AI Chat auto-routes to the fastest lightweight model
Generation uses the model best suited for each task. Cost scales dynamically with context size, reasoning depth, and tool usage. Use this library to understand each model's strengths and positioning.
Anthropic's most powerful model. Best for complex reasoning, nuanced writing, and deep code architecture.
Ideal blend of speed and intelligence. Best for coding, analysis, and structured tasks.
Fastest Anthropic model. Best for quick edits, simple questions, and high-volume tasks.
OpenAI's frontier model. Best for deep reasoning, research synthesis, and complex multi-step tasks.
High-capability multimodal model with vision and structured output. Excellent for UI generation.
Fast and cost-efficient. Best for everyday coding tasks, refactoring, and quick answers.
Google's flagship model. Best for large-context analysis, document understanding, and multimodal tasks.
Ultra-fast Google model. Best for rapid iteration, summaries, and lightweight tasks.
Real-time knowledge and strong reasoning. Best for research, analysis, and creative problem-solving.