litellm
Open-source AI gateway for unified invocation of 100+ large language models.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 49.3k
- Source
- GitHub
- Added
- 2026-06-05
- Last verified
- 2026-06-05
Overview
LiteLLM is an open-source AI gateway that supports unified API calls to over 100 large language models. It addresses the complexity of managing LLM invocations across different providers, such as varying SDKs, authentication methods, and request formats. Users can integrate it directly into their projects via the Python SDK or deploy the AI gateway as a centralized service for teams or organizations. Targeted at developers, enterprises, and research institutions.
Key features
- ▪Unified API for 100+ LLMs
- ▪Compatible with OpenAI format
- ▪Built-in cost tracking
- ▪Load balancing and logging
Use cases
Pros
- ＋Simplifies multi-vendor integration
- ＋Improves development efficiency
- ＋Enhances security and control
Limitations / notes
- －Requires some technical background
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
What language models does LiteLLM support?
Supports over 100 language models including OpenAI, Azure, Anthropic, and more.
How do I get started with LiteLLM?
You can integrate it directly using the Python SDK or deploy the AI gateway for use.
Something wrong? Let us know on the About page and we'll fix it.