Intro

any-llm is a Python library providing a single interface to different llm providers.

Demo

Try any-llm in action with our interactive chat demo that showcases streaming completions and provider switching:

📂 Run the Demo

The demo features real-time streaming responses, multiple provider support, and collapsible "thinking" content display.

Getting Started

Refer to the Quickstart for instructions on installation and usage.

API Documentation

any-llm provides two main interfaces:

Direct API Functions (recommended for simple use cases): - completion - Chat completions with any provider - embedding - Text embeddings - responses - OpenAI-style Responses API

AnyLLM Class (recommended for advanced use cases): - Provider API - Lower-level provider interface with metadata access and reusability

Error Handling

any-llm provides custom exceptions to indicate common errors like missing API keys and parameters that are unsupported by a specific provider.

For more details on exceptions, see the exceptions API documentation.

For AI Systems

This documentation is available in two AI-friendly formats:

• llms.txt - A structured overview with curated links to key documentation sections
• llms-full.txt - Complete documentation content concatenated into a single file