{"source":"models.dev","sourceUrl":"https://models.dev/api.json?type=all","license":"MIT","updatedAt":"2026-10-02T06:15:29.911Z","baselineAt":"2026-09-29T06:15:06.574Z","models":[{"providerId":"alibaba","providerName":"Alibaba","id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","type":null,"cost":{"input":0.2,"output":0.4,"cache_read":0.04},"limit":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"deepseek-flash","canonicalModelId":"deepseek/deepseek-v4-flash-0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","knowledge":"2025-05","releaseDate":"2026-07-31","lastUpdated":"2026-07-31"},{"providerId":"alibaba","providerName":"Alibaba","id":"glm-5.2","name":"GLM-5.2","type":null,"cost":{"input":1.4,"output":4.4,"cache_read":0.28,"cache_write":0},"limit":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"glm","canonicalModelId":"zhipuai/glm-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","releaseDate":"2026-06-13","lastUpdated":"2026-06-13"},{"providerId":"alibaba","providerName":"Alibaba","id":"kimi-k3","name":"Kimi K3","type":null,"cost":{"input":3,"output":15,"cache_read":0.3},"limit":{"context":1048576,"output":1048576},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"kimi-k3","canonicalModelId":"moonshotai/kimi-k3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","releaseDate":"2026-07-16","lastUpdated":"2026-07-16"},{"providerId":"alibaba","providerName":"Alibaba","id":"qvq-max","name":"QVQ Max","type":null,"cost":{"input":1.2,"output":4.8},"limit":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qvq","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","knowledge":"2024-04","releaseDate":"2025-03-25","lastUpdated":"2025-03-25"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-flash","name":"Qwen Flash","type":null,"cost":{"input":0.05,"output":0.4},"limit":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","knowledge":"2024-04","releaseDate":"2025-07-28","lastUpdated":"2025-07-28"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-max","name":"Qwen Max","type":null,"cost":{"input":1.6,"output":6.4},"limit":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","knowledge":"2024-04","releaseDate":"2024-04-03","lastUpdated":"2025-01-25"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-mt-plus","name":"Qwen-MT Plus","type":null,"cost":{"input":2.46,"output":7.37},"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Translation model for multilingual conversion, localization, and cross-language workflows","knowledge":"2024-04","releaseDate":"2025-01","lastUpdated":"2025-01"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-mt-turbo","name":"Qwen-MT Turbo","type":null,"cost":{"input":0.16,"output":0.49},"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Translation model for multilingual conversion, localization, and cross-language workflows","knowledge":"2024-04","releaseDate":"2025-01","lastUpdated":"2025-01"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-omni-turbo","name":"Qwen-Omni Turbo","type":null,"cost":{"input":0.07,"output":0.27},"limit":{"context":32768,"output":2048},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","knowledge":"2024-04","releaseDate":"2025-01-19","lastUpdated":"2025-03-26"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-omni-turbo-realtime","name":"Qwen-Omni Turbo Realtime","type":null,"cost":{"input":0.27,"output":1.07},"limit":{"context":32768,"output":2048},"modalities":{"input":["text","image","audio"],"output":["text","audio"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","knowledge":"2024-04","releaseDate":"2025-05-08","lastUpdated":"2025-05-08"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-plus","name":"Qwen Plus","type":null,"cost":{"input":0.4,"output":1.2,"reasoning":4},"limit":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","knowledge":"2024-04","releaseDate":"2024-01-25","lastUpdated":"2025-09-11"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-plus-character-ja","name":"Qwen Plus Character (Japanese)","type":null,"cost":{"input":0.5,"output":1.4},"limit":{"context":8192,"output":512},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","knowledge":"2024-04","releaseDate":"2024-01","lastUpdated":"2024-01"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-turbo","name":"Qwen Turbo","type":null,"cost":{"input":0.05,"output":0.2,"reasoning":0.5},"limit":{"context":1000000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","knowledge":"2024-04","releaseDate":"2024-11-01","lastUpdated":"2025-04-28"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-vl-max","name":"Qwen-VL Max","type":null,"cost":{"input":0.8,"output":3.2},"limit":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","knowledge":"2024-04","releaseDate":"2024-04-08","lastUpdated":"2025-08-13"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-vl-ocr","name":"Qwen-VL OCR","type":null,"cost":{"input":0.72,"output":0.72},"limit":{"context":34096,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"OCR model for extracting structured text from documents and screenshots","knowledge":"2024-04","releaseDate":"2024-10-28","lastUpdated":"2025-04-13"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen-vl-plus","name":"Qwen-VL Plus","type":null,"cost":{"input":0.21,"output":0.63},"limit":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","knowledge":"2024-04","releaseDate":"2024-01-25","lastUpdated":"2025-08-15"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen2-5-14b-instruct","name":"Qwen2.5 14B Instruct","type":null,"cost":{"input":0.35,"output":1.4},"limit":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","knowledge":"2024-04","releaseDate":"2024-09","lastUpdated":"2024-09"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen2-5-32b-instruct","name":"Qwen2.5 32B Instruct","type":null,"cost":{"input":0.7,"output":2.8},"limit":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","knowledge":"2024-04","releaseDate":"2024-09","lastUpdated":"2024-09"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen2-5-72b-instruct","name":"Qwen2.5 72B Instruct","type":null,"cost":{"input":1.4,"output":5.6},"limit":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","knowledge":"2024-04","releaseDate":"2024-09","lastUpdated":"2024-09"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen2-5-7b-instruct","name":"Qwen2.5 7B Instruct","type":null,"cost":{"input":0.175,"output":0.7},"limit":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","knowledge":"2024-04","releaseDate":"2024-09","lastUpdated":"2024-09"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen2-5-omni-7b","name":"Qwen2.5-Omni 7B","type":null,"cost":{"input":0.1,"output":0.4},"limit":{"context":32768,"output":2048},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","knowledge":"2024-04","releaseDate":"2024-12","lastUpdated":"2024-12"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen2-5-vl-72b-instruct","name":"Qwen2.5-VL 72B Instruct","type":null,"cost":{"input":2.8,"output":8.4},"limit":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","knowledge":"2024-04","releaseDate":"2024-09","lastUpdated":"2024-09"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL 7B Instruct","type":null,"cost":{"input":0.35,"output":1.05},"limit":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","knowledge":"2024-04","releaseDate":"2024-09","lastUpdated":"2024-09"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-14b","name":"Qwen3 14B","type":null,"cost":{"input":0.35,"output":1.4,"reasoning":4.2},"limit":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","knowledge":"2025-04","releaseDate":"2025-04","lastUpdated":"2025-04"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-235b-a22b","name":"Qwen3 235B-A22B","type":null,"cost":{"input":0.7,"output":2.8,"reasoning":8.4},"limit":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","knowledge":"2025-04","releaseDate":"2025-04","lastUpdated":"2025-04"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-32b","name":"Qwen3 32B","type":null,"cost":{"input":0.7,"output":2.8,"reasoning":8.4},"limit":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","knowledge":"2025-04","releaseDate":"2025-04","lastUpdated":"2025-04"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-8b","name":"Qwen3 8B","type":null,"cost":{"input":0.18,"output":0.7,"reasoning":2.1},"limit":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","knowledge":"2025-04","releaseDate":"2025-04","lastUpdated":"2025-04"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-asr-flash","name":"Qwen3-ASR Flash","type":null,"cost":{"input":0.035,"output":0.035},"limit":{"context":53248,"output":4096},"modalities":{"input":["audio"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Speech transcription model for accurate audio-to-text and captioning workflows","knowledge":"2024-04","releaseDate":"2025-09-08","lastUpdated":"2025-09-08"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","type":null,"cost":{"input":0.45,"output":2.25,"tiers":[{"input":0.75,"output":3.75,"tier":{"type":"context","size":32000}},{"input":1.2,"output":6,"tier":{"type":"context","size":128000}}]},"limit":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","knowledge":"2025-04","releaseDate":"2025-04","lastUpdated":"2025-04"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","type":null,"cost":{"input":1.5,"output":7.5,"tiers":[{"input":2.7,"output":13.5,"tier":{"type":"context","size":32000}},{"input":4.5,"output":22.5,"tier":{"type":"context","size":128000}}]},"limit":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","knowledge":"2025-04","releaseDate":"2025-04","lastUpdated":"2025-04"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","type":null,"cost":{"input":0.3,"output":1.5},"limit":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen coding model for software agents, repository edits, and code reasoning","knowledge":"2025-04","releaseDate":"2025-07-28","lastUpdated":"2025-07-28"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","type":null,"cost":{"input":1,"output":5},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","knowledge":"2025-04","releaseDate":"2025-07-23","lastUpdated":"2025-07-23"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-livetranslate-flash-realtime","name":"Qwen3-LiveTranslate Flash Realtime","type":null,"cost":{"input":10,"output":10},"limit":{"context":53248,"output":4096},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Speech generation model for controllable voice, narration, and audio delivery","knowledge":"2024-04","releaseDate":"2025-09-22","lastUpdated":"2025-09-22"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-max","name":"Qwen3 Max","type":null,"cost":{"input":1.2,"output":6},"limit":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","knowledge":"2025-04","releaseDate":"2025-09-23","lastUpdated":"2025-09-23"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","type":null,"cost":{"input":0.5,"output":2},"limit":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","knowledge":"2025-04","releaseDate":"2025-09","lastUpdated":"2025-09"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","type":null,"cost":{"input":0.5,"output":6},"limit":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","knowledge":"2025-04","releaseDate":"2025-09","lastUpdated":"2025-09"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-omni-flash","name":"Qwen3-Omni Flash","type":null,"cost":{"input":0.43,"output":1.66},"limit":{"context":65536,"output":16384},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","knowledge":"2024-04","releaseDate":"2025-09-15","lastUpdated":"2025-09-15"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-omni-flash-realtime","name":"Qwen3-Omni Flash Realtime","type":null,"cost":{"input":0.52,"output":1.99},"limit":{"context":65536,"output":16384},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","knowledge":"2024-04","releaseDate":"2025-09-15","lastUpdated":"2025-09-15"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-vl-235b-a22b","name":"Qwen3-VL 235B-A22B","type":null,"cost":{"input":0.7,"output":2.8,"reasoning":8.4},"limit":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","knowledge":"2025-04","releaseDate":"2025-04","lastUpdated":"2025-04"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-vl-30b-a3b","name":"Qwen3-VL 30B-A3B","type":null,"cost":{"input":0.2,"output":0.8,"reasoning":2.4},"limit":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","knowledge":"2025-04","releaseDate":"2025-04","lastUpdated":"2025-04"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3-vl-plus","name":"Qwen3-VL Plus","type":null,"cost":{"input":0.2,"output":1.6,"reasoning":4.8},"limit":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","knowledge":"2025-04","releaseDate":"2025-09-23","lastUpdated":"2025-09-23"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","type":null,"cost":{"input":0.4,"output":3.2},"limit":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","releaseDate":"2026-02-23","lastUpdated":"2026-02-23"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.5-27b","name":"Qwen3.5 27B","type":null,"cost":{"input":0.3,"output":2.4},"limit":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","releaseDate":"2026-02-23","lastUpdated":"2026-02-23"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","type":null,"cost":{"input":0.25,"output":2},"limit":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","releaseDate":"2026-02-23","lastUpdated":"2026-02-23"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","type":null,"cost":{"input":0.6,"output":3.6},"limit":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","releaseDate":"2026-02-15","lastUpdated":"2026-02-15"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.5-flash","name":"Qwen3.5 Flash","type":null,"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125},"limit":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","canonicalModelId":"alibaba/qwen3.5-flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","releaseDate":"2026-02-23","lastUpdated":"2026-02-23"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.5-plus","name":"Qwen3.5 Plus","type":null,"cost":{"input":0.4,"output":2.4,"reasoning":2.4},"limit":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","knowledge":"2025-04","releaseDate":"2026-02-16","lastUpdated":"2026-02-16"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.6-27b","name":"Qwen3.6 27B","type":null,"cost":{"input":0.6,"output":3.6},"limit":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","releaseDate":"2026-04-22","lastUpdated":"2026-04-22"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","type":null,"cost":{"input":0.248,"output":1.485},"limit":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","releaseDate":"2026-04-17","lastUpdated":"2026-04-17"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.6-flash","name":"Qwen3.6 Flash","type":null,"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375},"limit":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen3.6","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","releaseDate":"2026-04-27","lastUpdated":"2026-04-27"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.6-max-preview","name":"Qwen3.6 Max Preview","type":null,"cost":{"input":1.3,"output":7.8,"cache_read":0.13,"cache_write":1.625},"limit":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","knowledge":"2025-04","releaseDate":"2026-04-20","lastUpdated":"2026-04-20"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.6-plus","name":"Qwen3.6 Plus","type":null,"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"limit":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","knowledge":"2025-04","releaseDate":"2026-04-02","lastUpdated":"2026-04-02"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.7-flash","name":"Qwen3.7 Flash","type":null,"cost":{"input":0.03,"output":0.13,"cache_read":0.003,"cache_write":0.0375,"tiers":[{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125,"tier":{"type":"context","size":32000}},{"input":0.2,"output":0.8,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":256000}}]},"limit":{"context":1000000,"output":131072,"input":991808},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","canonicalModelId":"alibaba/qwen3.7-flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","releaseDate":"2026-07-15","lastUpdated":"2026-07-15"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.7-max","name":"Qwen3.7 Max","type":null,"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"limit":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","releaseDate":"2026-05-21","lastUpdated":"2026-05-21"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.7-plus","name":"Qwen3.7 Plus","type":null,"cost":{"input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5}},"limit":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","knowledge":"2025-04","releaseDate":"2026-06-02","lastUpdated":"2026-06-04"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.8-flash","name":"Qwen3.8 Flash","type":null,"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"limit":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","canonicalModelId":"alibaba/qwen3.8-flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","releaseDate":"2026-08-26","lastUpdated":"2026-08-26"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.8-max","name":"Qwen3.8 Max","type":null,"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"limit":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","canonicalModelId":"alibaba/qwen3.8-max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","releaseDate":"2026-08-03","lastUpdated":"2026-08-03"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","type":null,"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"limit":{"context":1000000,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","canonicalModelId":"alibaba/qwen3.8-omni-flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","releaseDate":"2026-09-17","lastUpdated":"2026-09-17"},{"providerId":"alibaba","providerName":"Alibaba","id":"qwq-plus","name":"QwQ Plus","type":null,"cost":{"input":0.8,"output":2.4},"limit":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://www.alibabacloud.com/help/en/model-studio/models","family":"qwen","description":"Qwen reasoning model for deliberate problem solving, math, and coding","knowledge":"2024-04","releaseDate":"2025-03-05","lastUpdated":"2025-03-05"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"amazon.nova-2-lite-v1:0","name":"Nova 2 Lite","type":null,"cost":{"input":0.33,"output":2.75,"cache_read":0.0825,"cache_write":0.33},"limit":{"context":1000000,"output":65535},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova","canonicalModelId":"amazon/nova-2-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","knowledge":"2025-10","releaseDate":"2025-12-02","lastUpdated":"2025-12-01"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"amazon.nova-lite-v1:0","name":"Nova Lite","type":null,"cost":{"input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0.06},"limit":{"context":300000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-lite","canonicalModelId":"amazon/nova-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"amazon.nova-micro-v1:0","name":"Nova Micro","type":null,"cost":{"input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0.035},"limit":{"context":128000,"output":10000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-micro","canonicalModelId":"amazon/nova-micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"amazon.nova-pro-v1:0","name":"Nova Pro","type":null,"cost":{"input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0.8},"limit":{"context":300000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-pro","canonicalModelId":"amazon/nova-pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"apac.amazon.nova-lite-v1:0","name":"Nova Lite (APAC)","type":null,"cost":{"input":0.063,"output":0.252,"cache_read":0.01575,"cache_write":0.063},"limit":{"context":300000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-lite","canonicalModelId":"amazon/nova-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"apac.amazon.nova-micro-v1:0","name":"Nova Micro (APAC)","type":null,"cost":{"input":0.037,"output":0.148,"cache_read":0.00925,"cache_write":0.037},"limit":{"context":128000,"output":10000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-micro","canonicalModelId":"amazon/nova-micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"apac.amazon.nova-pro-v1:0","name":"Nova Pro (APAC)","type":null,"cost":{"input":0.84,"output":3.36,"cache_read":0.21,"cache_write":0.84},"limit":{"context":300000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-pro","canonicalModelId":"amazon/nova-pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"ca.amazon.nova-lite-v1:0","name":"Nova Lite (CA)","type":null,"cost":{"input":0.064,"output":0.256,"cache_read":0.016,"cache_write":0.064},"limit":{"context":300000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-lite","canonicalModelId":"amazon/nova-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"eu.amazon.nova-2-lite-v1:0","name":"Nova 2 Lite (EU)","type":null,"cost":{"input":0.374,"output":3.157,"cache_read":0.0935,"cache_write":0.374},"limit":{"context":1000000,"output":65535},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova","canonicalModelId":"amazon/nova-2-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","knowledge":"2025-10","releaseDate":"2025-12-02","lastUpdated":"2025-12-01"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"eu.amazon.nova-lite-v1:0","name":"Nova Lite (EU)","type":null,"cost":{"input":0.069,"output":0.276,"cache_read":0.01725,"cache_write":0.069},"limit":{"context":300000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-lite","canonicalModelId":"amazon/nova-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"eu.amazon.nova-micro-v1:0","name":"Nova Micro (EU)","type":null,"cost":{"input":0.04,"output":0.16,"cache_read":0.01,"cache_write":0.04},"limit":{"context":128000,"output":10000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-micro","canonicalModelId":"amazon/nova-micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"eu.amazon.nova-pro-v1:0","name":"Nova Pro (EU)","type":null,"cost":{"input":0.92,"output":3.68,"cache_read":0.23,"cache_write":0.92},"limit":{"context":300000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-pro","canonicalModelId":"amazon/nova-pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"global.amazon.nova-2-lite-v1:0","name":"Nova 2 Lite (Global)","type":null,"cost":{"input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0.3},"limit":{"context":1000000,"output":65535},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova","canonicalModelId":"amazon/nova-2-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","knowledge":"2025-10","releaseDate":"2025-12-02","lastUpdated":"2025-12-01"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"jp.amazon.nova-2-lite-v1:0","name":"Nova 2 Lite (JP)","type":null,"cost":{"input":0.396,"output":3.311,"cache_read":0.099,"cache_write":0.396},"limit":{"context":1000000,"output":65535},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova","canonicalModelId":"amazon/nova-2-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","knowledge":"2025-10","releaseDate":"2025-12-02","lastUpdated":"2025-12-01"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"us.amazon.nova-2-lite-v1:0","name":"Nova 2 Lite (US)","type":null,"cost":{"input":0.33,"output":2.75,"cache_read":0.0825,"cache_write":0.33},"limit":{"context":1000000,"output":65535},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova","canonicalModelId":"amazon/nova-2-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","knowledge":"2025-10","releaseDate":"2025-12-02","lastUpdated":"2025-12-01"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"us.amazon.nova-lite-v1:0","name":"Nova Lite (US)","type":null,"cost":{"input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0.06},"limit":{"context":300000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-lite","canonicalModelId":"amazon/nova-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"us.amazon.nova-micro-v1:0","name":"Nova Micro (US)","type":null,"cost":{"input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0.035},"limit":{"context":128000,"output":10000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-micro","canonicalModelId":"amazon/nova-micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"us.amazon.nova-premier-v1:0","name":"Nova Premier (US)","type":null,"cost":{"input":2.5,"output":12.5,"cache_read":0.625,"cache_write":2.5},"limit":{"context":1000000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova","canonicalModelId":"amazon/nova-premier","description":"Multimodal model for complex analysis, long-context understanding, tool use, and model distillation","knowledge":"2024-10","releaseDate":"2025-04-30","lastUpdated":"2025-04-30"},{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","id":"us.amazon.nova-pro-v1:0","name":"Nova Pro (US)","type":null,"cost":{"input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0.8},"limit":{"context":300000,"output":10000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","family":"nova-pro","canonicalModelId":"amazon/nova-pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","knowledge":"2024-10","releaseDate":"2024-12-03","lastUpdated":"2024-12-03"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-fable-5","name":"Claude Fable 5","type":null,"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-fable","description":"Claude model for creative writing, analysis, and controlled agent workflows","releaseDate":"2026-06-07","lastUpdated":"2026-06-09"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-fable-5-1","name":"Claude Fable 5.1","type":null,"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-fable","canonicalModelId":"anthropic/claude-fable-5-1","description":"Claude model for demanding reasoning and long-horizon agentic work","knowledge":"2026-06","releaseDate":"2026-09-01","lastUpdated":"2026-09-01"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","type":null,"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"limit":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-haiku","canonicalModelId":"anthropic/claude-haiku-4-5","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","knowledge":"2025-02-28","releaseDate":"2025-10-15","lastUpdated":"2025-10-15"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","type":null,"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"limit":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","knowledge":"2025-02-28","releaseDate":"2025-10-15","lastUpdated":"2025-10-15"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-opus-4-5","name":"Claude Opus 4.5 (latest)","type":null,"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"limit":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-opus","canonicalModelId":"anthropic/claude-opus-4-5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","knowledge":"2025-05","releaseDate":"2025-11-24","lastUpdated":"2025-11-24"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-opus-4-5-20251101","name":"Claude Opus 4.5","type":null,"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"limit":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","knowledge":"2025-05","releaseDate":"2025-11-24","lastUpdated":"2025-11-01"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-opus-4-6","name":"Claude Opus 4.6","type":null,"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-opus","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","knowledge":"2025-05-31","releaseDate":"2026-02-04","lastUpdated":"2026-03-13"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-opus-4-7","name":"Claude Opus 4.7","type":null,"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-opus","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","knowledge":"2026-01-31","releaseDate":"2026-04-14","lastUpdated":"2026-04-16"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-opus-4-8","name":"Claude Opus 4.8","type":null,"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-opus","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","knowledge":"2026-01","releaseDate":"2026-05-28","lastUpdated":"2026-05-28"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-opus-5","name":"Claude Opus 5","type":null,"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-opus","canonicalModelId":"anthropic/claude-opus-5","description":"Strongest Claude Opus model for coding, agents, and professional work","knowledge":"2026-05","releaseDate":"2026-07-24","lastUpdated":"2026-07-24"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-opus-5-5","name":"Claude Opus 5.5","type":null,"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-opus","canonicalModelId":"anthropic/claude-opus-5-5","description":"Claude model for long-running agentic coding and knowledge work","knowledge":"2026-06","releaseDate":"2026-09-22","lastUpdated":"2026-09-22"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","type":null,"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"limit":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-sonnet","canonicalModelId":"anthropic/claude-sonnet-4-5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","knowledge":"2025-07-31","releaseDate":"2025-09-29","lastUpdated":"2025-09-29"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","type":null,"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"limit":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","knowledge":"2025-07-31","releaseDate":"2025-09-29","lastUpdated":"2025-09-29"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","type":null,"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-sonnet","description":"Claude workhorse for coding agents, careful analysis, and production cost control","knowledge":"2025-08-31","releaseDate":"2026-02-17","lastUpdated":"2026-03-13"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-sonnet-5","name":"Claude Sonnet 5","type":null,"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-sonnet","description":"Everyday Claude agent model for coding, planning, browsing, and general work","knowledge":"2026-01-31","releaseDate":"2026-06-29","lastUpdated":"2026-06-30"},{"providerId":"anthropic","providerName":"Anthropic","id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","type":null,"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"limit":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.anthropic.com/en/docs/about-claude/models","family":"claude-sonnet","canonicalModelId":"anthropic/claude-sonnet-5-5","description":"Fast Claude model for everyday coding, agents, and knowledge work","knowledge":"2026-06","releaseDate":"2026-09-28","lastUpdated":"2026-09-28"},{"providerId":"cohere","providerName":"Cohere","id":"c4ai-aya-expanse-32b","name":"Aya Expanse 32B","type":null,"cost":{"input":null,"output":null},"limit":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","canonicalModelId":"cohere/c4ai-aya-expanse-32b","description":"Open multilingual model optimized for generation across 23 languages","releaseDate":"2024-10-24","lastUpdated":"2024-10-24"},{"providerId":"cohere","providerName":"Cohere","id":"c4ai-aya-expanse-8b","name":"Aya Expanse 8B","type":null,"cost":{"input":null,"output":null},"limit":{"context":8000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","canonicalModelId":"cohere/c4ai-aya-expanse-8b","description":"Compact open multilingual model optimized for generation across 23 languages","releaseDate":"2024-10-24","lastUpdated":"2024-10-24"},{"providerId":"cohere","providerName":"Cohere","id":"c4ai-aya-vision-32b","name":"Aya Vision 32B","type":null,"cost":{"input":null,"output":null},"limit":{"context":16000,"output":4000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","canonicalModelId":"cohere/c4ai-aya-vision-32b","description":"Open multilingual vision model for OCR, visual reasoning, and image question answering","releaseDate":"2025-03-04","lastUpdated":"2025-05-14"},{"providerId":"cohere","providerName":"Cohere","id":"c4ai-aya-vision-8b","name":"Aya Vision 8B","type":null,"cost":{"input":null,"output":null},"limit":{"context":16000,"output":4000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","canonicalModelId":"cohere/c4ai-aya-vision-8b","description":"Compact open multilingual vision model for OCR and visual question answering","releaseDate":"2025-03-04","lastUpdated":"2025-05-14"},{"providerId":"cohere","providerName":"Cohere","id":"command-a-03-2025","name":"Command A","type":null,"cost":{"input":2.5,"output":10},"limit":{"context":256000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"command-a","canonicalModelId":"cohere/command-a-03-2025","description":"Cohere command model for multilingual enterprise agents, tools, and chat","knowledge":"2024-06-01","releaseDate":"2025-03-13","lastUpdated":"2025-03-13"},{"providerId":"cohere","providerName":"Cohere","id":"command-a-plus-05-2026","name":"Command A Plus","type":null,"cost":{"input":2.5,"output":10},"limit":{"context":128000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"command-a","canonicalModelId":"cohere/command-a-plus-05-2026","description":"Cohere's stronger command model for multilingual agents and enterprise workflows","knowledge":"2025-04-01","releaseDate":"2026-05-20","lastUpdated":"2026-06-09"},{"providerId":"cohere","providerName":"Cohere","id":"command-a-reasoning-08-2025","name":"Command A Reasoning","type":null,"cost":{"input":2.5,"output":10},"limit":{"context":256000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"command-a","canonicalModelId":"cohere/command-a-reasoning-08-2025","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","knowledge":"2024-06-01","releaseDate":"2025-08-21","lastUpdated":"2025-08-21"},{"providerId":"cohere","providerName":"Cohere","id":"command-a-translate-08-2025","name":"Command A Translate","type":null,"cost":{"input":2.5,"output":10},"limit":{"context":8000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"command-a","canonicalModelId":"cohere/command-a-translate-08-2025","description":"Translation model for multilingual conversion, localization, and cross-language workflows","knowledge":"2024-06-01","releaseDate":"2025-08-28","lastUpdated":"2025-08-28"},{"providerId":"cohere","providerName":"Cohere","id":"command-a-vision-07-2025","name":"Command A Vision","type":null,"cost":{"input":2.5,"output":10},"limit":{"context":128000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"command-a","canonicalModelId":"cohere/command-a-vision-07-2025","description":"Cohere vision model for multilingual document analysis, OCR, and image understanding","knowledge":"2024-06-01","releaseDate":"2025-07-31","lastUpdated":"2025-07-31"},{"providerId":"cohere","providerName":"Cohere","id":"command-r-08-2024","name":"Command R","type":null,"cost":{"input":0.15,"output":0.6},"limit":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"command-r","canonicalModelId":"cohere/command-r-08-2024","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","knowledge":"2024-06-01","releaseDate":"2024-08-30","lastUpdated":"2024-08-30"},{"providerId":"cohere","providerName":"Cohere","id":"command-r-plus-08-2024","name":"Command R+","type":null,"cost":{"input":2.5,"output":10},"limit":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"command-r","canonicalModelId":"cohere/command-r-plus-08-2024","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","knowledge":"2024-06-01","releaseDate":"2024-08-30","lastUpdated":"2024-08-30"},{"providerId":"cohere","providerName":"Cohere","id":"command-r7b-12-2024","name":"Command R7B","type":null,"cost":{"input":0.0375,"output":0.15},"limit":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"command-r","canonicalModelId":"cohere/command-r7b-12-2024","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","knowledge":"2024-06-01","releaseDate":"2024-12-02","lastUpdated":"2024-12-02"},{"providerId":"cohere","providerName":"Cohere","id":"command-r7b-arabic-02-2025","name":"Command R7B Arabic","type":null,"cost":{"input":0.0375,"output":0.15},"limit":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"command-r","canonicalModelId":"cohere/command-r7b-arabic-02-2025","description":"Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge","knowledge":"2024-06-01","releaseDate":"2025-02-27","lastUpdated":"2025-02-27"},{"providerId":"cohere","providerName":"Cohere","id":"north-mini-code-1-0","name":"North Mini Code","type":null,"cost":{"input":0,"output":0},"limit":{"context":256000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"north","canonicalModelId":"cohere/north-mini-code-1-0","description":"Cohere coding model for practical software engineering and agentic edits","knowledge":"2025-09-23","releaseDate":"2026-06-09","lastUpdated":"2026-06-09"},{"providerId":"cohere","providerName":"Cohere","id":"north-small-translate-09-2026","name":"North Small Translate","type":null,"cost":{"input":0,"output":0},"limit":{"context":32768,"output":16000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","family":"north","canonicalModelId":"cohere/north-small-translate-1-0","description":"Open-weight translation model for more than 50 languages and locale variants","releaseDate":"2026-09-09","lastUpdated":"2026-09-09"},{"providerId":"cohere","providerName":"Cohere","id":"tiny-aya-earth","name":"Tiny Aya Earth","type":null,"cost":{"input":null,"output":null},"limit":{"context":8000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","canonicalModelId":"cohere/tiny-aya-earth","description":"Compact multilingual model specialized for West Asian and African languages","releaseDate":"2026-02-17","lastUpdated":"2026-02-17"},{"providerId":"cohere","providerName":"Cohere","id":"tiny-aya-fire","name":"Tiny Aya Fire","type":null,"cost":{"input":null,"output":null},"limit":{"context":8000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","canonicalModelId":"cohere/tiny-aya-fire","description":"Compact multilingual model specialized for South Asian languages","releaseDate":"2026-02-17","lastUpdated":"2026-02-17"},{"providerId":"cohere","providerName":"Cohere","id":"tiny-aya-global","name":"Tiny Aya Global","type":null,"cost":{"input":null,"output":null},"limit":{"context":8000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","canonicalModelId":"cohere/tiny-aya-global","description":"Compact multilingual model balanced across 70 languages and regions","releaseDate":"2026-02-17","lastUpdated":"2026-02-17"},{"providerId":"cohere","providerName":"Cohere","id":"tiny-aya-water","name":"Tiny Aya Water","type":null,"cost":{"input":null,"output":null},"limit":{"context":8000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.cohere.com/docs/models","canonicalModelId":"cohere/tiny-aya-water","description":"Compact multilingual model specialized for European and Asia-Pacific languages","releaseDate":"2026-02-17","lastUpdated":"2026-02-17"},{"providerId":"deepseek","providerName":"DeepSeek","id":"deepseek-flash","name":"DeepSeek V4.1 Flash","type":null,"cost":{"input":0.15,"output":0.6,"cache_read":0.003,"reasoning":0.6},"limit":{"context":1000000,"output":393216},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://api-docs.deepseek.com/quick_start/pricing","family":"deepseek-flash","canonicalModelId":"deepseek/deepseek-v4.1-flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","knowledge":"2025-05","releaseDate":"2026-09-10","lastUpdated":"2026-09-10"},{"providerId":"deepseek","providerName":"DeepSeek","id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","type":null,"cost":{"input":0.15,"output":0.6,"cache_read":0.003,"reasoning":0.6},"limit":{"context":1000000,"output":393216},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://api-docs.deepseek.com/quick_start/pricing","family":"deepseek-flash","canonicalModelId":"deepseek/deepseek-v4.1-flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","knowledge":"2025-05","releaseDate":"2026-09-10","lastUpdated":"2026-09-10"},{"providerId":"deepseek","providerName":"DeepSeek","id":"deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","type":null,"cost":{"input":0.15,"output":0.6,"cache_read":0.003,"reasoning":0.6},"limit":{"context":1000000,"output":393216},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://api-docs.deepseek.com/quick_start/pricing","family":"deepseek-flash","canonicalModelId":"deepseek/deepseek-v4.1-flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","knowledge":"2025-05","releaseDate":"2026-09-10","lastUpdated":"2026-09-10"},{"providerId":"deepseek","providerName":"DeepSeek","id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","type":null,"cost":{"input":0.435,"output":0.87,"cache_read":0.003625,"reasoning":0.87},"limit":{"context":1000000,"output":393216},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://api-docs.deepseek.com/quick_start/pricing","family":"deepseek-thinking","canonicalModelId":"deepseek/deepseek-v4-pro-0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","releaseDate":"2026-08-12","lastUpdated":"2026-08-22"},{"providerId":"google","providerName":"Google","id":"deep-research-max-preview-04-2026","name":"Deep Research Max Preview (Apr-21-2026)","type":null,"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"limit":{"context":131072,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-pro","canonicalModelId":"google/deep-research-max-preview-04-2026","description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","knowledge":"2025-01","releaseDate":"2026-04-21","lastUpdated":"2026-04-21"},{"providerId":"google","providerName":"Google","id":"deep-research-preview-04-2026","name":"Deep Research Preview (Apr-21-2026)","type":null,"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"limit":{"context":131072,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-pro","canonicalModelId":"google/deep-research-preview-04-2026","description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","knowledge":"2025-01","releaseDate":"2026-04-21","lastUpdated":"2026-04-21"},{"providerId":"google","providerName":"Google","id":"gemini-2.5-computer-use-preview-10-2025","name":"Gemini 2.5 Computer Use Preview 10-2025","type":null,"cost":{"input":1.25,"output":10,"tiers":[{"input":2.5,"output":15,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15}},"limit":{"context":128000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-pro","canonicalModelId":"google/gemini-2.5-computer-use-preview-10-2025","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","knowledge":"2025-01","releaseDate":"2025-10-07","lastUpdated":"2025-10-07"},{"providerId":"google","providerName":"Google","id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","type":null,"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","canonicalModelId":"google/gemini-2.5-flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","knowledge":"2025-01","releaseDate":"2025-06-17","lastUpdated":"2025-06-17"},{"providerId":"google","providerName":"Google","id":"gemini-2.5-flash-image","name":"Nano Banana","type":null,"cost":{"input":0.3,"output":30,"cache_read":0.075},"limit":{"context":32768,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"reasoning":true,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","canonicalModelId":"google/gemini-2.5-flash-image","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","knowledge":"2024-06","releaseDate":"2025-08-26","lastUpdated":"2025-08-26"},{"providerId":"google","providerName":"Google","id":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","type":null,"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash-lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","knowledge":"2025-01","releaseDate":"2025-06-17","lastUpdated":"2025-06-17"},{"providerId":"google","providerName":"Google","id":"gemini-2.5-flash-preview-tts","name":"Gemini 2.5 Flash Preview TTS","type":null,"cost":{"input":0.5,"output":10},"limit":{"context":8192,"output":16384},"modalities":{"input":["text"],"output":["audio"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","description":"Speech generation model for controllable voice, narration, and audio delivery","knowledge":"2025-01","releaseDate":"2025-05-01","lastUpdated":"2025-05-01"},{"providerId":"google","providerName":"Google","id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","type":null,"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-pro","canonicalModelId":"google/gemini-2.5-pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","knowledge":"2025-01","releaseDate":"2025-06-17","lastUpdated":"2025-06-17"},{"providerId":"google","providerName":"Google","id":"gemini-2.5-pro-preview-tts","name":"Gemini 2.5 Pro Preview TTS","type":null,"cost":{"input":1,"output":20},"limit":{"context":8192,"output":16384},"modalities":{"input":["text"],"output":["audio"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","description":"Speech generation model for controllable voice, narration, and audio delivery","knowledge":"2025-01","releaseDate":"2025-05-01","lastUpdated":"2025-05-01"},{"providerId":"google","providerName":"Google","id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","type":null,"cost":{"input":0.5,"output":3,"cache_read":0.05},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","knowledge":"2025-01","releaseDate":"2025-12-17","lastUpdated":"2025-12-17"},{"providerId":"google","providerName":"Google","id":"gemini-3-pro-image","name":"Nano Banana Pro","type":null,"cost":{"input":2,"output":120},"limit":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"reasoning":true,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-pro","canonicalModelId":"google/gemini-3-pro-image","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","knowledge":"2025-01","releaseDate":"2026-05-28","lastUpdated":"2026-05-28"},{"providerId":"google","providerName":"Google","id":"gemini-3-pro-image-preview","name":"Nano Banana Pro","type":null,"cost":{"input":2,"output":120},"limit":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"reasoning":true,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-pro","canonicalModelId":"google/gemini-3-pro-image-preview","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","knowledge":"2025-01","releaseDate":"2025-11-20","lastUpdated":"2025-11-20"},{"providerId":"google","providerName":"Google","id":"gemini-3.1-flash-image","name":"Nano Banana 2","type":null,"cost":{"input":0.5,"output":60},"limit":{"context":131072,"output":32768},"modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"reasoning":true,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","canonicalModelId":"google/gemini-3.1-flash-image","description":"Image model for prompt-driven generation, editing, and visual design workflows","knowledge":"2025-01","releaseDate":"2026-05-28","lastUpdated":"2026-05-28"},{"providerId":"google","providerName":"Google","id":"gemini-3.1-flash-image-preview","name":"Nano Banana 2","type":null,"cost":{"input":0.5,"output":60},"limit":{"context":65536,"output":65536},"modalities":{"input":["text","image","pdf"],"output":["text","image"]},"reasoning":true,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","description":"Image model for prompt-driven generation, editing, and visual design workflows","knowledge":"2025-01","releaseDate":"2026-02-26","lastUpdated":"2026-02-26"},{"providerId":"google","providerName":"Google","id":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","type":null,"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash-lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","knowledge":"2025-01","releaseDate":"2026-05-07","lastUpdated":"2026-05-07"},{"providerId":"google","providerName":"Google","id":"gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","type":null,"cost":{"input":0.25,"output":30},"limit":{"context":65536,"output":4096},"modalities":{"input":["text","image"],"output":["text","image"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash-lite","canonicalModelId":"google/gemini-3.1-flash-lite-image","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","knowledge":"2025-01","releaseDate":"2026-06-30","lastUpdated":"2026-06-30"},{"providerId":"google","providerName":"Google","id":"gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","type":null,"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash-lite","description":"Legacy model retained for compatibility with older integrations","knowledge":"2025-01","releaseDate":"2026-03-03","lastUpdated":"2026-03-03"},{"providerId":"google","providerName":"Google","id":"gemini-3.1-flash-live-preview","name":"Gemini 3.1 Flash Live Preview","type":null,"cost":{"input":0.75,"output":4.5},"limit":{"context":131072,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text","audio"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","canonicalModelId":"google/gemini-3.1-flash-live-preview","description":"High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications","knowledge":"2025-01","releaseDate":"2026-03-26","lastUpdated":"2026-03-26"},{"providerId":"google","providerName":"Google","id":"gemini-3.1-flash-tts-preview","name":"Gemini 3.1 Flash TTS Preview","type":null,"cost":{"input":1,"output":20},"limit":{"context":8192,"output":16384},"modalities":{"input":["text"],"output":["audio"]},"reasoning":true,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","canonicalModelId":"google/gemini-3.1-flash-tts-preview","description":"Low-latency speech generation with steerable prompts and expressive audio tags","knowledge":"2025-01","releaseDate":"2026-04-15","lastUpdated":"2026-04-15"},{"providerId":"google","providerName":"Google","id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","type":null,"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-pro","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","knowledge":"2025-01","releaseDate":"2026-02-19","lastUpdated":"2026-02-19"},{"providerId":"google","providerName":"Google","id":"gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","type":null,"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","knowledge":"2025-01","releaseDate":"2026-02-19","lastUpdated":"2026-02-19"},{"providerId":"google","providerName":"Google","id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","type":null,"cost":{"input":1.5,"output":9,"cache_read":0.15},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","knowledge":"2025-01","releaseDate":"2026-05-19","lastUpdated":"2026-05-19"},{"providerId":"google","providerName":"Google","id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","type":null,"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash-lite","canonicalModelId":"google/gemini-3.5-flash-lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","knowledge":"2026-03","releaseDate":"2026-07-21","lastUpdated":"2026-07-21"},{"providerId":"google","providerName":"Google","id":"gemini-3.5-live-translate-preview","name":"Gemini 3.5 Live Translate Preview","type":null,"cost":{"input":3.5,"output":21},"limit":{"context":16384,"output":32768},"modalities":{"input":["audio"],"output":["audio","text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-pro","canonicalModelId":"google/gemini-3.5-live-translate-preview","description":"Low-latency audio-to-audio model for real-time speech translation across 70+ languages","knowledge":"2025-01","releaseDate":"2026-06-09","lastUpdated":"2026-06-09"},{"providerId":"google","providerName":"Google","id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","type":null,"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","canonicalModelId":"google/gemini-3.6-flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","knowledge":"2026-03","releaseDate":"2026-07-21","lastUpdated":"2026-07-21"},{"providerId":"google","providerName":"Google","id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","type":null,"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","canonicalModelId":"google/gemini-3.7-flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","knowledge":"2026-03","releaseDate":"2026-08-13","lastUpdated":"2026-08-13"},{"providerId":"google","providerName":"Google","id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","type":null,"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","canonicalModelId":"google/gemini-3.8-flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","releaseDate":"2026-09-02","lastUpdated":"2026-09-02"},{"providerId":"google","providerName":"Google","id":"gemini-embedding-001","name":"Gemini Embedding 001","type":null,"cost":{"input":0.15,"output":0},"limit":{"context":2048,"output":1},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","knowledge":"2025-05","releaseDate":"2025-05-20","lastUpdated":"2025-05-20"},{"providerId":"google","providerName":"Google","id":"gemini-embedding-2","name":"Gemini Embedding 2","type":null,"cost":{"input":0.2,"output":0},"limit":{"context":8192,"output":1},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini","canonicalModelId":"google/gemini-embedding-2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","knowledge":"2025-11","releaseDate":"2026-04-22","lastUpdated":"2026-04-22"},{"providerId":"google","providerName":"Google","id":"gemini-flash-latest","name":"Gemini Flash Latest","type":null,"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","knowledge":"2026-03","releaseDate":"2026-08-13","lastUpdated":"2026-08-13"},{"providerId":"google","providerName":"Google","id":"gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","type":null,"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini-flash-lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","knowledge":"2026-03","releaseDate":"2026-07-21","lastUpdated":"2026-07-21"},{"providerId":"google","providerName":"Google","id":"gemini-omni-flash-preview","name":"Gemini Omni Flash Preview","type":null,"cost":{"input":1.5,"output":17.5},"limit":{"context":131072,"output":65536},"modalities":{"input":["text","image","video"],"output":["video"]},"reasoning":true,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemini","canonicalModelId":"google/gemini-omni-flash-preview","description":"Video generation and editing model for fast, conversational text- and image-to-video workflows","releaseDate":"2026-06-30","lastUpdated":"2026-06-30"},{"providerId":"google","providerName":"Google","id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","type":null,"cost":{"input":null,"output":null},"limit":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemma","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","releaseDate":"2026-04-02","lastUpdated":"2026-04-02"},{"providerId":"google","providerName":"Google","id":"gemma-4-31b-it","name":"Gemma 4 31B IT","type":null,"cost":{"input":null,"output":null},"limit":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"gemma","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","releaseDate":"2026-04-02","lastUpdated":"2026-04-02"},{"providerId":"google","providerName":"Google","id":"lyria-3-clip-preview","name":"Lyria 3 Clip Preview","type":null,"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image"],"output":["text","audio"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"lyria","canonicalModelId":"google/lyria-3-clip-preview","description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","releaseDate":"2026-03-25","lastUpdated":"2026-03-25"},{"providerId":"google","providerName":"Google","id":"lyria-3-pro-preview","name":"Lyria 3 Pro Preview","type":null,"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":65536},"modalities":{"input":["text","image"],"output":["text","audio"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"lyria","canonicalModelId":"google/lyria-3-pro-preview","description":"Music generation model for full-length songs from text or images with vocals and structure","releaseDate":"2026-03-25","lastUpdated":"2026-03-25"},{"providerId":"google","providerName":"Google","id":"veo-3.1-fast-generate-preview","name":"Veo 3.1 fast","type":null,"cost":{"input":null,"output":null},"limit":{"context":480,"output":8192},"modalities":{"input":["text","image","video"],"output":["video"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"veo","canonicalModelId":"google/veo-3.1-fast-generate-preview","description":"Video model for prompt-guided generation, editing, and motion workflows","releaseDate":"2025-10-15","lastUpdated":"2026-01-01"},{"providerId":"google","providerName":"Google","id":"veo-3.1-generate-preview","name":"Veo 3.1","type":null,"cost":{"input":null,"output":null},"limit":{"context":480,"output":8192},"modalities":{"input":["text","image"],"output":["video"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"veo","canonicalModelId":"google/veo-3.1-generate-preview","description":"Video model for prompt-guided generation, editing, and motion workflows","releaseDate":"2025-10-15","lastUpdated":"2026-01"},{"providerId":"google","providerName":"Google","id":"veo-3.1-lite-generate-preview","name":"Veo 3.1 lite","type":null,"cost":{"input":null,"output":null},"limit":{"context":480,"output":8192},"modalities":{"input":["text","image"],"output":["video"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://ai.google.dev/gemini-api/docs/models","family":"veo","canonicalModelId":"google/veo-3.1-lite-generate-preview","description":"Video model for prompt-guided generation, editing, and motion workflows","releaseDate":"2026-03-31","lastUpdated":"2026-03-31"},{"providerId":"meta","providerName":"Meta","id":"muse-spark-1.1","name":"Muse Spark 1.1","type":null,"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"limit":{"context":1048576,"output":131072},"modalities":{"input":["text","image","pdf","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://dev.meta.ai/docs","family":"muse","canonicalModelId":"meta/muse-spark-1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","releaseDate":"2026-04-08","lastUpdated":"2026-07-09"},{"providerId":"meta","providerName":"Meta","id":"muse-spark-1.2","name":"Muse Spark 1.2","type":null,"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"limit":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://dev.meta.ai/docs","family":"muse","canonicalModelId":"meta/muse-spark-1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","releaseDate":"2026-08-05","lastUpdated":"2026-08-05"},{"providerId":"meta","providerName":"Meta","id":"muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","type":null,"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"limit":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://dev.meta.ai/docs","family":"muse","canonicalModelId":"meta/muse-spark-1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","releaseDate":"2026-08-05","lastUpdated":"2026-08-05"},{"providerId":"meta","providerName":"Meta","id":"muse-spark-1.3","name":"Muse Spark 1.3","type":null,"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"limit":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://dev.meta.ai/docs","family":"muse","canonicalModelId":"meta/muse-spark-1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","releaseDate":"2026-09-02","lastUpdated":"2026-09-02"},{"providerId":"meta","providerName":"Meta","id":"muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","type":null,"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"limit":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://dev.meta.ai/docs","family":"muse","canonicalModelId":"meta/muse-spark-1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","releaseDate":"2026-09-02","lastUpdated":"2026-09-02"},{"providerId":"mistral","providerName":"Mistral","id":"codestral-latest","name":"Codestral (latest)","type":null,"cost":{"input":0.3,"output":0.9,"cache_read":0.03},"limit":{"context":256000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"codestral","description":"Mistral code model for completions, refactors, and developer IDE workflows","knowledge":"2024-10","releaseDate":"2024-05-29","lastUpdated":"2025-01-04"},{"providerId":"mistral","providerName":"Mistral","id":"devstral-2512","name":"Devstral 2","type":null,"cost":{"input":0.4,"output":2},"limit":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"devstral","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","knowledge":"2025-12","releaseDate":"2025-12-09","lastUpdated":"2025-12-09"},{"providerId":"mistral","providerName":"Mistral","id":"devstral-latest","name":"Devstral 2","type":null,"cost":{"input":0.4,"output":2},"limit":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"devstral","description":"Legacy model retained for compatibility with older integrations","knowledge":"2025-12","releaseDate":"2025-12-09","lastUpdated":"2025-12-09"},{"providerId":"mistral","providerName":"Mistral","id":"devstral-medium-2507","name":"Devstral Medium","type":null,"cost":{"input":0.4,"output":2},"limit":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"devstral","description":"Legacy model retained for compatibility with older integrations","knowledge":"2025-05","releaseDate":"2025-07-10","lastUpdated":"2025-07-10"},{"providerId":"mistral","providerName":"Mistral","id":"devstral-medium-latest","name":"Devstral 2 (latest)","type":null,"cost":{"input":0.4,"output":2},"limit":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"devstral","description":"Legacy model retained for compatibility with older integrations","knowledge":"2025-12","releaseDate":"2025-12-02","lastUpdated":"2025-12-02"},{"providerId":"mistral","providerName":"Mistral","id":"devstral-small-2505","name":"Devstral Small 2505","type":null,"cost":{"input":0.1,"output":0.3},"limit":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"devstral","description":"Legacy model retained for compatibility with older integrations","knowledge":"2025-05","releaseDate":"2025-05-07","lastUpdated":"2025-05-07"},{"providerId":"mistral","providerName":"Mistral","id":"devstral-small-2507","name":"Devstral Small","type":null,"cost":{"input":0.1,"output":0.3},"limit":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"devstral","description":"Legacy model retained for compatibility with older integrations","knowledge":"2025-05","releaseDate":"2025-07-10","lastUpdated":"2025-07-10"},{"providerId":"mistral","providerName":"Mistral","id":"labs-devstral-small-2512","name":"Devstral Small 2","type":null,"cost":{"input":0,"output":0},"limit":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"devstral","description":"Legacy model retained for compatibility with older integrations","knowledge":"2025-12","releaseDate":"2025-12-09","lastUpdated":"2025-12-09"},{"providerId":"mistral","providerName":"Mistral","id":"magistral-medium-latest","name":"Magistral Medium (latest)","type":null,"cost":{"input":2,"output":5},"limit":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"magistral-medium","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","knowledge":"2025-06","releaseDate":"2025-03-17","lastUpdated":"2025-03-20"},{"providerId":"mistral","providerName":"Mistral","id":"ministral-3b-latest","name":"Ministral 3B (latest)","type":null,"cost":{"input":0.04,"output":0.04},"limit":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"ministral","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","knowledge":"2024-10","releaseDate":"2024-10-01","lastUpdated":"2024-10-04"},{"providerId":"mistral","providerName":"Mistral","id":"ministral-8b-latest","name":"Ministral 8B (latest)","type":null,"cost":{"input":0.1,"output":0.1},"limit":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"ministral","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","knowledge":"2024-10","releaseDate":"2024-10-01","lastUpdated":"2024-10-04"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-embed","name":"Mistral Embed","type":null,"cost":{"input":0.1,"output":0},"limit":{"context":8000,"output":3072},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","releaseDate":"2023-12-11","lastUpdated":"2023-12-11"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-large-2411","name":"Mistral Large 2.1","type":null,"cost":{"input":2,"output":6},"limit":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-large","canonicalModelId":"mistral/mistral-large-2411","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","knowledge":"2024-11","releaseDate":"2024-11-18","lastUpdated":"2024-11-18"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-large-2512","name":"Mistral Large 3","type":null,"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"limit":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-large","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","knowledge":"2024-11","releaseDate":"2024-11-01","lastUpdated":"2025-12-02"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-large-latest","name":"Mistral Large (latest)","type":null,"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"limit":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","knowledge":"2024-11","releaseDate":"2024-11-01","lastUpdated":"2025-12-02"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-medium-2505","name":"Mistral Medium 3","type":null,"cost":{"input":0.4,"output":2},"limit":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-medium","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","knowledge":"2025-05","releaseDate":"2025-05-07","lastUpdated":"2025-05-07"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-medium-2508","name":"Mistral Medium 3.1","type":null,"cost":{"input":0.4,"output":2},"limit":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-medium","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","knowledge":"2025-05","releaseDate":"2025-08-12","lastUpdated":"2025-08-12"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-medium-2604","name":"Mistral Medium 3.5","type":null,"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"limit":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-medium","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","releaseDate":"2026-04-29","lastUpdated":"2026-04-29"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-medium-latest","name":"Mistral Medium (latest)","type":null,"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"limit":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-medium","canonicalModelId":"mistral/mistral-medium-latest","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","releaseDate":"2026-04-29","lastUpdated":"2026-04-29"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-nemo","name":"Mistral Nemo","type":null,"cost":{"input":0.15,"output":0.15},"limit":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","knowledge":"2024-07","releaseDate":"2024-07-01","lastUpdated":"2024-07-01"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-small-2506","name":"Mistral Small 3.2","type":null,"cost":{"input":0.1,"output":0.3},"limit":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-small","description":"Efficient Mistral model for fast chat, extraction, and production assistants","knowledge":"2025-03","releaseDate":"2025-06-20","lastUpdated":"2025-06-20"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-small-2603","name":"Mistral Small 4","type":null,"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"limit":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-small","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","knowledge":"2025-06","releaseDate":"2026-03-16","lastUpdated":"2026-03-16"},{"providerId":"mistral","providerName":"Mistral","id":"mistral-small-latest","name":"Mistral Small (latest)","type":null,"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"limit":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-small","description":"Efficient Mistral model for fast chat, extraction, and production assistants","knowledge":"2025-06","releaseDate":"2026-03-16","lastUpdated":"2026-03-16"},{"providerId":"mistral","providerName":"Mistral","id":"open-mistral-7b","name":"Mistral 7B","type":null,"cost":{"input":0.25,"output":0.25},"limit":{"context":8000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","knowledge":"2023-12","releaseDate":"2023-09-27","lastUpdated":"2023-09-27"},{"providerId":"mistral","providerName":"Mistral","id":"open-mistral-nemo","name":"Open Mistral Nemo","type":null,"cost":{"input":0.15,"output":0.15},"limit":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mistral-nemo","description":"Legacy model retained for compatibility with older integrations","knowledge":"2024-07","releaseDate":"2024-07-01","lastUpdated":"2024-07-01"},{"providerId":"mistral","providerName":"Mistral","id":"open-mixtral-8x22b","name":"Mixtral 8x22B","type":null,"cost":{"input":2,"output":6},"limit":{"context":64000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mixtral","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","knowledge":"2024-04","releaseDate":"2024-04-17","lastUpdated":"2024-04-17"},{"providerId":"mistral","providerName":"Mistral","id":"open-mixtral-8x7b","name":"Mixtral 8x7B","type":null,"cost":{"input":0.7,"output":0.7},"limit":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"mixtral","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","knowledge":"2024-01","releaseDate":"2023-12-11","lastUpdated":"2023-12-11"},{"providerId":"mistral","providerName":"Mistral","id":"pixtral-12b","name":"Pixtral 12B","type":null,"cost":{"input":0.15,"output":0.15},"limit":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"pixtral","description":"Mistral vision-language model for image understanding and multimodal chat","knowledge":"2024-09","releaseDate":"2024-09-01","lastUpdated":"2024-09-01"},{"providerId":"mistral","providerName":"Mistral","id":"pixtral-large-latest","name":"Pixtral Large (latest)","type":null,"cost":{"input":2,"output":6},"limit":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"pixtral","description":"Mistral's larger vision model for document-heavy image understanding and chat","knowledge":"2024-11","releaseDate":"2024-11-01","lastUpdated":"2024-11-04"},{"providerId":"mistral","providerName":"Mistral","id":"voxtral-mini-latest","name":"Voxtral Mini (latest)","type":null,"cost":{"input":null,"output":null},"limit":{"context":0,"output":0},"modalities":{"input":["audio"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"voxtral","description":"Speech transcription model for accurate audio-to-text and captioning workflows","releaseDate":"2026-02-01","lastUpdated":"2026-02-01"},{"providerId":"mistral","providerName":"Mistral","id":"voxtral-mini-tts-latest","name":"Voxtral Mini TTS (latest)","type":null,"cost":{"input":null,"output":null},"limit":{"context":0,"output":0},"modalities":{"input":["text"],"output":["audio"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"voxtral","description":"Multilingual text-to-speech model with zero-shot voice cloning","releaseDate":"2026-03-01","lastUpdated":"2026-03-01"},{"providerId":"mistral","providerName":"Mistral","id":"voxtral-small-latest","name":"Voxtral Small (latest)","type":null,"cost":{"input":0.1,"output":0.3},"limit":{"context":32000,"output":32000},"modalities":{"input":["text","audio"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"voxtral","description":"Instruct model with native audio input for speech understanding and tool use","releaseDate":"2025-07-15","lastUpdated":"2025-07-15"},{"providerId":"mistral","providerName":"Mistral","id":"zai-glm-5-2","name":"GLM-5.2","type":null,"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"limit":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"glm","canonicalModelId":"zhipuai/glm-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","releaseDate":"2026-06-13","lastUpdated":"2026-06-13"},{"providerId":"mistral","providerName":"Mistral","id":"zai-glm-5-3","name":"GLM-5.3","type":null,"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"limit":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":true,"providerDoc":"https://docs.mistral.ai/getting-started/models/","family":"glm","canonicalModelId":"zhipuai/glm-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","releaseDate":"2026-08-14","lastUpdated":"2026-08-14"},{"providerId":"moonshotai","providerName":"Moonshot AI","id":"kimi-k2.6","name":"Kimi K2.6","type":null,"cost":{"input":0.95,"output":4,"cache_read":0.16},"limit":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://platform.moonshot.ai/docs/api/chat","family":"kimi-k2","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","knowledge":"2025-01","releaseDate":"2026-04-21","lastUpdated":"2026-04-21"},{"providerId":"moonshotai","providerName":"Moonshot AI","id":"kimi-k2.7-code","name":"Kimi K2.7 Code","type":null,"cost":{"input":0.95,"output":4,"cache_read":0.19},"limit":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://platform.moonshot.ai/docs/api/chat","family":"kimi-k2","canonicalModelId":"moonshotai/kimi-k2.7-code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","knowledge":"2025-01","releaseDate":"2026-06-12","lastUpdated":"2026-06-12"},{"providerId":"moonshotai","providerName":"Moonshot AI","id":"kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code HighSpeed","type":null,"cost":{"input":1.9,"output":8,"cache_read":0.38},"limit":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://platform.moonshot.ai/docs/api/chat","family":"kimi-k2","canonicalModelId":"moonshotai/kimi-k2.7-code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","knowledge":"2025-01","releaseDate":"2026-06-12","lastUpdated":"2026-06-12"},{"providerId":"moonshotai","providerName":"Moonshot AI","id":"kimi-k3","name":"Kimi K3","type":null,"cost":{"input":3,"output":15,"cache_read":0.3},"limit":{"context":1048576,"output":1048576},"modalities":{"input":["text","image","video"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":true,"providerDoc":"https://platform.moonshot.ai/docs/api/chat","family":"kimi-k3","canonicalModelId":"moonshotai/kimi-k3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","releaseDate":"2026-07-16","lastUpdated":"2026-07-16"},{"providerId":"openai","providerName":"OpenAI","id":"chatgpt-image-latest","name":"chatgpt-image-latest","type":null,"cost":{"input":null,"output":null},"limit":{"context":0,"output":0,"input":0},"modalities":{"input":["text","image"],"output":["text","image"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-image","description":"Image model for prompt-driven generation, editing, and visual design workflows","releaseDate":"2025-12-16","lastUpdated":"2025-12-16"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-3.5-turbo","name":"GPT-3.5-turbo","type":null,"cost":{"input":0.5,"output":1.5,"cache_read":0},"limit":{"context":16385,"output":4096},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"Compact GPT model for low-latency assistance and high-volume workloads","knowledge":"2021-09-01","releaseDate":"2023-03-01","lastUpdated":"2023-11-06"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4","name":"GPT-4","type":null,"cost":{"input":30,"output":60},"limit":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","knowledge":"2023-11","releaseDate":"2023-11-06","lastUpdated":"2024-04-09"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4-turbo","name":"GPT-4 Turbo","type":null,"cost":{"input":10,"output":30},"limit":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"Compact GPT model for low-latency assistance and high-volume workloads","knowledge":"2023-12","releaseDate":"2023-11-06","lastUpdated":"2024-04-09"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4.1","name":"GPT-4.1","type":null,"cost":{"input":2,"output":8,"cache_read":0.5},"limit":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","knowledge":"2024-04","releaseDate":"2025-04-14","lastUpdated":"2025-04-14"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4.1-mini","name":"GPT-4.1 mini","type":null,"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"limit":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","knowledge":"2024-04","releaseDate":"2025-04-14","lastUpdated":"2025-04-14"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4.1-nano","name":"GPT-4.1 nano","type":null,"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"limit":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","knowledge":"2024-04","releaseDate":"2025-04-14","lastUpdated":"2025-04-14"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4o","name":"GPT-4o","type":null,"cost":{"input":2.5,"output":10,"cache_read":1.25},"limit":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","knowledge":"2023-09","releaseDate":"2024-05-13","lastUpdated":"2024-08-06"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","type":null,"cost":{"input":5,"output":15},"limit":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","knowledge":"2023-09","releaseDate":"2024-05-13","lastUpdated":"2024-05-13"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","type":null,"cost":{"input":2.5,"output":10,"cache_read":1.25},"limit":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","knowledge":"2023-09","releaseDate":"2024-08-06","lastUpdated":"2024-08-06"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","type":null,"cost":{"input":2.5,"output":10,"cache_read":1.25},"limit":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","knowledge":"2023-09","releaseDate":"2024-11-20","lastUpdated":"2024-11-20"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-4o-mini","name":"GPT-4o mini","type":null,"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"limit":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","knowledge":"2023-09","releaseDate":"2024-07-18","lastUpdated":"2024-07-18"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5","name":"GPT-5","type":null,"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","canonicalModelId":"openai/gpt-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","knowledge":"2024-09-30","releaseDate":"2025-08-07","lastUpdated":"2025-08-07"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5-mini","name":"GPT-5 Mini","type":null,"cost":{"input":0.25,"output":2,"cache_read":0.025},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","knowledge":"2024-05-30","releaseDate":"2025-08-07","lastUpdated":"2025-08-07"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5-nano","name":"GPT-5 Nano","type":null,"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","knowledge":"2024-05-30","releaseDate":"2025-08-07","lastUpdated":"2025-08-07"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5-pro","name":"GPT-5 Pro","type":null,"cost":{"input":15,"output":120},"limit":{"context":400000,"output":272000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","knowledge":"2024-09-30","releaseDate":"2025-10-06","lastUpdated":"2025-10-06"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.1","name":"GPT-5.1","type":null,"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","knowledge":"2024-09-30","releaseDate":"2025-11-13","lastUpdated":"2025-11-13"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.2","name":"GPT-5.2","type":null,"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","knowledge":"2025-08-31","releaseDate":"2025-12-11","lastUpdated":"2025-12-11"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.2-chat-latest","name":"GPT-5.2 Chat","type":null,"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-codex","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","knowledge":"2025-08-31","releaseDate":"2025-12-11","lastUpdated":"2025-12-11"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.2-pro","name":"GPT-5.2 Pro","type":null,"cost":{"input":21,"output":168},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","knowledge":"2025-08-31","releaseDate":"2025-12-11","lastUpdated":"2025-12-11"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.3-chat-latest","name":"GPT-5.3 Chat (latest)","type":null,"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","knowledge":"2025-08-31","releaseDate":"2026-03-03","lastUpdated":"2026-03-03"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.3-codex","name":"GPT-5.3 Codex","type":null,"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","knowledge":"2025-08-31","releaseDate":"2026-02-05","lastUpdated":"2026-02-05"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.3-codex-spark","name":"GPT-5.3 Codex Spark","type":null,"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":128000,"output":32000,"input":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-codex-spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","knowledge":"2025-08-31","releaseDate":"2026-02-05","lastUpdated":"2026-02-05"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.4","name":"GPT-5.4","type":null,"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","knowledge":"2025-08-31","releaseDate":"2026-03-05","lastUpdated":"2026-03-05"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.4-mini","name":"GPT-5.4 mini","type":null,"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","knowledge":"2025-08-31","releaseDate":"2026-03-17","lastUpdated":"2026-03-17"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.4-nano","name":"GPT-5.4 nano","type":null,"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","knowledge":"2025-08-31","releaseDate":"2026-03-17","lastUpdated":"2026-03-17"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.4-pro","name":"GPT-5.4 Pro","type":null,"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","knowledge":"2025-08-31","releaseDate":"2026-03-05","lastUpdated":"2026-03-05"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.5","name":"GPT-5.5","type":null,"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","description":"Default frontier GPT for coding, computer use, research, and knowledge work","knowledge":"2025-12-01","releaseDate":"2026-04-23","lastUpdated":"2026-04-23"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.5-pro","name":"GPT-5.5 Pro","type":null,"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","knowledge":"2025-12-01","releaseDate":"2026-04-23","lastUpdated":"2026-04-23"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.6","name":"GPT-5.6","type":null,"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-sol","canonicalModelId":"openai/gpt-5.6-sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","knowledge":"2026-02-16","releaseDate":"2026-07-09","lastUpdated":"2026-07-09"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.6-luna","name":"GPT-5.6 Luna","type":null,"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-luna","canonicalModelId":"openai/gpt-5.6-luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","knowledge":"2026-02-16","releaseDate":"2026-07-09","lastUpdated":"2026-07-09"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.6-sol","name":"GPT-5.6 Sol","type":null,"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-sol","canonicalModelId":"openai/gpt-5.6-sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","knowledge":"2026-02-16","releaseDate":"2026-07-09","lastUpdated":"2026-07-09"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-5.6-terra","name":"GPT-5.6 Terra","type":null,"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-terra","canonicalModelId":"openai/gpt-5.6-terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","knowledge":"2026-02-16","releaseDate":"2026-07-09","lastUpdated":"2026-07-09"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-6-astra","name":"GPT-6 Astra","type":null,"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-astra","canonicalModelId":"openai/gpt-6-astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","knowledge":"2026-04-30","releaseDate":"2026-09-04","lastUpdated":"2026-09-04"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-6-luna","name":"GPT-6 Luna","type":null,"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-luna","canonicalModelId":"openai/gpt-6-luna","description":"OpenAI's most efficient model for focused, high-volume tasks","knowledge":"2026-05-18","releaseDate":"2026-09-22","lastUpdated":"2026-09-22"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-6-sol","name":"GPT-6 Sol","type":null,"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-sol","canonicalModelId":"openai/gpt-6-sol","description":"OpenAI model for complex coding and agentic workflows","knowledge":"2026-04-20","releaseDate":"2026-09-22","lastUpdated":"2026-09-22"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-6.1-sol","name":"GPT-6.1 Sol","type":null,"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-sol","canonicalModelId":"openai/gpt-6.1-sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","knowledge":"2026-04-30","releaseDate":"2026-09-29","lastUpdated":"2026-09-29"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-daybreak-blue-latest","name":"Daybreak Blue","type":null,"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"limit":{"context":1050000,"output":128000,"input":922000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-sol","canonicalModelId":"openai/gpt-5.6-sol","description":"Alias for flagship general-purpose models with safeguards for defensive cybersecurity work","knowledge":"2026-02-16","releaseDate":"2026-08-07","lastUpdated":"2026-08-07"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-daybreak-red-latest","name":"Daybreak Red","type":null,"cost":{"input":12.5,"output":75,"cache_read":1.25,"cache_write":15.625},"limit":{"context":400000,"output":128000,"input":272000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","canonicalModelId":"openai/gpt-5.6-cyber","description":"Alias for advanced cybersecurity models for authorized vulnerability research and security testing","knowledge":"2026-02-16","releaseDate":"2026-08-07","lastUpdated":"2026-08-07"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-image-1","name":"gpt-image-1","type":null,"cost":{"input":null,"output":null},"limit":{"context":0,"output":0,"input":0},"modalities":{"input":["text","image"],"output":["image"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-image","canonicalModelId":"openai/gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","releaseDate":"2025-04-24","lastUpdated":"2025-04-24"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-image-1-mini","name":"gpt-image-1-mini","type":null,"cost":{"input":null,"output":null},"limit":{"context":0,"output":0,"input":0},"modalities":{"input":["text","image"],"output":["text","image"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-image","description":"Image model for prompt-driven generation, editing, and visual design workflows","releaseDate":"2025-09-26","lastUpdated":"2025-09-26"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-image-1.5","name":"gpt-image-1.5","type":null,"cost":{"input":null,"output":null},"limit":{"context":0,"output":0,"input":0},"modalities":{"input":["text","image"],"output":["text","image"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-image","canonicalModelId":"openai/gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","releaseDate":"2025-11-25","lastUpdated":"2025-11-25"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-image-2","name":"gpt-image-2","type":null,"cost":{"input":5,"output":30,"cache_read":1.25},"limit":{"context":0,"output":0,"input":0},"modalities":{"input":["text","image"],"output":["image"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt-image","canonicalModelId":"openai/gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","releaseDate":"2026-04-21","lastUpdated":"2026-04-21"},{"providerId":"openai","providerName":"OpenAI","id":"gpt-realtime-2.1","name":"GPT-Realtime-2.1","type":null,"cost":{"input":4,"output":24,"cache_read":0.4},"limit":{"context":128000,"output":32000,"input":96000},"modalities":{"input":["text","audio","image"],"output":["text","audio"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"gpt","canonicalModelId":"openai/gpt-realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","knowledge":"2024-09-30","releaseDate":"2026-07-06","lastUpdated":"2026-07-06"},{"providerId":"openai","providerName":"OpenAI","id":"o1","name":"o1","type":null,"cost":{"input":15,"output":60,"cache_read":7.5},"limit":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"o","description":"O-series reasoning model for hard analysis, math, coding, and planning","knowledge":"2023-09","releaseDate":"2024-12-05","lastUpdated":"2024-12-05"},{"providerId":"openai","providerName":"OpenAI","id":"o1-pro","name":"o1-pro","type":null,"cost":{"input":150,"output":600},"limit":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"o-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","knowledge":"2023-09","releaseDate":"2025-03-19","lastUpdated":"2025-03-19"},{"providerId":"openai","providerName":"OpenAI","id":"o3","name":"o3","type":null,"cost":{"input":2,"output":8,"cache_read":0.5},"limit":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"o","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","knowledge":"2024-05","releaseDate":"2025-04-16","lastUpdated":"2025-04-16"},{"providerId":"openai","providerName":"OpenAI","id":"o3-mini","name":"o3-mini","type":null,"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"limit":{"context":200000,"output":100000},"modalities":{"input":["text"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":false,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"o-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","knowledge":"2024-05","releaseDate":"2024-12-20","lastUpdated":"2025-01-29"},{"providerId":"openai","providerName":"OpenAI","id":"o3-pro","name":"o3-pro","type":null,"cost":{"input":20,"output":80},"limit":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"o-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","knowledge":"2024-05","releaseDate":"2025-06-10","lastUpdated":"2025-06-10"},{"providerId":"openai","providerName":"OpenAI","id":"o4-mini","name":"o4-mini","type":null,"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"limit":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"o-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","knowledge":"2024-05","releaseDate":"2025-04-16","lastUpdated":"2025-04-16"},{"providerId":"openai","providerName":"OpenAI","id":"text-embedding-3-large","name":"text-embedding-3-large","type":null,"cost":{"input":0.13,"output":0},"limit":{"context":8191,"output":3072},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"text-embedding","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","knowledge":"2024-01","releaseDate":"2024-01-25","lastUpdated":"2024-01-25"},{"providerId":"openai","providerName":"OpenAI","id":"text-embedding-3-small","name":"text-embedding-3-small","type":null,"cost":{"input":0.02,"output":0},"limit":{"context":8191,"output":1536},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"text-embedding","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","knowledge":"2024-01","releaseDate":"2024-01-25","lastUpdated":"2024-01-25"},{"providerId":"openai","providerName":"OpenAI","id":"text-embedding-ada-002","name":"text-embedding-ada-002","type":null,"cost":{"input":0.1,"output":0},"limit":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"reasoning":false,"toolCall":false,"attachment":false,"openWeights":false,"providerDoc":"https://platform.openai.com/docs/models","family":"text-embedding","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","knowledge":"2022-12","releaseDate":"2022-12-15","lastUpdated":"2022-12-15"},{"providerId":"xai","providerName":"xAI","id":"grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","type":null,"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"limit":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":false,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","releaseDate":"2026-03-09","lastUpdated":"2026-03-09"},{"providerId":"xai","providerName":"xAI","id":"grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","type":null,"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"limit":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","releaseDate":"2026-03-09","lastUpdated":"2026-03-09"},{"providerId":"xai","providerName":"xAI","id":"grok-4.20-multi-agent-0309","name":"Grok 4.20 Multi-Agent","type":null,"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"limit":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","releaseDate":"2026-03-09","lastUpdated":"2026-03-09"},{"providerId":"xai","providerName":"xAI","id":"grok-4.3","name":"Grok 4.3","type":null,"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"limit":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","releaseDate":"2026-04-17","lastUpdated":"2026-04-17"},{"providerId":"xai","providerName":"xAI","id":"grok-4.5","name":"Grok 4.5","type":null,"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"limit":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","canonicalModelId":"xai/grok-4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","releaseDate":"2026-07-08","lastUpdated":"2026-07-08"},{"providerId":"xai","providerName":"xAI","id":"grok-4.6","name":"Grok 4.6","type":null,"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"limit":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","canonicalModelId":"xai/grok-4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","knowledge":"2026-02-01","releaseDate":"2026-08-12","lastUpdated":"2026-08-12"},{"providerId":"xai","providerName":"xAI","id":"grok-4.7","name":"Grok 4.7","type":null,"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"limit":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","canonicalModelId":"xai/grok-4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","knowledge":"2026-05","releaseDate":"2026-09-21","lastUpdated":"2026-09-21"},{"providerId":"xai","providerName":"xAI","id":"grok-build-0.1","name":"Grok Build 0.1","type":null,"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"limit":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"reasoning":true,"toolCall":true,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok-build","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","releaseDate":"2026-04-16","lastUpdated":"2026-04-16"},{"providerId":"xai","providerName":"xAI","id":"grok-imagine-image","name":"Grok Imagine Image","type":null,"cost":{"input":null,"output":null},"limit":{"context":16000,"output":0},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","description":"Image model for prompt-driven generation, editing, and visual design workflows","releaseDate":"2026-01-28","lastUpdated":"2026-01-28"},{"providerId":"xai","providerName":"xAI","id":"grok-imagine-image-quality","name":"Grok Imagine Image Quality","type":null,"cost":{"input":null,"output":null},"limit":{"context":16000,"output":0},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","canonicalModelId":"xai/grok-imagine-image-quality","description":"Higher-fidelity Grok Imagine image model for prompt-driven generation, editing, and visual design workflows","releaseDate":"2026-04-03","lastUpdated":"2026-04-03"},{"providerId":"xai","providerName":"xAI","id":"grok-imagine-video","name":"Grok Imagine Video","type":null,"cost":{"input":null,"output":null},"limit":{"context":1024,"output":0},"modalities":{"input":["text","image","video","pdf"],"output":["video"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","description":"Image model for prompt-driven generation, editing, and visual design workflows","releaseDate":"2026-01-28","lastUpdated":"2026-01-28"},{"providerId":"xai","providerName":"xAI","id":"grok-imagine-video-1.5","name":"Grok Imagine Video 1.5","type":null,"cost":{"input":null,"output":null},"limit":{"context":1024,"output":0},"modalities":{"input":["text","image","audio","pdf"],"output":["video"]},"reasoning":false,"toolCall":false,"attachment":true,"openWeights":false,"providerDoc":"https://docs.x.ai/docs/models","family":"grok","canonicalModelId":"xai/grok-imagine-video-1.5","description":"Video model for image-to-video generation, editing, and extension workflows","releaseDate":"2026-05-30","lastUpdated":"2026-05-30"}]}