Compare features
Everything in LiteLLM Free and Enterprise, side by side.
No credit card · Self-host in minutes
Run in production by the teams shipping AI at scale.
Testimonial
Testimonial
Testimonial“LiteLLM gives NVIDIA engineers a single, consistent way to access more than 100 AI model endpoints.”
Testimonial
Testimonial“LiteLLM streamlines the complexities of managing multiple LLM models.”
Testimonial
Testimonial“LiteLLM has let my team provide the latest LLM models to our users, usually within a day of them being released… it has saved us months of work.”
Testimonial
Testimonial“If we decide to switch the backend model, it’s a simple configuration update in the gateway; no code changes, procurement cycles, or repetitive security reviews required.”
Testimonial
Testimonial“After the company began using router provider LiteLLM, the costs of some advanced AI tasks such as coding fell by as much as 56%.”
01
Pass-through Endpoints
Cost Tracking
Logging
End-user Tracking
Using LiteLLM Virtual Keys/Authentication
Logging
LLM Observability Tools (Langfuse, Langsmith, etc.)
Datadog Logging
S3 Logging
GCS Logging
Azure Data Lake
Key/Team-based Logging
Alerting/Monitoring
Slack/Discord/Teams/Email/Webhook
Pagerduty Alerting
Prometheus Metrics
Authentication
Virtual Keys
Custom Auth
OIDC/JWT Auth
Virtual Key Rotation
Write Key to Secret Manager
CRUD Endpoints + UI
Create / Manage Users
Create / Manage Teams
Create / Manage Orgs
Assign Team Admins
Assign Org Admins
Control Model Access
Restrict Models by Key/User/Team
Model Access Groups
Team-only Models
Admin UI
Internal User Self-serve
SSO
Auto-add SSO User to Teams
Spend Tracking
Track Spend by Model/Key/User/Team
Track Spend for Org
Track Spend for Custom Tags
API endpoints for Spend Reporting
Budgets + Rate Limits
Set Budgets by Key/User/Team
Set Rate Limits by Key/User/Team
Temporary Budget Increase
Budget/Rate Limit Tiers
Guardrails
Set Guardrails per request
Default-on Guardrails
Set Guardrails by Key/Team
