Manage AI models centrally
LiteLLM is an AI gateway that unifies more than 100 large language model (LLM) interfaces into a single standard format. It makes it easy to switch between different model providers by offering software developers features such as cost tracking, load balancing, and guardrails.
Updates
- October 26, 2026: Stars 61,984 → 62,039, latest release v1.106.4 (October 25, 2026).
- October 25, 2026: Stars 61,793 → 61,984, latest release v1.106.3 (October 24, 2026).
- October 22, 2026: Stars 61,715 → 61,793, latest release v1.106.2 (October 21, 2026).
- October 21, 2026: Stars 61,706 → 61,715, latest release v1.107.0 (October 21, 2026).
What you get
- Prevents code clutter by unifying more than a hundred LLM (Large Language Model) providers into a single standard format.
- Eliminates the need to rewrite your codebase when switching between AI models.
- Offers an enterprise-grade management infrastructure with tools such as virtual keys, budget tracking, and load balancing.
Installation
uv add litellmRunning it
uv tool install 'litellm[proxy]'
litellm --model gpt-4oIf you don't write code
You are a software development assistant. In our project, we want to use the LiteLLM tool to manage different AI models from a single central hub. First, help me install the library by running the 'uv add litellm' command in the terminal. Then, explain step-by-step how to start a local gateway server for the large language model gpt-4o using the commands 'uv tool install 'litellm[proxy]'' and 'litellm --model gpt-4o', and how I can route models through this server.
Repository: https://github.com/BerriAI/litellm. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-10-09: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.