Skip to main content

W&B Weave

tip

For a limited time, the new W&B Inference service is included in your free tier. W&B Inference provides access to leading open-source foundation models via API and the Weave Playground.

Weights & Biases (W&B) Weave is a framework for tracking, experimenting with, evaluating, deploying, and improving LLM-based applications. Designed for flexibility and scalability, Weave supports every stage of your LLM application development workflow:

Integrate Weave with your existing development stack via the:

Weave supports numerous LLM providers, local models, frameworks, protocols, and third-party services.

Get started

Choose your path to get started with Weave:

Try Weave with W&B Inference - The fastest way to experience Weave

  • No API keys needed - start building immediately
  • Free credits included with all plans
  • Learn tracing, evaluation, and monitoring with real models
  • Access to live instances of powerful models like Llama, GPT-OSS, Qwen, and DeepSeek

Have your own API keys?

Track LLM Calls - Connect your existing LLM providers

  • Works with OpenAI, Anthropic, and more
  • Automatic tracing and cost tracking
  • Perfect if you already have LLM infrastructure

Using TypeScript

TypeScript quickstart - Get started with Weave in TypeScript

Advanced guides

Learn more about advanced topics:

  • Integrations: Use Weave with popular LLM providers, local models, frameworks, and third-party services.
  • Cookbooks: Build with Weave using Python and TypeScript. Tutorials are available as interactive notebooks.
  • W&B AI Academy: Build advanced RAG systems, improve LLM prompting, fine-tune LLMs, and more.