Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

Developer toolsPythonMIT (enterprise features under separate terms)

BerriAI/litellm

LiteLLM standardises calls across providers, supports fallbacks, budgets, rate limits and logging, and can run as a proxy in front of your models. It is useful for cost control and provider abstraction, especially when different teams need keys and spend limits.

33.0k stars4.3k forks780 contributors2100 open issuesUpdated

What it does

  • Maps a consistent interface to many model providers.
  • Runs a proxy with virtual keys, budgets and rate limits.
  • Tracks spend and usage across models.

Key features

  • OpenAI-compatible endpoints.
  • Fallbacks and retries across providers.
  • Budget and key management.
  • Logging and observability integrations.

How to install it

Commands are copied from the project documentation at the time of review. Check the repository for the current version.

Python
pip install litellm[proxy]
litellm --model gpt-4.1-mini

Alternatives to consider

litellm is a strong default for developer tools, but the right choice depends on your stack, licence constraints and how much control you need. These are the projects we compare most often.

OpenRoutervLLMPortkey

Prompts that pair with it

All prompts →
Verified Knowledge · FAQ

litellm FAQ

Adoption questions we hear most often about this project.

Related repositories

Developer tools · TypeScript

Programmatic video creation in React, used with Claude Code & Claude 3.5 Sonnet to build automated YouTube videos and Shorts from code.

24.5k1.6kPolyform Noncommercial 1.0.0