AI Models
The underlying AI models that power our agents, each with different capabilities.
Anthropic Claude
Anthropic is an AI safety company and public benefit corporation that builds the Claude family of large language models. Founded in 2021, Anthropic focuses on developing reliable, steerable AI designed to be helpful, harmless, and honest.
Fast and intelligent model for quick tasks
The best combination of speed and intelligence, with adaptive thinking and long context support
Most intelligent Claude model with adaptive thinking for complex reasoning and agentic workflows
Google Gemini
Google DeepMind's Gemini models offer multimodal understanding with large context windows, strong reasoning, and efficient performance across tasks.
Google's fastest Gemini 3 model, optimized for speed and efficiency while maintaining strong reasoning capabilities.
Google's most advanced Gemini 3.1 model with powerful agentic capabilities, multimodal understanding, and state-of-the-art reasoning.
Google's state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.
Google's fast general-use model, capable of handling a wide range of tasks with large amounts of context with speed and efficiency.
Mistral AI
Mistral AI builds efficient, open-weight language models. Known for strong multilingual support, fast inference, and competitive performance at lower cost.
Hybrid model optimized for general chat, coding, agentic tasks, and complex reasoning with text and image input support
Balanced model for most tasks with good performance and cost efficiency
Mistral's most capable model with strong multilingual support and advanced reasoning for complex tasks
OpenAI GPT
OpenAI's GPT models deliver strong general-purpose intelligence with broad knowledge, creative writing, and code generation capabilities.
GPT-5.4 is OpenAI's frontier model with a 1M context window, built-in computer-use capabilities, and optional reasoning.
GPT-5.2 is OpenAI's flagship model for coding and agentic tasks.
GPT 5.4 mini is an optimized version of GPT 5.4 — fast and efficient for everyday tasks.
GPT-5 mini is a fast, cost-efficient version of GPT-5, great for everyday tasks.
Last version of GPT 4
OpenRouter
OpenRouter provides unified access to hundreds of AI models from different providers through a single API endpoint.
Z-AI's fast and efficient general-purpose model with strong multilingual capabilities.
Moonshot AI's advanced reasoning model with strong performance on complex tasks.
xAI's fast model with an unprecedented 2 million token context window.
DeepSeek's efficient reasoning model with strong coding and math capabilities.
MiniMax's latest general-purpose model with strong reasoning and large context support.
OpenAI's open-source 120B parameter model available through OpenRouter.
Qwen's high-performance model with 1 million token context window.
Qwen's fast and efficient model optimized for speed with 1M context.
Anthropic Claude
Anthropic is an AI safety company and public benefit corporation that builds the Claude family of large language models. Founded in 2021, Anthropic focuses on developing reliable, steerable AI designed to be helpful, harmless, and honest.
Fast and intelligent model for quick tasks
claude-haiku-4-5 The best combination of speed and intelligence, with adaptive thinking and long context support
claude-sonnet-4-6 Most intelligent Claude model with adaptive thinking for complex reasoning and agentic workflows
claude-opus-4-6 Google Gemini
Google DeepMind's Gemini models offer multimodal understanding with large context windows, strong reasoning, and efficient performance across tasks.
Google's fastest Gemini 3 model, optimized for speed and efficiency while maintaining strong reasoning capabilities.
google/gemini-3-flash-preview Google's most advanced Gemini 3.1 model with powerful agentic capabilities, multimodal understanding, and state-of-the-art reasoning.
google/gemini-3.1-pro-preview Google's state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.
google/gemini-2.5-pro Google's fast general-use model, capable of handling a wide range of tasks with large amounts of context with speed and efficiency.
google/gemini-2.5 Mistral AI
Mistral AI builds efficient, open-weight language models. Known for strong multilingual support, fast inference, and competitive performance at lower cost.
Hybrid model optimized for general chat, coding, agentic tasks, and complex reasoning with text and image input support
mistral-small-2603 Balanced model for most tasks with good performance and cost efficiency
mistral-medium-latest Mistral's most capable model with strong multilingual support and advanced reasoning for complex tasks
mistral-large-latest OpenAI GPT
OpenAI's GPT models deliver strong general-purpose intelligence with broad knowledge, creative writing, and code generation capabilities.
GPT-5.4 is OpenAI's frontier model with a 1M context window, built-in computer-use capabilities, and optional reasoning.
gpt-5.4 GPT-5.2 is OpenAI's flagship model for coding and agentic tasks.
gpt-5.2 GPT 5.4 mini is an optimized version of GPT 5.4 — fast and efficient for everyday tasks.
gpt-5.4-mini GPT-5 mini is a fast, cost-efficient version of GPT-5, great for everyday tasks.
gpt-5-mini Last version of GPT 4
gpt-4.1 OpenRouter
OpenRouter provides unified access to hundreds of AI models from different providers through a single API endpoint.
Z-AI's fast and efficient general-purpose model with strong multilingual capabilities.
openrouter/z-ai/glm-5-turbo Moonshot AI's advanced reasoning model with strong performance on complex tasks.
openrouter/moonshotai/kimi-k2.5 xAI's fast model with an unprecedented 2 million token context window.
openrouter/x-ai/grok-4.1-fast DeepSeek's efficient reasoning model with strong coding and math capabilities.
openrouter/deepseek/deepseek-v3.2 MiniMax's latest general-purpose model with strong reasoning and large context support.
openrouter/minimax/minimax-m2.7 OpenAI's open-source 120B parameter model available through OpenRouter.
openrouter/openai/gpt-oss-120b Qwen's high-performance model with 1 million token context window.
openrouter/qwen/qwen3.5-plus-02-15 Qwen's fast and efficient model optimized for speed with 1M context.
openrouter/qwen/qwen3.5-flash-02-23