What is LiteLLM used for?

LiteLLM is an open-source AI gateway and Python SDK that lets you call 100+ LLM providers through one OpenAI-style interface, with spend tracking and load balancing. It is a good fit for central LLM gateway for a team, switching model providers without code changes and tracking spend across LLM usage.

Is LiteLLM open source?

Yes. LiteLLM is open source under a custom licence. Its source code is on GitHub at BerriAI/litellm and is written mainly in Python.

Yes. LiteLLM is open source, so the software itself is free to use under the terms of its own licence. A managed cloud version is also available.

Can I self-host LiteLLM?

Yes. LiteLLM can be self-hosted on your own server or infrastructure.

What is LiteLLM an alternative to?

LiteLLM is an open-source alternative to Amazon Bedrock, OpenRouter, Portkey and Azure AI Foundry. Other open-source alternatives to Amazon Bedrock include Portkey AI Gateway, LLM Gateway and Dify.

Is LiteLLM actively maintained?

Yes. The most recent commit to LiteLLM was on 2 October 2026, and the latest release is v1.103.2, published on 1 October 2026. The project has 60k stars on GitHub.

LiteLLM: open-source alternative to Amazon Bedrock

About LiteLLM

LiteLLM is an AI gateway, open source, offering one unified interface for calling more than 100 LLM providers, including OpenAI, Anthropic, Gemini, Bedrock and Azure, using the OpenAI request format. It can be used as a Python SDK inside an application or deployed as a proxy server that serves a whole team or organization. The core is Python with a Rust component, and GitHub lists the license as 'Other'.

The project aims to remove the hassle of handling a separate SDK, login scheme, request format and set of errors for each model. On top of that the gateway provides load balancing, guardrails, spend tracking, virtual keys and an admin dashboard, and it exposes endpoints for chat completions, responses, embeddings, images, audio, batches and reranking.

Because requests keep the OpenAI format, teams can swap providers without rewriting application code. It is self-hosted, with hosted-proxy and enterprise tier options linked in the README, and its topics also reference an MCP gateway and LLMOps. It suits platform and AI engineering teams that need central control over model access, budgets and logging.

Key features

Unified OpenAI-format interface for 100+ LLMs
Python SDK and proxy server modes
Virtual keys and spend tracking
Guardrails and load balancing
Built-in admin dashboard
Endpoints for chat, embeddings, images and audio

Good fit for

→Central LLM gateway for a team
→Switching model providers without code changes
→Tracking spend across LLM usage

Built with: Python; Rust
Tags: ai-gateway; llm; openai-compatible; llmops; proxy; python; load-balancing; cost-tracking

LiteLLM: questions and answers

What is LiteLLM used for?: LiteLLM is an open-source AI gateway and Python SDK that lets you call 100+ LLM providers through one OpenAI-style interface, with spend tracking and load balancing. It is a good fit for central LLM gateway for a team, switching model providers without code changes and tracking spend across LLM usage.
Is LiteLLM open source?: Yes. LiteLLM is open source under a custom licence. Its source code is on GitHub at BerriAI/litellm and is written mainly in Python.
Is LiteLLM free?: Yes. LiteLLM is open source, so the software itself is free to use under the terms of its own licence. A managed cloud version is also available.
Can I self-host LiteLLM?: Yes. LiteLLM can be self-hosted on your own server or infrastructure.
What is LiteLLM an alternative to?: LiteLLM is an open-source alternative to Amazon Bedrock, OpenRouter, Portkey and Azure AI Foundry. Other open-source alternatives to Amazon Bedrock include Portkey AI Gateway, LLM Gateway and Dify.
Is LiteLLM actively maintained?: Yes. The most recent commit to LiteLLM was on 2 October 2026, and the latest release is v1.103.2, published on 1 October 2026. The project has 60k stars on GitHub.