AI gateway unifying 100+ LLM providers under one OpenAI-compatible API. Cost tracking, guardrails, load balancing. pip install litellm. 47k GitHub stars.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Spend Tracking
Use LiteLLM to track and budget LLM spend: ‹what you need›
- Load Balancing
Use LiteLLM to distribute requests across multiple model deployments: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: docs.litellm.ai
Call the API
Auth An API key from BerriAI
Its page: docs.litellm.ai
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLI
- Auth
- API Key
- Skills
- 3
Skills
Provider Unification
Call OpenAI, Anthropic, Azure, Bedrock, Vertex AI, and 95+ providers through one unified API format.
Spend Tracking
Track and budget LLM spend per user, team, or API key with automatic cost attribution across all providers.
Load Balancing
Distribute requests across multiple model deployments with fallback routing and rate limit management.