Join us Tuesday, May 19th, for a town hall to discuss LiteLLM's Roadmap.
Backed by Y Combinator

Give Developers
LLM Access

AI Gateway to provide model access, fallbacks and spend tracking across 100+ LLMs. All in the OpenAI format.

Request Pricing → Deploy LiteLLM On-Prem →
LiteLLM Dashboard
Azure Access • Azure OpenAI Gemini Access • Google Gemini Bedrock Access • AWS Bedrock OpenAI Access • OpenAI Anthropic Access • Anthropic Claude 100+ • More Providers Azure Access • Azure OpenAI Gemini Access • Google Gemini Bedrock Access • AWS Bedrock OpenAI Access • OpenAI Anthropic Access • Anthropic Claude 100+ • More Providers
240M+
docker pulls
1B+
requests served
80%
uptime
1,005+
contributors

What is LiteLLM?

LiteLLM simplifies model access, spend tracking and fallbacks across 100+ LLMs. Watch this demo, to learn more.

LiteLLM Demo Video

🚅 LiteLLM

Cost Tracking
Batches API
Guardrails
Model Access
Budgets
LLM Observability
Rate Limiting
Prompt Management
S3 Logging
Pass-Through Endpoints

Features

LiteLLM makes it easy for Platform teams to give developers LLM access

Spend Tracking Budgets & Rate Limits OpenAI-Compatible LLM Fallbacks

Spend Tracking

Accurately charge teams for their usage. Track every API call across providers with full cost attribution.

Budgets & Rate Limits

Set per-key, per-user, or per-team budgets with RPM/TPM rate limits. Load balance across multiple deployments of the same model.

OpenAI-Compatible

Full OpenAI API compatibility — use any OpenAI SDK directly with LiteLLM. Prompt formatting support for Hugging Face models.

LLM Fallbacks

Configure automatic fallback chains across providers and models for high availability. If one provider fails, LiteLLM routes to the next.

LiteLLM Spend Tracking Dashboard

Trusted by Engineering Teams Worldwide

Customer logos

The Best Pricing Plans

Open Source
$0
Free
  • 100+ LLM Provider Integrations
  • Langfuse, Arize Phoenix, Langsmith, OTEL logging
  • Virtual keys, budgets, teams
  • Load balancing, RPM/TPM limits
  • LLM guardrails
View on GitHub →
Enterprise
Custom
30-day trial available
  • Everything in Open Source
  • JWT Auth, SSO, Audit Logs
  • Custom SLAs & dedicated support
  • Team/Org admins & key rotations
  • Cloud or self-hosted deployment
Request Pricing →

Trusted by Industry Leaders

"LiteLLM has let my team provide the latest LLM models to our users usually within a day of them being released. Without LiteLLM this would be hours of work each time a new model is announced. It means we don't have to transform inputs and outputs across providers and has saved us months of work."
David Leen
David Leen
Staff Software Engineer, Netflix
"Our experience with LiteLLM and Langfuse at Lemonade has been outstanding. LiteLLM streamlines the complexities of managing multiple LLM models, enabling our team to focus on building innovative features rather than wrestling with API integrations. It's an essential part of our GenAI platform."
Mark Koltnuk
Mark Koltnuk
Principal Architect (GenAI Platform), Lemonade

Get Started with LiteLLM

Deploy on-prem, explore the open-source repo, or try Enterprise with a 30-day trial.

Deploy On-Prem → Open Source → Enterprise →