litellm

Library to easily interface with LLM API providers

litellm Permissive license MIT Active ★ 56,269 v1.96.2 released 2026-08-11

Install

litellm on PyPI

pip

pip install litellm

uv

uv add litellm

poetry

poetry add litellm

Package facts

License	MIT (permissive)
Python support	supports the current Python release (<3.15,>=3.10)
Install friction	medium — platform-specific wheel
Runtime dependencies	13 — fastuuid, httpx, openai, python-dotenv, tiktoken, importlib-metadata, tokenizers, click, jinja2, aiohttp, pydantic, pydantic-settings, jsonschema
Maintenance	actively maintained — 2 days since the last release
Last repo commit	2026-08-13
First released	2023-07-27
Popularity	one of the 100 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: litellm-1.96.2-cp310-abi3-macosx_10_12_x86_64.whl; litellm-1.96.2-cp310-abi3-macosx_11_0_arm64.whl; litellm-1.96.2-cp310-abi3-manylinux_2_28_aarch64.whl; litellm-1.96.2-cp310-abi3-manylinux_2_28_x86_64.whl; litellm-1.96.2-cp310-abi3-musllinux_1_2_aarch64.whl; litellm-1.96.2-cp310-abi3-musllinux_1_2_x86_64.whl; litellm-1.96.2-cp310-abi3-win_amd64.whl

About litellm

from the package's own PyPI description — quoted content, verbatim

<h1 align="center"> 🚅 LiteLLM </h1> <p align="center"> <p align="center">LiteLLM AI Gateway </p> <p align="center">Open Source AI Gateway for 100+ LLMs. Self-hosted. Enterprise-ready. Call any LLM in OpenAI format.</p> <p align="center"> <a href="https://render.com/deploy?repo=https://github.com/BerriAI/litellm" target="_blank" rel="nofollow"><img src="https://render.com/images/deploy-to-render-button.svg" alt="Deploy to Render" height="40"></a> <a href="https://railway.com/deploy/RhvhdC?referralCode=7mRv9K&utm_medium=integration&utm_source=template&utm_campaign=generic"><img src="https://railway.com/button.svg" alt="Deploy on Railway" height="40"></a> <a href="https://console.aws.amazon.com/cloudshell/home" target="_blank" rel="nofollow"><img src="./.github/deploy-on-aws.png" alt="Deploy on AWS" height="40"></a> <a...

Read as markdown · JSON record · Source repository · Homepage · Docs

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

LiteLLM provides a unified Python SDK and self-hosted AI Gateway to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, etc.) through a single OpenAI-compatible interface.

Medium friction: 13 runtime dependencies including httpx, openai, tiktoken, pydantic, and aiohttp. Active maintenance with latest release 2 days old and 56269 GitHub stars suggest solid upkeep, though the dependency footprint warrants review for your environment.

MIT license (permissive) allows free use, modification, and distribution with minimal restrictions—suitable for both open-source and commercial projects.

Usage

pip install litellm

from litellm import completion
import os

os.environ["OPENAI_API_KEY"] = "your-key"
response = completion(model="openai/gpt-4o", messages=[{"role": "user", "content": "Hello!"}])

Requires Python >=3.10,<3.15; API keys for at least one LLM provider must be set as environment variables.

Verdict: LiteLLM is a well-maintained, top-100 PyPI package offering a practical unified interface to 100+ LLM providers via OpenAI-compatible SDK or self-hosted gateway. No known vulnerabilities, permissive MIT license, and 56269 GitHub stars indicate strong adoption; medium install friction from 13 dependencies is typical for this scope.

Needs verification

Whether the 13 runtime dependencies introduce transitive security concerns beyond the 0 direct OSV findings.
Performance overhead of the unified interface compared to direct provider SDKs in latency-critical workloads.
Compatibility guarantees across the 100+ supported providers and their API evolution.

llm gateway unified apiopenai compatible proxymulti-provider llm clientself-hosted ai gatewayllm provider abstractioncentralized llm routingllm load balancinglllm api abstraction