Supported Models

Weco supports models from multiple AI providers. The model you use affects the optimization quality and speed. You can specify which model to use with the -M or --model flag when running weco run.

Default Models

If you don't specify a model, Weco automatically selects a default based on your available API keys:

• o4-mini when OPENAI_API_KEY is set
• claude-sonnet-4-0 when ANTHROPIC_API_KEY is set
• gemini-2.5-pro when GEMINI_API_KEY is set

If more than one API key is available and you don't specify a model, Weco will uses the following precedence:

1. OPENAI_API_KEY
2. ANTHROPIC_API_KEY
3. GEMINI_API_KEY

For information on setting up API keys, see our Getting Started guide.

OpenAI

• o3
• o3-mini
• o4-mini
• o1-pro
• o1
• gpt-4.1
• gpt-4.1-mini
• gpt-4.1-nano
• gpt-4o
• gpt-4o-mini

Anthropic

• claude-opus-4-0
• claude-sonnet-4-0
• claude-3-7-sonnet-latest

Google

• gemini-2.5-pro
• gemini-2.5-flash
• gemini-2.5-flash-lite

What's Next?

• Start optimizing: Follow the Getting Started guide to set up your API key and run your first optimization
• Choose the right model: Different models offer trade-offs between speed and quality - experiment to find what works best for your use case
• Learn more about CLI options: Check the CLI Reference for all available command flags and options
• Write better evaluations: Read our guide on Writing Good Evaluation Scripts to get the most out of your optimizations