litellm
Call more than 100 models through one interface and govern LLM traffic centrally.
- Stars
- 53,206
- Forks
- 9,642
- Updated
- Updated Jul 10, 2026
Call more than 100 models through one interface and govern LLM traffic centrally.
LiteLLM works as either a Python SDK or a self-hosted AI gateway, exposing more than 100 providers through a unified OpenAI-compatible interface. Teams can switch among services such as OpenAI, Anthropic, Gemini, Bedrock, and Azure without rewriting every integration, while centralizing virtual keys, spend tracking, load balancing, logging, and guardrails at the gateway.
Resource types
Use cases
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Build AI apps and agents through one provider-agnostic TypeScript API.
Create MCP servers and clients with concise Python APIs.
Build MCP servers, clients, and runtime integrations in TypeScript.
Generate AI music through an SDK, CLI, MCP server, or agent skill