BerriAI/litellm
LiteLLM is an AI gateway that exposes 100+ model providers through a single OpenAI-compatible API. It runs as a Python SDK or as a proxy server with virtual keys, spend tracking, budgets, rate limits, guardrails, load balancing, and an admin dashboard. Requests can be routed, retried, and failed over between OpenAI, Anthropic, Gemini, Bedrock, Azure, and other providers, and the Python-based project ships Docker deployment options for a self-hosted gateway.
Maintenance activity