AI · Early access

LiteLLM hosting on your own server

A single API gateway for calling over 100 different LLM providers.

Early access. Join the list and we email you when LiteLLM opens on VPS.

What LiteLLM does

LiteLLM presents one OpenAI-compatible API in front of more than a hundred LLM providers, handling routing, cost tracking, rate limiting, and fallback between models. Teams self-host it as a central gateway so applications don't need provider-specific code for each model they use. It can also enforce spend limits and generate scoped virtual API keys for individual teams or projects.

LiteLLM at a glance

License: MIT
Source code: github.com/BerriAI/litellm
Website: docs.litellm.ai
Runs on: Your own server (VPS)
Good to know: Lightweight to run; needs a database for logging and virtual keys at any real traffic volume.

Unified gateway for multiple LLM providers
Centralized cost and usage tracking
Fallback and load balancing across models

LiteLLM, connected to the rest of your business

On your domain
LiteLLM answers at an address like litellm.yourbusiness.com, with SSL and daily backups switched on.
Mail from your address
LiteLLM sends its emails from your CloudWish business mailbox. Business email
AI with a cap you set
Give LiteLLM its own AI key with a monthly spend cap. Usage shows as its own line on your bill. AI in your apps (early access)