{"message":null,"data":[{"provider":"@aion-labs","models":[{"name":"@aion-labs/aion-3.0","description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":32768,"contextWindow":131072,"parameterSize":null,"releaseDate":"2026-07-07","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":3,"cachedInputPerMillionTokens":0.75,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260707,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@aion-labs/aion-3.0-mini","description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Medium"],"maxOutputTokens":32768,"contextWindow":131072,"parameterSize":null,"releaseDate":"2026-07-07","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.7,"cachedInputPerMillionTokens":0.18,"outputPerMillionTokens":1.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260707,"rateLimitGroup":"Low","capabilities":["Thinking","ToolCalling"]}]},{"provider":"@amazon","models":[{"name":"@amazon/nova-pro","description":"A highly capable multimodal model with the best combination of accuracy, speed, and cost for a wide range of tasks.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":65536,"contextWindow":307200,"parameterSize":null,"releaseDate":"2024-12-05","provider":{"name":"AWS","link":"https://aws.amazon.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.8,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":3.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20241205,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@amazon/nova-lite","description":"A very low cost multimodal model that is lightning fast for processing image, video, and text inputs.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Medium"],"maxOutputTokens":65536,"contextWindow":307200,"parameterSize":null,"releaseDate":"2024-12-05","provider":{"name":"AWS","link":"https://aws.amazon.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.06,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.24,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20241205,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@amazon/nova-micro","description":"A text-only model that delivers the lowest latency responses at very low cost.","technicalInfo":{"intelligenceLevel":["Low"],"speedLevel":["Medium"],"maxOutputTokens":65536,"contextWindow":131072,"parameterSize":null,"releaseDate":null,"provider":{"name":"AWS","link":"https://aws.amazon.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.04,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.14,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["ToolCalling"]}]},{"provider":"@anthropic","models":[{"name":"@anthropic/claude-5-sonnet","description":"Claude Sonnet 5 is Anthropic\u0027s most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-06-30","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260630,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-fable-5","description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-06-09","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":10,"cachedInputPerMillionTokens":1,"outputPerMillionTokens":50,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260609,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-4.8-opus","description":"Claude Opus 4.8 is Anthropic\u0027s most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-05-27","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":25,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260527,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-4.7-opus","description":"Opus 4.7 is the next generation of Anthropic\u0027s Opus family, built for long-running, asynchronous agents.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-04-16","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":25,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260416,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-4.6-sonnet","description":"Sonnet 4.6 is Anthropic\u0027s most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-02-17","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":3,"cachedInputPerMillionTokens":0.3,"outputPerMillionTokens":15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":6,"cachedInputPerMillionTokens":0.6,"outputPerMillionTokens":22.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260217,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-4.6-opus","description":"Opus 4.6 is Anthropic\u2019s strongest model for coding and long-running professional tasks.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-02-04","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":25,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":10,"cachedInputPerMillionTokens":1,"outputPerMillionTokens":37.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260204,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-4.5-opus","description":"Claude Opus 4.5 is Anthropic\u2019s latest reasoning model, developed for advanced software engineering, complex agent workflows, and extended computer tasks.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":65536,"contextWindow":200000,"parameterSize":null,"releaseDate":"2025-11-24","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":25,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251124,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-4.5-haiku","description":"Claude Haiku 4.5 is Anthropic\u2019s fastest and most efficient model, offering near-frontier intelligence with much lower cost and latency than larger Claude models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":65536,"contextWindow":200000,"parameterSize":null,"releaseDate":"2025-10-15","provider":{"name":"AWS","link":"https://aws.amazon.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.1,"outputPerMillionTokens":5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251015,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@anthropic/claude-4.5-sonnet","description":"Claude Sonnet 4.5 is the newest model in the Sonnet series, offering improvements and updates over Sonnet 4.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":65536,"contextWindow":200000,"parameterSize":null,"releaseDate":"2025-09-29","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":3,"cachedInputPerMillionTokens":0.3,"outputPerMillionTokens":15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250929,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-4.1-opus","description":"Claude Opus 4.1 is Anthropic\u2019s flagship model, offering improved performance in coding, reasoning, and agentic tasks.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":65536,"contextWindow":200000,"parameterSize":null,"releaseDate":"2025-08-05","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":15,"cachedInputPerMillionTokens":1.5,"outputPerMillionTokens":75,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250805,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-4-sonnet","description":"Anthropic\u0027s mid-size model with superior intelligence for high-volume uses in coding, in-depth research, agents, \u0026 more.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":65536,"contextWindow":200000,"parameterSize":null,"releaseDate":"2025-05-22","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":3,"cachedInputPerMillionTokens":0.3,"outputPerMillionTokens":15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250522,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@anthropic/claude-3.5-haiku","description":"Claude 3.5 Haiku is the next generation of our fastest model. For a similar speed to Claude 3 Haiku, Claude 3.5 Haiku improves across every skill set and surpasses Claude 3 Opus, the largest model in our previous generation, on many intelligence benchmarks.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Slow"],"maxOutputTokens":65536,"contextWindow":200000,"parameterSize":null,"releaseDate":"2024-11-04","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.8,"cachedInputPerMillionTokens":0.08,"outputPerMillionTokens":4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20241104,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@anthropic/claude-3-haiku","description":"Claude 3 Haiku is Anthropic\u0027s fastest model yet, designed for enterprise workloads which often involve longer prompts.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Slow"],"maxOutputTokens":65536,"contextWindow":200000,"parameterSize":null,"releaseDate":null,"provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.25,"cachedInputPerMillionTokens":0.03,"outputPerMillionTokens":1.25,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]}]},{"provider":"@arcee-ai","models":[{"name":"@arcee-ai/trinity-large-thinking","description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":2048000,"contextWindow":2048000,"parameterSize":null,"releaseDate":"2026-04-01","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.25,"cachedInputPerMillionTokens":0.06,"outputPerMillionTokens":0.9,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260401,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]}]},{"provider":"@bytedance","models":[{"name":"@bytedance/seed-2.0-mini","description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Medium"],"maxOutputTokens":134144,"contextWindow":262144,"parameterSize":null,"releaseDate":"2026-02-26","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.1,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260226,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]}]},{"provider":"@cohere","models":[{"name":"@cohere/command-a","description":"Command A is Cohere\u0027s most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R\u002B 08-2024.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":65536,"contextWindow":262144,"parameterSize":null,"releaseDate":"2025-03-13","provider":{"name":"Cohere","link":"https://cohere.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250313,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]}]},{"provider":"@deepseek","models":[{"name":"@deepseek/deepseek-v4-pro","description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model designed for advanced reasoning, coding, and long-horizon agent workflows with 1.6T total parameters.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-04-24","provider":{"name":"DeepSeek","link":"https://deepseek.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":4.45,"cachedInputPerMillionTokens":0.35,"outputPerMillionTokens":5.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260424,"rateLimitGroup":"Common","capabilities":["ToolCalling"]},{"name":"@deepseek/deepseek-v4-flash","description":"An efficiency-optimized Mixture-of-Experts model from DeepSeek designed for fast inference and high-throughput workloads.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":384000,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-04-24","provider":{"name":"DeepSeek","link":"https://deepseek.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.14,"cachedInputPerMillionTokens":0.028,"outputPerMillionTokens":0.28,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260424,"rateLimitGroup":"Common","capabilities":["ToolCalling"]},{"name":"@deepseek/v3.2","description":"DeepSeek-V3.2 is a large language model optimized for high computational efficiency and strong tool-use reasoning.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":16384,"contextWindow":166912,"parameterSize":null,"releaseDate":"2025-12-01","provider":{"name":"DeepInfra","link":"https://deepinfra.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.6,"cachedInputPerMillionTokens":0.028,"outputPerMillionTokens":1.7,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251201,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@deepseek/v3.1-terminus","description":"DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":16384,"contextWindow":166912,"parameterSize":"685b","releaseDate":"2025-09-22","provider":{"name":"DeepInfra","link":"https://deepinfra.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.27,"cachedInputPerMillionTokens":0.216,"outputPerMillionTokens":1,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250922,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@deepseek/r1","description":"The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":16384,"contextWindow":163840,"parameterSize":"685b","releaseDate":"2025-05-28","provider":{"name":"DeepInfra","link":"https://deepinfra.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.5,"cachedInputPerMillionTokens":0.4,"outputPerMillionTokens":2.15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250528,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]}]},{"provider":"@google","models":[{"name":"@google/gemini-3.5-flash","description":"Gemini 3.5 Flash is Google\u0027s high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Ultrafast"],"maxOutputTokens":65536,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-05-19","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.5,"cachedInputPerMillionTokens":0.15,"outputPerMillionTokens":9,"audioInputPerMillionTokens":0.3,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260519,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","FileInput"]},{"name":"@google/gemini-3.1-flash-lite","description":"Gemini 3.1 Flash Lite Preview is Google\u0027s high-efficiency model optimized for high-volume use cases.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Ultrafast"],"maxOutputTokens":65536,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-05-07","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.25,"cachedInputPerMillionTokens":0.025,"outputPerMillionTokens":1.5,"audioInputPerMillionTokens":0.5,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":true,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260507,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","FileInput"]},{"name":"@google/gemma-4-26b-a4b-it","description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference \u2014 delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":262144,"contextWindow":262144,"parameterSize":null,"releaseDate":"2026-04-03","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.07,"cachedInputPerMillionTokens":0.04,"outputPerMillionTokens":0.35,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260403,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@google/gemma-4-31b-it","description":"Gemma 4 31B Instruct is Google DeepMind\u0027s 30.7B dense multimodal model supporting text and image input. Strong on coding, reasoning, and document understanding tasks with multilingual support across 140\u002B languages.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":262144,"contextWindow":262144,"parameterSize":null,"releaseDate":"2026-04-02","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.13,"cachedInputPerMillionTokens":0.02,"outputPerMillionTokens":0.38,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260402,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@google/gemini-3.1-pro","description":"Gemini 3.1 Pro Preview is Google\u2019s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":65536,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-02-19","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":12,"audioInputPerMillionTokens":2,"subscriptionMultiplier":null},{"tokenThreshold":204800,"inputPerMillionTokens":4,"cachedInputPerMillionTokens":0.4,"outputPerMillionTokens":18,"audioInputPerMillionTokens":4,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":true,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260219,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","FileInput"]},{"name":"@google/gemini-3-flash","description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":65536,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2025-12-17","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.5,"cachedInputPerMillionTokens":0.05,"outputPerMillionTokens":3,"audioInputPerMillionTokens":1,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":true,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251217,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","FileInput"]},{"name":"@google/gemini-2.5-flash-lite","description":"A Gemini 2.5 Flash model optimized for cost efficiency and low latency.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Ultrafast"],"maxOutputTokens":64000,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2025-07-22","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.1,"cachedInputPerMillionTokens":0.025,"outputPerMillionTokens":0.4,"audioInputPerMillionTokens":0.3,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250722,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@google/gemini-2.5-pro","description":"One of the most powerful models today.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Fast"],"maxOutputTokens":65536,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2025-06-17","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.25,"cachedInputPerMillionTokens":0.125,"outputPerMillionTokens":10,"audioInputPerMillionTokens":1.25,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":0.25,"outputPerMillionTokens":15,"audioInputPerMillionTokens":2.5,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250617,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","FileInput"]},{"name":"@google/gemini-2.5-flash","description":"Google\u0027s best model in terms of price-performance, offering well-rounded capabilities. 2.5 Flash is best for large scale processing, low-latency, high volume tasks that require thinking, and agentic use cases.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Ultrafast"],"maxOutputTokens":65536,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2025-06-17","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.3,"cachedInputPerMillionTokens":0.075,"outputPerMillionTokens":2.5,"audioInputPerMillionTokens":1,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250617,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","FileInput"]}]},{"provider":"@inception","models":[{"name":"@inception/mercury-2","description":"The fastest reasoning LLM and Inception most powerful model.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Ultrafast"],"maxOutputTokens":65536,"contextWindow":131072,"parameterSize":null,"releaseDate":"2026-03-04","provider":{"name":"Inception Labs","link":"https://www.inceptionlabs.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.25,"cachedInputPerMillionTokens":0.025,"outputPerMillionTokens":0.75,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260304,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling","Diffusion"]},{"name":"@inception/mercury","description":"Extremely fast model by generative diffusion.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Ultrafast"],"maxOutputTokens":32768,"contextWindow":131072,"parameterSize":null,"releaseDate":"2025-06-26","provider":{"name":"Inception Labs","link":"https://www.inceptionlabs.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.25,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250626,"rateLimitGroup":"Common","capabilities":["ToolCalling","Diffusion"]}]},{"provider":"@metaai","models":[{"name":"@metaai/llama-3.3-70b","description":"Previous generation model with many parameters and surprisingly fast speed.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Ultrafast"],"maxOutputTokens":32768,"contextWindow":131072,"parameterSize":"70b","releaseDate":"2024-12-06","provider":{"name":"Groq","link":"https://groq.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.59,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.79,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20241206,"rateLimitGroup":"Common","capabilities":["ToolCalling"]},{"name":"@metaai/llama-3.1-8b","description":"Cheap and fast model for less demanding tasks.","technicalInfo":{"intelligenceLevel":["Lowest"],"speedLevel":["Ultrafast"],"maxOutputTokens":131072,"contextWindow":131072,"parameterSize":"8b","releaseDate":"2024-07-23","provider":{"name":"Groq","link":"https://groq.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.05,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.08,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20240723,"rateLimitGroup":"Common","capabilities":["ToolCalling"]}]},{"provider":"@minimax","models":[{"name":"@minimax/m3","description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":524288,"contextWindow":524288,"parameterSize":null,"releaseDate":"2026-05-31","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.6,"cachedInputPerMillionTokens":0.12,"outputPerMillionTokens":2.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260531,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@minimax/m2.7","description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":204800,"parameterSize":null,"releaseDate":"2026-02-12","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.3,"cachedInputPerMillionTokens":0.06,"outputPerMillionTokens":1.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260212,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@minimax/m2.5","description":"MiniMax-M2.5 is a state-of-the-art large language model built for real-world productivity.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":204800,"parameterSize":null,"releaseDate":"2026-02-12","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.3,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260212,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@minimax/m2.1","description":"MiniMax-M2.1 is a cutting-edge, lightweight large language model designed for coding, agentic workflows, and modern application development.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":204800,"parameterSize":null,"releaseDate":"2025-12-23","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.3,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251223,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@minimax/m2","description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":8192,"contextWindow":131072,"parameterSize":null,"releaseDate":null,"provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.3,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]}]},{"provider":"@mistral","models":[{"name":"@mistral/large-2512","description":"Mistral Large 3 2512 is Mistral\u2019s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total).","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":16384,"contextWindow":268288,"parameterSize":"675b/41b","releaseDate":"2025-12-01","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.5,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251201,"rateLimitGroup":"Common","capabilities":["ToolCalling"]},{"name":"@mistral/nemo-12b-it-2407","description":"12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.","technicalInfo":{"intelligenceLevel":["Lowest"],"speedLevel":["Medium"],"maxOutputTokens":16384,"contextWindow":131072,"parameterSize":"12.2b","releaseDate":null,"provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.02,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.04,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["ToolCalling"]}]},{"provider":"@model-router","models":[{"name":"@model-router/openai:frontier","description":"Route between latest frontier OpenAI models.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-07-09","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":30,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":10,"cachedInputPerMillionTokens":1,"outputPerMillionTokens":45,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@openai/gpt-5.6-sol","flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260709,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","ModelRouter","FileInput"]},{"name":"@model-router/openai:mid","description":"Route between latest mid-tier OpenAI models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-07-09","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":0.25,"outputPerMillionTokens":15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":22.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@openai/gpt-5.6-terra","flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260709,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","ModelRouter","FileInput"]},{"name":"@model-router/openai:budget","description":"Route between latest budget OpenAI models.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-07-09","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.1,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":9,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@openai/gpt-5.6-luna","flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260709,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","ModelRouter","FileInput"]},{"name":"@model-router/grok:latest","description":"Route between latest Grok models.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":500000,"contextWindow":500000,"parameterSize":null,"releaseDate":"2026-07-08","provider":{"name":"xAI","link":"https://x.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":4,"cachedInputPerMillionTokens":1,"outputPerMillionTokens":12,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@x-ai/grok-4.5","flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260708,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","ModelRouter","FileInput"]},{"name":"@model-router/claude:mid","description":"Route between latest mid-tier Claude models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-06-30","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@anthropic/claude-5-sonnet","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260630,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","ModelRouter","FileInput"]},{"name":"@model-router/glm:latest","description":"Route between latest GLM models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-06-16","provider":{"name":"Z.ai","link":"https://z.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.4,"cachedInputPerMillionTokens":0.26,"outputPerMillionTokens":4.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@z-ai/glm-5.2","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260616,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling","ModelRouter"]},{"name":"@model-router/kimi:latest","description":"Route between latest Kimi models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":262144,"contextWindow":262144,"parameterSize":null,"releaseDate":"2026-06-12","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.95,"cachedInputPerMillionTokens":0.19,"outputPerMillionTokens":4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@moonshotai/kimi-k2.7-code","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260612,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling","ModelRouter"]},{"name":"@model-router/minimax:latest","description":"Route between latest MiniMax models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":524288,"contextWindow":524288,"parameterSize":null,"releaseDate":"2026-05-31","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.6,"cachedInputPerMillionTokens":0.12,"outputPerMillionTokens":2.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@minimax/m3","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260531,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling","ModelRouter"]},{"name":"@model-router/claude:frontier","description":"Route between latest frontier Claude models.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-05-27","provider":{"name":"Anthropic","link":"https://www.anthropic.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":25,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@anthropic/claude-4.8-opus","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260527,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","ModelRouter","FileInput"]},{"name":"@model-router/google:mid","description":"Route between latest mid-tier Google models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Ultrafast"],"maxOutputTokens":65536,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-05-19","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.5,"cachedInputPerMillionTokens":0.15,"outputPerMillionTokens":9,"audioInputPerMillionTokens":0.3,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@google/gemini-3.5-flash","flags":{"isNew":false,"isPreview":true,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260519,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","ModelRouter","FileInput"]},{"name":"@model-router/google:budget","description":"Route between latest budget Google models.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Ultrafast"],"maxOutputTokens":65536,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-05-07","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.25,"cachedInputPerMillionTokens":0.025,"outputPerMillionTokens":1.5,"audioInputPerMillionTokens":0.5,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@google/gemini-3.1-flash-lite","flags":{"isNew":false,"isPreview":true,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260507,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","ModelRouter","FileInput"]},{"name":"@model-router/deepseek:latest","description":"Route between latest DeepSeek models.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-04-24","provider":{"name":"DeepSeek","link":"https://deepseek.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":4.45,"cachedInputPerMillionTokens":0.35,"outputPerMillionTokens":5.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@deepseek/deepseek-v4-pro","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260424,"rateLimitGroup":"Common","capabilities":["ToolCalling","ModelRouter"]},{"name":"@model-router/xiaomi:frontier","description":"Route between latest frontier Xiaomi models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":131072,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-04-22","provider":{"name":"Xiaomi","link":"https://huggingface.co/XiaomiMiMo"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":3,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":262144,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.4,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@xiaomi/mimo-v2.5-pro","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260422,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling","ModelRouter"]},{"name":"@model-router/xiaomi:mid","description":"Route between latest mid-tier Xiaomi models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-04-22","provider":{"name":"Xiaomi","link":"https://huggingface.co/XiaomiMiMo"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.4,"cachedInputPerMillionTokens":0.08,"outputPerMillionTokens":2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":262144,"inputPerMillionTokens":0.8,"cachedInputPerMillionTokens":0.16,"outputPerMillionTokens":4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@xiaomi/mimo-v2.5","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260422,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","ModelRouter"]},{"name":"@model-router/xiaomi:budget","description":"Route between latest budget Xiaomi models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-04-22","provider":{"name":"Xiaomi","link":"https://huggingface.co/XiaomiMiMo"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.4,"cachedInputPerMillionTokens":0.08,"outputPerMillionTokens":2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":262144,"inputPerMillionTokens":0.8,"cachedInputPerMillionTokens":0.16,"outputPerMillionTokens":4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@xiaomi/mimo-v2.5","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260422,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","ModelRouter"]},{"name":"@model-router/google:frontier","description":"Route between latest frontier Google models.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":65536,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-02-19","provider":{"name":"Google Vertex AI","link":"https://cloud.google.com/vertex-ai?hl=pt_br"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":12,"audioInputPerMillionTokens":2,"subscriptionMultiplier":null},{"tokenThreshold":204800,"inputPerMillionTokens":4,"cachedInputPerMillionTokens":0.4,"outputPerMillionTokens":18,"audioInputPerMillionTokens":4,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@google/gemini-3.1-pro","flags":{"isNew":false,"isPreview":true,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260219,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling","ModelRouter","FileInput"]},{"name":"@model-router/claude:budget","description":"Route between latest budget-tier Claude models.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":65536,"contextWindow":200000,"parameterSize":null,"releaseDate":"2025-10-15","provider":{"name":"AWS","link":"https://aws.amazon.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.1,"outputPerMillionTokens":5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":"@anthropic/claude-4.5-haiku","flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251015,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling","ModelRouter"]},{"name":"@model-router/complexity","description":"Model Router: chooses the best models according to the complexity of the conversation.","technicalInfo":null,"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.5,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["ModelRouter"]}]},{"provider":"@moonshotai","models":[{"name":"@moonshotai/kimi-k2.7-code","description":"Kimi K2.7 Code is a coding-focused model in Moonshot AI\u0027s Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":262144,"contextWindow":262144,"parameterSize":null,"releaseDate":"2026-06-12","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.95,"cachedInputPerMillionTokens":0.19,"outputPerMillionTokens":4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260612,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@moonshotai/kimi-k2.6","description":"Kimi K2.6 is Moonshot AI\u0027s next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":32768,"contextWindow":134144,"parameterSize":null,"releaseDate":"2026-04-20","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260420,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@moonshotai/kimi-k2.5:fast","description":"Kimi K2.5 turbo is a high-performance variant of the Kimi K2.5 model, optimized for faster processing and enhanced capabilities.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Ultrafast"],"maxOutputTokens":32768,"contextWindow":134144,"parameterSize":null,"releaseDate":"2026-04-06","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":0.6,"outputPerMillionTokens":5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260406,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@moonshotai/kimi-k2.5","description":"Kimi K2.5 is Moonshot AI\u0027s native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":16384,"contextWindow":262144,"parameterSize":null,"releaseDate":"2026-01-27","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.55,"cachedInputPerMillionTokens":0.6,"outputPerMillionTokens":3,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260127,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@moonshotai/kimi-k2-thinking","description":"Kimi K2 Thinking is Moonshot AI\u2019s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Fast"],"maxOutputTokens":16384,"contextWindow":262144,"parameterSize":"MoE 1t/32b","releaseDate":"2025-11-06","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.6,"cachedInputPerMillionTokens":0.15,"outputPerMillionTokens":2.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251106,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@moonshotai/kimi-k2","description":"Model with 1tri total parameters, 32bi activated parameters, optimized for agentic intelligence.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Ultrafast"],"maxOutputTokens":16384,"contextWindow":262144,"parameterSize":"MoE 1t/32b","releaseDate":"2025-09-04","provider":{"name":"Groq","link":"https://groq.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":3,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250904,"rateLimitGroup":"Common","capabilities":["ToolCalling"]}]},{"provider":"@nex-agi","models":[{"name":"@nex-agi/nex-n2-mini","description":"Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI for coding, tool use, deep research, and long-horizon agentic workflows.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":262144,"contextWindow":262144,"parameterSize":null,"releaseDate":"2026-06-24","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.025,"cachedInputPerMillionTokens":0.0025,"outputPerMillionTokens":0.1,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260624,"rateLimitGroup":"Low","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@nex-agi/nex-n2-pro","description":"Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total, built for coding, tool use, and long-horizon agentic workflows.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":262144,"contextWindow":262144,"parameterSize":"MoE 397b/17b","releaseDate":"2026-06-08","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.25,"cachedInputPerMillionTokens":0.025,"outputPerMillionTokens":1,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260608,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]}]},{"provider":"@nvidia","models":[{"name":"@nvidia/nemotron-3-ultra","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":16400,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-06-04","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.5,"cachedInputPerMillionTokens":0.15,"outputPerMillionTokens":2.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260604,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]}]},{"provider":"@openai","models":[{"name":"@openai/gpt-5.6-sol:pro","description":"GPT-5.6 Sol is OpenAI\u0027s flagship GPT-5.6 model for complex reasoning, coding, and agentic workflows.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-07-09","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":30,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":10,"cachedInputPerMillionTokens":1,"outputPerMillionTokens":45,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260709,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.6-sol","description":"GPT-5.6 Sol is OpenAI\u0027s flagship GPT-5.6 model for complex reasoning, coding, and agentic workflows.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-07-09","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":30,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":10,"cachedInputPerMillionTokens":1,"outputPerMillionTokens":45,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260709,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.6-terra:pro","description":"GPT-5.6 Terra is OpenAI\u0027s balanced GPT-5.6 model for everyday coding, reasoning, and agentic tasks.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-07-09","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":0.25,"outputPerMillionTokens":15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":22.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260709,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.6-terra","description":"GPT-5.6 Terra is OpenAI\u0027s balanced GPT-5.6 model for everyday coding, reasoning, and agentic tasks.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-07-09","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":0.25,"outputPerMillionTokens":15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":22.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260709,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.6-luna:pro","description":"GPT-5.6 Luna is OpenAI\u0027s fast, cost-efficient GPT-5.6 model for high-volume chat, classification, and lightweight agentic workflows.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-07-09","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.1,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":9,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260709,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.6-luna","description":"GPT-5.6 Luna is OpenAI\u0027s fast, cost-efficient GPT-5.6 model for high-volume chat, classification, and lightweight agentic workflows.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-07-09","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.1,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":9,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260709,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.5-pro","description":"GPT-5.5 Pro is OpenAI\u2019s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M\u002B token context window.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":131072,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-04-24","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":30,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":180,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260424,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.5","description":"GPT-5.5 is OpenAI\u2019s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning and higher reliability.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-04-24","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":30,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":10,"cachedInputPerMillionTokens":1,"outputPerMillionTokens":45,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260424,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.4-mini","description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2026-03-17","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.75,"cachedInputPerMillionTokens":0.075,"outputPerMillionTokens":4.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260317,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.4-nano","description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.","technicalInfo":{"intelligenceLevel":["Low"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2026-03-17","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.2,"cachedInputPerMillionTokens":0.02,"outputPerMillionTokens":1.25,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260317,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.4-pro","description":"GPT-5.4 Pro is OpenAI\u0027s most advanced model, building on GPT-5.4\u0027s unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slowest"],"maxOutputTokens":128000,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-03-05","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":30,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":180,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260305,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@openai/gpt-5.4","description":"GPT-5.4 is OpenAI\u2019s latest frontier model, unifying the Codex and GPT lines into a single system.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-03-05","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":0.25,"outputPerMillionTokens":15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":278528,"inputPerMillionTokens":5,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":22.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260305,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.3-chat","description":"GPT-5.3 Chat is an update to ChatGPT\u0027s most-used model that makes everyday conversations smoother, more useful, and more directly helpful.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2026-03-03","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.75,"cachedInputPerMillionTokens":0.175,"outputPerMillionTokens":14,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260303,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.3-codex","description":"GPT-5.3-Codex is OpenAI\u2019s most advanced agentic coding model. It pairs the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2026-01-14","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.75,"cachedInputPerMillionTokens":0.175,"outputPerMillionTokens":14,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260114,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.2-codex","description":"GPT-5.2-Codex is an enhanced version of GPT-5.1-Codex, optimized for software engineering and coding tasks.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2026-01-14","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.75,"cachedInputPerMillionTokens":0.175,"outputPerMillionTokens":14,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260114,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.2-pro","description":"GPT-5.2 Pro is OpenAI\u0027s most advanced model, featuring significant upgrades in agentic coding and long-context capabilities compared to GPT-5 Pro.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slowest"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-12-11","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":21,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":168,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251211,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.2-chat","description":"GPT-5.2 Chat (also known as Instant) is the fast and lightweight version of the 5.2 family, built for low-latency chatting while maintaining strong general intelligence.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-12-10","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.75,"cachedInputPerMillionTokens":0.175,"outputPerMillionTokens":14,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251210,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.2","description":"GPT-5.2 is the newest frontier-level model in the GPT-5 line, providing enhanced agentic abilities and better long-context performance than GPT-5.1.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-12-10","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.75,"cachedInputPerMillionTokens":0.175,"outputPerMillionTokens":14,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251210,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.1-codex-max","description":"GPT-5.1-Codex-Max is OpenAI\u2019s latest agentic coding model, designed for long-running, high-context software development tasks.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-12-04","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.25,"cachedInputPerMillionTokens":0.125,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251204,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.1-codex","description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-11-13","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.25,"cachedInputPerMillionTokens":0.125,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251113,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.1-chat","description":"GPT-5.1 Chat (also known as Instant) is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Fast"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-11-13","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.25,"cachedInputPerMillionTokens":0.125,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251113,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5.1","description":"GPT-5.1 is the newest top-tier model in the GPT-5 series, featuring enhanced general reasoning, better instruction following, and a more natural conversational tone compared to GPT-5.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-11-13","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.25,"cachedInputPerMillionTokens":0.125,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251113,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5-codex","description":"GPT-5-Codex is a specialized version of GPT-5 tailored for software engineering and coding tasks.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-09-23","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.25,"cachedInputPerMillionTokens":0.125,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250923,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5","description":"OpenAI\u0027s newest flagship model for coding, reasoning, and agentic tasks across domains.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-08-07","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.25,"cachedInputPerMillionTokens":0.125,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250807,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-5-chat","description":"GPT-5 snapshot currently used by OpenAI\u0027s ChatGPT.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-08-07","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.25,"cachedInputPerMillionTokens":0.125,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250807,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@openai/gpt-5-mini","description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-08-07","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.25,"cachedInputPerMillionTokens":0.025,"outputPerMillionTokens":2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250807,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@openai/gpt-5-nano","description":"OpenAI\u0027s fastest, cheapest version of GPT-5.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Medium"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":"2025-08-07","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.05,"cachedInputPerMillionTokens":0.005,"outputPerMillionTokens":0.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250807,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@openai/gpt-oss-120b","description":"OpenAI\u0027s flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 120 billion parameters and 128 experts.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Ultrafast"],"maxOutputTokens":32768,"contextWindow":131072,"parameterSize":"MoE 120b/6b","releaseDate":"2025-08-05","provider":{"name":"Groq","link":"https://groq.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.15,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.75,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250805,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@openai/gpt-oss-20b","description":"OpenAI\u0027s flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 20 billion parameters and 128 experts.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Ultrafast"],"maxOutputTokens":32768,"contextWindow":131072,"parameterSize":"MoE 20b/6b","releaseDate":"2025-08-05","provider":{"name":"Groq","link":"https://groq.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.1,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250805,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@openai/o3","description":"A well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":100000,"contextWindow":200000,"parameterSize":null,"releaseDate":"2025-04-16","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":8,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250416,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/o4-mini","description":"Optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":100000,"contextWindow":200000,"parameterSize":null,"releaseDate":"2025-04-16","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.1,"cachedInputPerMillionTokens":0.275,"outputPerMillionTokens":4.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250416,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@openai/gpt-4.1","description":"Versatile, highly intelligent, and top-of-the-line. One of the most capable models currently available.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Slow"],"maxOutputTokens":32768,"contextWindow":1047576,"parameterSize":null,"releaseDate":"2025-04-14","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":8,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250414,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@openai/gpt-4.1-mini","description":"Fast and cheap for focused tasks.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Slow"],"maxOutputTokens":32768,"contextWindow":1047576,"parameterSize":null,"releaseDate":"2025-04-14","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.4,"cachedInputPerMillionTokens":0.1,"outputPerMillionTokens":1.6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250414,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@openai/gpt-4.1-nano","description":"The fastest and cheapest GPT 4.1 model.","technicalInfo":{"intelligenceLevel":["Low"],"speedLevel":["Slow"],"maxOutputTokens":32768,"contextWindow":1047576,"parameterSize":null,"releaseDate":"2025-04-14","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.1,"cachedInputPerMillionTokens":0.025,"outputPerMillionTokens":0.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250414,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@openai/o3-mini","description":"o3-mini provides high intelligence at the same cost and latency targets of previous versions of o-mini series.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":100000,"contextWindow":200000,"parameterSize":null,"releaseDate":"2025-01-31","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.1,"cachedInputPerMillionTokens":0.55,"outputPerMillionTokens":4.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250131,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@openai/gpt-4o-mini","description":"Smaller version of 4o, optimized for everyday tasks.","technicalInfo":{"intelligenceLevel":["Low"],"speedLevel":["Slow"],"maxOutputTokens":16384,"contextWindow":128000,"parameterSize":null,"releaseDate":"2024-07-18","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.15,"cachedInputPerMillionTokens":0.075,"outputPerMillionTokens":0.6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20240718,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@openai/gpt-4o","description":"Dedicated to tasks requiring reasoning for mathematical and logical problem solving.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":16384,"contextWindow":128000,"parameterSize":null,"releaseDate":"2024-05-13","provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":1.25,"outputPerMillionTokens":10,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20240513,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@openai/gpt-5.1-codex-mini","description":"GPT-5.1-Codex-Mini is a more compact and faster variant of GPT-5.1-Codex.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Slow"],"maxOutputTokens":128000,"contextWindow":400000,"parameterSize":null,"releaseDate":null,"provider":{"name":"Open AI","link":"https://openai.com"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.25,"cachedInputPerMillionTokens":0.025,"outputPerMillionTokens":2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]}]},{"provider":"@perplexity","models":[{"name":"@perplexity/sonar-pro","description":"Sonar Pro is an enterprise-grade API from Perplexity, built for advanced, multi-step queries with added extensibility.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":131072,"parameterSize":null,"releaseDate":"2025-03-07","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":3,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250307,"rateLimitGroup":"Common","capabilities":["Thinking"]},{"name":"@perplexity/sonar","description":"Sonar is Perplexity\u2019s lightweight, affordable, and fast question-answering model, now featuring citations and customizable sources.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":131072,"parameterSize":null,"releaseDate":"2025-01-27","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250127,"rateLimitGroup":"Common","capabilities":["0"]}]},{"provider":"@poolside","models":[{"name":"@poolside/laguna-xs-2.1","description":"Laguna XS 2.1 is Poolside\u0027s compact coding agent model in the 33B-A3B category, combining tool calling and reasoning for agentic software engineering tasks.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":32768,"contextWindow":268288,"parameterSize":"MoE 33b/3b","releaseDate":"2026-07-02","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.1,"cachedInputPerMillionTokens":0.05,"outputPerMillionTokens":0.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260702,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]}]},{"provider":"@qwen","models":[{"name":"@qwen/qwen3.7-plus","description":"Qwen3.7-Plus is a cost-effective model in Alibaba\u0027s Qwen3.7 series. It supports text and image input with text output, building on the series\u0027 text capabilities with a comprehensive upgrade to its vision-language abilities.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":65536,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-06-03","provider":{"name":"Alibaba","link":"https://www.alibabacloud.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.4,"cachedInputPerMillionTokens":0.08,"outputPerMillionTokens":1.6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":256000,"inputPerMillionTokens":1.2,"cachedInputPerMillionTokens":0.24,"outputPerMillionTokens":4.8,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260603,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling","FileInput"]},{"name":"@qwen/qwen3.7-max","description":"Qwen3.7-Max is the flagship model in Alibaba\u0027s Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous agents.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":65536,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-05-21","provider":{"name":"Alibaba","link":"https://www.alibabacloud.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":0.25,"outputPerMillionTokens":7.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260521,"rateLimitGroup":"Common","capabilities":["ToolCalling"]},{"name":"@qwen/qwen3.6-27b","description":"Qwen3.6 27B is a dense 27-billion-parameter model from Alibaba Qwen, designed for agentic coding, long-context reasoning, and multimodal workflows.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":82944,"contextWindow":268288,"parameterSize":null,"releaseDate":"2026-04-27","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.32,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":3.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260427,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@qwen/qwen3.6-plus","description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":65536,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-04-02","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.5,"cachedInputPerMillionTokens":0.05,"outputPerMillionTokens":3,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":262144,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260402,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@qwen/qwen3.5-9b","description":"Qwen3.5 9B is an efficient multimodal model from the Qwen3.5 family for low-cost reasoning, coding, and visual understanding workloads.","technicalInfo":{"intelligenceLevel":["Low"],"speedLevel":["Fast"],"maxOutputTokens":82944,"contextWindow":268288,"parameterSize":null,"releaseDate":"2026-03-10","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.04,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.15,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260310,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@qwen/qwen3.5-27b","description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":16384,"contextWindow":268288,"parameterSize":null,"releaseDate":"2026-02-25","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.3,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":2.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260225,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@qwen/qwen3.5-flash","description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":65536,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-02-25","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.1,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260225,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@qwen/qwen3.5-397b-a17b","description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":16384,"contextWindow":268288,"parameterSize":null,"releaseDate":"2026-02-16","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.6,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":3.6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260216,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@qwen/qwen3.5-plus","description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":65536,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-02-16","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.5,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":3,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260216,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput","Thinking","ToolCalling"]},{"name":"@qwen/qwen3-max","description":"Qwen3-Max improves instruction following, multilingual ability, and tool use; reduced hallucinations.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":16384,"contextWindow":268288,"parameterSize":null,"releaseDate":"2025-09-23","provider":{"name":"Alibaba","link":"https://www.alibabacloud.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.2,"cachedInputPerMillionTokens":0.24,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250923,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@qwen/qwen3-coder-plus","description":"Powered by Qwen3, this is a powerful Coding Agent that excels in tool calling and environment interaction to achieve autonomous programming.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":16384,"contextWindow":268288,"parameterSize":null,"releaseDate":null,"provider":{"name":"Alibaba","link":"https://www.alibabacloud.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["ToolCalling"]},{"name":"@qwen/qwen3-next-80b-a3b-it","description":"An 80\u202FB-parameter instruction model with hybrid attention and Mixture\u2011of\u2011Experts, optimized for ultra\u2011long contexts up to 262\u202Fk tokens.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Fast"],"maxOutputTokens":16384,"contextWindow":268288,"parameterSize":"MoE 80/3b","releaseDate":null,"provider":{"name":"DeepInfra","link":"https://deepinfra.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.14,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["ToolCalling"]},{"name":"@qwen/qwen3-next-80b-a3b-think","description":"A 80\u202FB\u2011parameter \u201Cthinking\u2011only\u201D model with hybrid attention and high\u2011sparsity MoE, designed for deep reasoning over ultra\u2011long contexts.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Medium"],"maxOutputTokens":16384,"contextWindow":268288,"parameterSize":"MoE 80/3b","releaseDate":null,"provider":{"name":"DeepInfra","link":"https://deepinfra.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.14,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@qwen/qwen3-coder-480b-a35b-it","description":"Qwen3-Coder-480B-A35B-Instruct is the Qwen3\u0027s most agentic code model, featuring Significant Performance on Agentic Coding, Agentic Browser-Use and other foundational coding tasks, achieving results comparable to Claude Sonnet.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":16384,"contextWindow":268288,"parameterSize":"MoE 480/35b","releaseDate":null,"provider":{"name":"DeepInfra","link":"https://deepinfra.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.29,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":1.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["ToolCalling"]},{"name":"@qwen/qwen3-32b","description":"32B-parameter LLM with a 131K-token context window, offering advanced chain-of-thought reasoning, seamless tool calling, native JSON outputs, and robust multilingual fluency.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Ultrafast"],"maxOutputTokens":40960,"contextWindow":131072,"parameterSize":"32b","releaseDate":null,"provider":{"name":"Groq","link":"https://groq.com/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.29,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.59,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]}]},{"provider":"@reka","models":[{"name":"@reka/reka-edge","description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video\u002Btext inputs and generates text outputs. ","technicalInfo":{"intelligenceLevel":["Lowest"],"speedLevel":["Fast"],"maxOutputTokens":16384,"contextWindow":16384,"parameterSize":null,"releaseDate":"2026-03-20","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.1,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.1,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260320,"rateLimitGroup":"Common","capabilities":["ImageInput","VideoInput"]}]},{"provider":"@tencent","models":[{"name":"@tencent/hy3","description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent, built for reasoning, agentic workflows, and real-world production use.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":131072,"contextWindow":268288,"parameterSize":"MoE 295b/21b","releaseDate":"2026-07-06","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.14,"cachedInputPerMillionTokens":0.035,"outputPerMillionTokens":0.58,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260706,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]}]},{"provider":"@venice","models":[{"name":"@venice/dphn-24b-uncensored","description":"Venice Uncensored is a fine-tuned version of Mistral-Small-24B-Instruct-2501, created by dphn.ai in partnership with Venice.ai.","technicalInfo":{"intelligenceLevel":["Medium"],"speedLevel":["Medium"],"maxOutputTokens":8192,"contextWindow":131072,"parameterSize":null,"releaseDate":null,"provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.1,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":0.45,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":0,"rateLimitGroup":"Common","capabilities":["Uncensored"]}]},{"provider":"@x-ai","models":[{"name":"@x-ai/grok-4.5","description":"Grok 4.5 is xAI\u0027s smartest model with frontier performance on coding, knowledge work, and STEM.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":500000,"contextWindow":500000,"parameterSize":null,"releaseDate":"2026-07-08","provider":{"name":"xAI","link":"https://x.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.5,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":4,"cachedInputPerMillionTokens":1,"outputPerMillionTokens":12,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":true,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260708,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@x-ai/grok-build-0.1","description":"Grok Build 0.1 is xAI\u2019s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":256000,"contextWindow":256000,"parameterSize":null,"releaseDate":"2026-05-20","provider":{"name":"xAI","link":"https://x.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.4,"outputPerMillionTokens":4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260520,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]},{"name":"@x-ai/grok-4.3","description":"Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual logic.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Medium"],"maxOutputTokens":131072,"contextWindow":1000000,"parameterSize":null,"releaseDate":"2026-04-30","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.25,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":2.5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":2.5,"cachedInputPerMillionTokens":0.4,"outputPerMillionTokens":5,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260430,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling","FileInput"]},{"name":"@x-ai/grok-4.20-multi-agent","description":"Grok 4.20 Multi-Agent Beta is a variant of xAI\u2019s Grok 4.20 designed for collaborative, agent-based workflows.","technicalInfo":{"intelligenceLevel":["Highest"],"speedLevel":["Fast"],"maxOutputTokens":2048000,"contextWindow":2048000,"parameterSize":null,"releaseDate":"2026-03-31","provider":{"name":"xAI","link":"https://x.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":4,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":12,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260331,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking"]},{"name":"@x-ai/grok-4.20-reasoning","description":"Grok 4.20 Beta is xAI\u0027s newest flagship model with industry-leading speed and agentic tool calling capabilities.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":2048000,"contextWindow":2048000,"parameterSize":null,"releaseDate":"2026-03-31","provider":{"name":"xAI","link":"https://x.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":4,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":12,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260331,"rateLimitGroup":"Common","capabilities":["ImageInput","Thinking","ToolCalling"]},{"name":"@x-ai/grok-4.20","description":"Grok 4.20 Beta is xAI\u0027s newest flagship model with industry-leading speed and agentic tool calling capabilities.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":2048000,"contextWindow":2048000,"parameterSize":null,"releaseDate":"2026-03-12","provider":{"name":"xAI","link":"https://x.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":200000,"inputPerMillionTokens":4,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":12,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260312,"rateLimitGroup":"Common","capabilities":["ImageInput","ToolCalling"]}]},{"provider":"@xiaomi","models":[{"name":"@xiaomi/mimo-v2.5-pro","description":"MiMo-V2.5-Pro is Xiaomi\u2019s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Medium"],"maxOutputTokens":131072,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-04-22","provider":{"name":"Xiaomi","link":"https://huggingface.co/XiaomiMiMo"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":3,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":262144,"inputPerMillionTokens":2,"cachedInputPerMillionTokens":0.4,"outputPerMillionTokens":6,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260422,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@xiaomi/mimo-v2.5","description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":1050000,"parameterSize":null,"releaseDate":"2026-04-22","provider":{"name":"Xiaomi","link":"https://huggingface.co/XiaomiMiMo"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.4,"cachedInputPerMillionTokens":0.08,"outputPerMillionTokens":2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null},{"tokenThreshold":262144,"inputPerMillionTokens":0.8,"cachedInputPerMillionTokens":0.16,"outputPerMillionTokens":4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260422,"rateLimitGroup":"Common","capabilities":["AudioInput","ImageInput","VideoInput","Thinking","ToolCalling"]}]},{"provider":"@z-ai","models":[{"name":"@z-ai/glm-5.2","description":"GLM-5.2 is Z.ai\u0027s flagship model for long-horizon tasks, with a usable 1M-token context window for project-level engineering context and long-running agent workflows.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":1048576,"parameterSize":null,"releaseDate":"2026-06-16","provider":{"name":"Z.ai","link":"https://z.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.4,"cachedInputPerMillionTokens":0.26,"outputPerMillionTokens":4.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260616,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@z-ai/glm-5.1","description":"GLM-5.1 represents a major advance in coding ability, with especially notable improvements in tackling long-horizon tasks.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":204800,"parameterSize":null,"releaseDate":"2026-04-07","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.4,"cachedInputPerMillionTokens":0.3,"outputPerMillionTokens":4.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260407,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@z-ai/glm-5-turbo","description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Ultrafast"],"maxOutputTokens":131072,"contextWindow":204800,"parameterSize":null,"releaseDate":"2026-03-15","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1.2,"cachedInputPerMillionTokens":0.24,"outputPerMillionTokens":4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260315,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@z-ai/glm-5","description":"GLM-5 is Z.ai\u2019s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":204800,"parameterSize":null,"releaseDate":"2026-02-11","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":1,"cachedInputPerMillionTokens":0.2,"outputPerMillionTokens":3.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260211,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@z-ai/glm-4.7-flash","description":"As a SOTA 30B-class model, GLM-4.7-Flash provides a new option that balances efficiency and performance.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":204800,"parameterSize":null,"releaseDate":"2026-01-19","provider":null},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.07,"cachedInputPerMillionTokens":0.01,"outputPerMillionTokens":0.4,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20260119,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@z-ai/glm-4.7","description":"GLM-4.7 is Z.AI\u2019s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":131072,"contextWindow":204800,"parameterSize":"MoE 355b/32b","releaseDate":"2025-12-22","provider":{"name":"Z.ai","link":"https://z.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.6,"cachedInputPerMillionTokens":0.11,"outputPerMillionTokens":2.2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":false,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20251222,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]},{"name":"@z-ai/glm-4.6","description":"GLM\u20114.6 is a high\u2011capacity LLM with a 200K\u2011token context window, strong coding and reasoning abilities, and enhanced tool\u2011use capabilities.","technicalInfo":{"intelligenceLevel":["High"],"speedLevel":["Fast"],"maxOutputTokens":16384,"contextWindow":204800,"parameterSize":"MoE 355b/32b","releaseDate":"2025-09-30","provider":{"name":"Z.ai","link":"https://z.ai/"}},"pricing":[{"tokenThreshold":0,"inputPerMillionTokens":0.6,"cachedInputPerMillionTokens":null,"outputPerMillionTokens":2,"audioInputPerMillionTokens":null,"subscriptionMultiplier":null}],"stability":["Stable"],"routingModel":null,"flags":{"isNew":false,"isPreview":false,"isDeprecating":true,"isFree":false,"isDiscounted":false,"isAvailable":true},"order":20250930,"rateLimitGroup":"Common","capabilities":["Thinking","ToolCalling"]}]}]}