# LiteLLM

AI gateway and Python SDK for calling many LLM providers through OpenAI-compatible or native formats.

## Summary
LiteLLM is a Python SDK and proxy server used by AI builders to route requests across many model providers, track cost, add logging, and manage gateway behavior.


## Guide
LiteLLM is a Python SDK and proxy server used by AI builders to route requests across many model providers, track cost, add logging, and manage gateway behavior.

### What it is
LiteLLM is listed on OpenAgent.bot as a tools resource for open AI builders.

### Why it matters
Agent applications often need provider routing, fallbacks, cost tracking, and observability before they can be trusted in production. LiteLLM gives teams a practical gateway layer for those needs.

### How it works
Start from the official source links, then validate the project against your deployment needs, license requirements, and maintenance expectations.


### Getting Started
- Review the repository: https://github.com/BerriAI/litellm
- Homepage: https://docs.litellm.ai/docs/
## Why It Matters
Agent applications often need provider routing, fallbacks, cost tracking, and observability before they can be trusted in production. LiteLLM gives teams a practical gateway layer for those needs.


## Best For
- Teams routing agent traffic across multiple model providers
- Developers who want OpenAI-compatible access to many LLM APIs
- Builders adding cost tracking, load balancing, and gateway logs

## Not For
- Teams that only call one model provider directly
- Users who do not want to operate a gateway or proxy

## What It Actually Does
- Model serving: LiteLLM surfaces model serving as a core capability in its published project metadata and source links.
  - Why it matters: This gives readers a starting point for evaluating whether the project fits their workflow before visiting the source repository or docs.
- Inference: LiteLLM surfaces inference as a core capability in its published project metadata and source links.
  - Why it matters: This gives readers a starting point for evaluating whether the project fits their workflow before visiting the source repository or docs.
- Connectors: LiteLLM surfaces connectors as a core capability in its published project metadata and source links.
  - Why it matters: This gives readers a starting point for evaluating whether the project fits their workflow before visiting the source repository or docs.

## Typical Use Cases
- Self hosted ai: Use it as a candidate for self hosted ai when the project facts, license, and official links match your deployment requirements.

## How It Compares
- When to choose LiteLLM: Compare it with nearby tools by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need.

## Command Line
### Install or run
```bash
pip install litellm
```

## Facts
- Category: tools
- Resource type: tool
- Open source: no
- License: See repository
- Last verified: 2026-06-02
- GitHub repo: BerriAI/litellm
- GitHub stars: 48958

## Capabilities
- model-serving
- inference
- connectors

## Structured Use Case Tags
- self-hosted-ai

## Getting Started
- Review the repository: https://github.com/BerriAI/litellm
- Homepage: https://docs.litellm.ai/docs/

## Links
- GitHub: https://github.com/BerriAI/litellm
- Homepage: https://docs.litellm.ai/docs/

## Structured Outputs
- JSON: https://www.openagent.bot/tools/litellm.json
- Markdown: https://www.openagent.bot/tools/litellm.md
- Canonical: https://www.openagent.bot/tools/litellm