{"anthropic/claude-opus-4.6":{"maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsReasoningEffort":["disable","low","medium","high"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Opus 4.6 is the world's best model for coding and professional work, built to power agents that take on whole categories of real-world work. It excels across the entire SDLC, breaking through on hard problems, identifying complex bugs, and demonstrating deeper codebase understanding. It also delivers a step-change in knowledge work, with near-production-ready documents, presentations, and spreadsheets on the first pass.","deprecated":false,"isFree":false,"defaultTemperature":0,"reasoningEffort":"medium"},"anthropic/claude-opus-4.5":{"maxTokens":16384,"contextWindow":200000,"supportsImages":true,"supportsReasoningEffort":["disable","low","medium","high"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Claude Opus 4.5 is Anthropic's latest model in the Opus series, meant for demanding reasoning tasks and complex problem solving. This model has improvements in general intelligence and vision compared to previous iterations. In addition, it is suited for difficult coding tasks and agentic workflows, especially those with computer use and tool use, and can effectively handle context usage and external memory files.","deprecated":false,"isFree":false,"defaultTemperature":0,"reasoningEffort":"medium"},"anthropic/claude-opus-4.1":{"maxTokens":16384,"contextWindow":200000,"supportsImages":true,"supportsReasoningEffort":["disable","low","medium","high"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":15,"outputPrice":75,"cacheWritesPrice":18.75,"cacheReadsPrice":1.5,"description":"Claude Opus 4.1 is a drop-in replacement for Opus 4 that delivers superior performance and precision for real-world coding and agentic tasks. Opus 4.1 advances state-of-the-art coding performance to 74.5% on SWE-bench Verified, and handles complex, multi-step problems with more rigor and attention to detail.","deprecated":false,"isFree":false,"defaultTemperature":0,"reasoningEffort":"medium"},"anthropic/claude-sonnet-4.5":{"maxTokens":64000,"contextWindow":1000000,"supportsImages":true,"supportsReasoningEffort":["disable","low","medium","high"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3,"description":"Claude Sonnet 4.5 is the newest model in the Sonnet series, offering improvements and updates over Sonnet 4.","deprecated":false,"isFree":false,"defaultTemperature":0,"reasoningEffort":"medium"},"anthropic/claude-haiku-4.5":{"maxTokens":16384,"contextWindow":200000,"supportsImages":true,"supportsReasoningEffort":["disable","low","medium","high"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":1,"outputPrice":5,"cacheWritesPrice":1.25,"cacheReadsPrice":0.09999999999999999,"description":"Claude Haiku 4.5 matches Sonnet 4's performance on coding, computer use, and agent tasks at substantially lower cost and faster speeds. It delivers near-frontier performance and Claude's unique character at a price point that works for scaled sub-agent deployments, free tier products, and intelligence-sensitive applications with budget constraints.","deprecated":false,"isFree":false,"reasoningEffort":"medium"},"moonshotai/kimi-k2-turbo":{"maxTokens":16384,"contextWindow":256000,"supportsImages":false,"supportsReasoningEffort":false,"requiredReasoningEffort":false,"supportsPromptCache":false,"inputPrice":2.4,"outputPrice":10,"description":"Kimi K2 Turbo is the high-speed version of kimi-k2, with the same model parameters as kimi-k2, but the output speed is increased to 60 tokens per second, with a maximum of 100 tokens per second, the context length is 256k","deprecated":false,"isFree":false},"minimax/minimax-m2.1":{"maxTokens":16384,"contextWindow":204800,"supportsImages":false,"supportsReasoningEffort":true,"requiredReasoningEffort":true,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":1.2,"cacheWritesPrice":0.375,"cacheReadsPrice":0.03,"description":"MiniMax 2.1 is MiniMax's latest model, optimized specifically for robustness in coding, tool use, instruction following, and long-horizon planning.","deprecated":false,"isFree":false,"includedTools":["search_and_replace"],"excludedTools":["apply_diff"]},"minimax/minimax-m2.1-lightning":{"maxTokens":16384,"contextWindow":204800,"supportsImages":false,"supportsReasoningEffort":true,"requiredReasoningEffort":true,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":2.4,"cacheWritesPrice":0.375,"cacheReadsPrice":0.03,"description":"MiniMax-M2.1-lightning is a faster version of MiniMax-M2.1, offering the same performance but with significantly higher throughput (output speed ~100 TPS, MiniMax-M2 output speed ~60 TPS).","deprecated":false,"isFree":false,"includedTools":["search_and_replace"],"excludedTools":["apply_diff"]},"zai/glm-4.6":{"maxTokens":16384,"contextWindow":200000,"supportsImages":false,"supportsReasoningEffort":true,"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":0.44999999999999996,"outputPrice":1.7999999999999998,"cacheReadsPrice":0.11,"description":"As the latest iteration in the GLM series, GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications.","deprecated":false,"isFree":false,"defaultTemperature":0.6},"zai/glm-4.7":{"maxTokens":16384,"contextWindow":200000,"supportsImages":false,"supportsReasoningEffort":["disable","medium"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":0.6,"outputPrice":2.2,"cacheReadsPrice":0.11,"description":"GLM-4.7 is Z.AI's latest flagship model, with major upgrades focused on two key areas: stronger coding capabilities and more stable multi-step reasoning and execution.","deprecated":false,"isFree":false,"defaultTemperature":0.6,"reasoningEffort":"medium"},"zai/glm-5":{"maxTokens":16384,"contextWindow":202800,"supportsImages":false,"supportsReasoningEffort":["disable","medium"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":1,"outputPrice":3.1999999999999997,"cacheReadsPrice":0.19999999999999998,"description":"GLM-5 is Zai's new-generation flagship foundation model, designed for Agentic Engineering, capable of providing reliable productivity in complex system engineering and long-range Agent tasks. In terms of Coding and Agent capabilities, GLM-5 has achieved state-of-the-art (SOTA) performance in open source, with its usability in real programming scenarios approaching that of Claude Opus 4.5.","deprecated":false,"isFree":false,"defaultTemperature":0.6,"reasoningEffort":"medium"},"openai/gpt-5.2":{"maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsReasoningEffort":["none","low","medium","high","xhigh"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":1.75,"outputPrice":14,"cacheWritesPrice":0,"cacheReadsPrice":0.175,"description":"GPT-5.2: Our flagship model for coding and agentic tasks across industries","deprecated":false,"isFree":false,"includedTools":["apply_patch"],"excludedTools":["apply_diff","write_to_file"],"reasoningEffort":"medium","supportsTemperature":false},"openai/gpt-5.2-codex":{"maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsReasoningEffort":["none","low","medium","high","xhigh"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":1.75,"outputPrice":14,"cacheWritesPrice":0,"cacheReadsPrice":0.175,"description":"GPT‑5.2-Codex is a version of GPT‑5.2⁠ further optimized for agentic coding in Codex, including improvements on long-horizon work through context compaction, stronger performance on large code changes like refactors and migrations, improved performance in Windows environments, and significantly stronger cybersecurity capabilities.","deprecated":false,"isFree":false,"includedTools":["apply_patch"],"excludedTools":["apply_diff","write_to_file"],"supportsTemperature":false,"reasoningEffort":"medium"},"openai/gpt-5.1":{"maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsReasoningEffort":["none","low","medium","high"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheWritesPrice":0,"cacheReadsPrice":0.13,"description":"An upgraded version of GPT-5 that adapts thinking time more precisely to the question to spend more time on complex questions and respond more quickly to simpler tasks.","deprecated":false,"isFree":false,"includedTools":["apply_patch"],"excludedTools":["apply_diff","write_to_file"],"reasoningEffort":"medium","supportsTemperature":false},"openai/gpt-5.1-codex-max":{"maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsReasoningEffort":["low","medium","high","xhigh"],"requiredReasoningEffort":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheWritesPrice":0,"cacheReadsPrice":0.125,"description":"GPT-5.1 Codex Max: Our most intelligent coding model optimized for long-horizon, agentic coding tasks.","deprecated":false,"isFree":false,"includedTools":["apply_patch"],"excludedTools":["apply_diff","write_to_file"],"supportsTemperature":false,"reasoningEffort":"xhigh"},"openai/gpt-5":{"maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsReasoningEffort":["none","low","medium","high"],"requiredReasoningEffort":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheWritesPrice":0,"cacheReadsPrice":0.13,"description":"GPT-5 is OpenAI's flagship language model that excels at complex reasoning, broad real-world knowledge, code-intensive, and multi-step agentic tasks.","deprecated":false,"isFree":false,"includedTools":["apply_patch"],"excludedTools":["apply_diff","write_to_file"],"reasoningEffort":"medium","supportsTemperature":false},"openai/gpt-5-mini":{"maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsReasoningEffort":["none","low","medium","high"],"requiredReasoningEffort":true,"supportsPromptCache":true,"inputPrice":0.25,"outputPrice":2,"cacheWritesPrice":0,"cacheReadsPrice":0.03,"description":"GPT-5 mini is a cost optimized model that excels at reasoning/chat tasks. It offers an optimal balance between speed, cost, and capability.","deprecated":false,"isFree":false,"includedTools":["apply_patch"],"excludedTools":["apply_diff","write_to_file"],"reasoningEffort":"medium","supportsTemperature":false},"google/gemini-2.5-pro":{"maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsReasoningEffort":["low","medium","high"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheReadsPrice":0.125,"description":"Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 2.5 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, and even entire code repositories.","deprecated":false,"isFree":false,"defaultTemperature":1,"reasoningEffort":"low"},"google/gemini-3-pro-preview":{"maxTokens":64000,"contextWindow":1000000,"supportsImages":true,"supportsReasoningEffort":["low","high"],"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":2,"outputPrice":12,"cacheReadsPrice":0.19999999999999998,"description":"This model improves upon Gemini 2.5 Pro and is catered towards challenging tasks, especially those involving complex reasoning or agentic workflows. Improvements highlighted include use cases for coding, multi-step function calling, planning, reasoning, deep knowledge tasks, and instruction following.","deprecated":false,"isFree":false,"defaultTemperature":1,"reasoningEffort":"high"},"google/gemini-3-flash":{"maxTokens":64000,"contextWindow":1000000,"supportsImages":true,"supportsReasoningEffort":["minimal","low","medium","high"],"requiredReasoningEffort":false,"supportsPromptCache":false,"inputPrice":0.5,"outputPrice":3,"description":"Google's most intelligent model built for speed, combining frontier intelligence with superior search and grounding.","deprecated":false,"isFree":false,"defaultTemperature":1,"reasoningEffort":"medium"},"roo/code-supernova":{"maxTokens":30000,"contextWindow":1000000,"supportsImages":true,"supportsReasoningEffort":true,"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":0,"outputPrice":0,"cacheWritesPrice":0,"cacheReadsPrice":0,"description":"A versatile agentic coding stealth model with a 1M token context window that supports image inputs, accessible for free through Roo Code Cloud for a limited time. (Note: the free prompts and completions are logged by the model provider and used to improve the model.)","deprecated":true,"isFree":true},"roo/code-supernova-1-million":{"maxTokens":30000,"contextWindow":1000000,"supportsImages":true,"supportsReasoningEffort":true,"requiredReasoningEffort":false,"supportsPromptCache":true,"inputPrice":0,"outputPrice":0,"cacheWritesPrice":0,"cacheReadsPrice":0,"description":"A versatile agentic coding stealth model with a 1M token context window that supports image inputs, accessible for free through Roo Code Cloud for a limited time. (Note: the free prompts and completions are logged by the model provider and used to improve the model.)","deprecated":true,"isFree":true},"xai/grok-code-fast-1":{"maxTokens":16384,"contextWindow":262144,"supportsImages":false,"supportsReasoningEffort":true,"requiredReasoningEffort":true,"supportsPromptCache":true,"inputPrice":0,"outputPrice":0,"cacheWritesPrice":0,"cacheReadsPrice":0,"description":"A reasoning model that is blazing fast and excels at agentic coding, accessible for free through Roo Code Cloud for a limited time. (Note: the free prompts and completions are logged by xAI and used to improve the model.)","deprecated":true,"isFree":true,"defaultTemperature":0.7,"includedTools":["search_replace"],"excludedTools":["apply_diff"]},"roo/sonic":{"maxTokens":16384,"contextWindow":262144,"supportsImages":false,"supportsReasoningEffort":true,"requiredReasoningEffort":true,"supportsPromptCache":true,"inputPrice":0,"outputPrice":0,"cacheWritesPrice":0,"cacheReadsPrice":0,"description":"A reasoning model that is blazing fast and excels at agentic coding, accessible for free through Roo Code Cloud for a limited time. (Note: the free prompts and completions are logged by xAI and used to improve the model.)","deprecated":true,"isFree":true,"defaultTemperature":0.7,"includedTools":["search_replace"],"excludedTools":["apply_diff"]},"deepseek/deepseek-chat-v3.1":{"maxTokens":16384,"contextWindow":163840,"supportsImages":false,"supportsReasoningEffort":false,"requiredReasoningEffort":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active). It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference.","deprecated":true,"isFree":true},"minimax/minimax-m2:free":{"maxTokens":16384,"contextWindow":204800,"supportsImages":false,"supportsReasoningEffort":true,"requiredReasoningEffort":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows, offered for free to the Roo Code community for a limited time with reasonable rate limits. If rate limits are a concern, use the paid version through the OpenRouter provider. (Note: all prompts and completions for the free version are logged by the provider and may be used to improve the model.)","deprecated":true,"isFree":true,"defaultTemperature":1,"includedTools":["search_and_replace"],"excludedTools":["apply_diff"]},"minimax/minimax-m2":{"maxTokens":16384,"contextWindow":204800,"supportsImages":false,"supportsReasoningEffort":true,"requiredReasoningEffort":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows, offered for free to the Roo Code community for a limited time with reasonable rate limits. If rate limits are a concern, use the paid version through the OpenRouter provider. (Note: all prompts and completions for the free version are logged by the provider and may be used to improve the model.)","deprecated":true,"isFree":true,"defaultTemperature":1,"includedTools":["search_and_replace"],"excludedTools":["apply_diff"]},"minimax/minimax-m2.1:free":{"maxTokens":16384,"contextWindow":204800,"supportsImages":false,"supportsReasoningEffort":true,"requiredReasoningEffort":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"MiniMax 2.1 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows, offered for free to the Roo Code community for a limited time with reasonable rate limits. (Note: all prompts and completions for the free version are logged by the provider and may be used to improve the model.)","deprecated":true,"isFree":true,"defaultTemperature":1,"includedTools":["search_and_replace"],"excludedTools":["apply_diff"]},"kwaipilot/kat-coder-pro":{"maxTokens":32000,"contextWindow":256000,"supportsImages":false,"supportsReasoningEffort":false,"requiredReasoningEffort":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"KAT-Coder-Pro V1 is KwaiKAT's most advanced agentic coding model in the KAT-Coder series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, achieving 73.4% solve rate on the SWE-Bench Verified benchmark.","deprecated":true,"isFree":true},"openrouter/polaris-alpha":{"maxTokens":16384,"contextWindow":256000,"supportsImages":false,"supportsReasoningEffort":false,"requiredReasoningEffort":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"This is a cloaked model provided to the community to gather feedback. A powerful, general-purpose model that excels across real-world tasks, with standout performance in coding, tool calling, and instruction following. (Note: all prompts and completions for this model are logged by the provider and may be used to improve the model.)","deprecated":true,"isFree":true},"openrouter/sherlock-dash-alpha:free":{"maxTokens":64000,"contextWindow":1840000,"supportsImages":true,"supportsReasoningEffort":false,"requiredReasoningEffort":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"This is a cloaked model provided to the community to gather feedback. A frontier non-reasoning model that excels at tool calling, with a 1.8M context window and multimodal support. (Note: all prompts and completions for this model are logged by the provider and may be used to improve the model.)","deprecated":true,"isFree":true},"openrouter/sherlock-think-alpha:free":{"maxTokens":64000,"contextWindow":1840000,"supportsImages":true,"supportsReasoningEffort":true,"requiredReasoningEffort":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"This is a cloaked model provided to the community to gather feedback. A frontier reasoning model that excels at tool calling, with a 1.8M context window and multimodal support. (Note: all prompts and completions for this model are logged by the provider and may be used to improve the model.)","deprecated":true,"isFree":true}}