3.1-flash-lite-image","reasoning":true,"structured_output":false,"tool_call":false},{"api":"https://openrouter.ai/api/v1","context":65536,"cost":{"input":0.25,"output":1.5},"doc":"https://openrouter.ai/models","output":58982,"provider":"OpenRouter","provider_id":"openrouter","provider_model_id":"google/gemini-3.1-flash-lite-image","reasoning":true,"structured_output":false,"tool_call":false},{"api":"https://api.edenai.run/v3","context":65536,"cost":{"input":0.25,"output":1.5},"doc":"https://docs.edenai.co","output":4096,"provider":"Eden AI","provider_id":"edenai","provider_model_id":"google/gemini-3.1-flash-lite-image","reasoning":true,"structured_output":true,"tool_call":false}],"open_weights":false,"output_price_per_million":30.0,"release_date":"2026-06-30","slug":"google/gemini-3.1-flash-lite-image","source":"Models.dev","source_url":"https://models.dev/models/google/gemini-3.1-flash-lite-image/","speed_tps":337.0,"verification_status":"Source-linked"}],"meta":{"limit":50,"page":1,"total":4171}}