Tool overview
LiteLLM is listed under AI Infrastructure & MLOps AI tools.
What is LiteLLM?
LiteLLM provides an OpenAI-compatible Python SDK and self-hosted proxy for routing across more than 100 model providers, controlling spend, enforcing budgets, applying guardrails, and adding reliability and observability.
Best for
Organizations standardizing access to many model providers
Who is it for?
Decision note
Rebuilt from the original export under the complete V412/V411 factual-source-verification workflow. Preview only. Apply remains blocked until Failures = 0, Warnings = 0, Unmapped = 0, Missing = 0; explicit clears are reviewed; image import is disabled; a representative WordPress edit screen is compared with the export and proposed row; and a post-Apply zero-change Preview succeeds.
Key features
OpenAI-compatible gateway and Python SDK
Routing, fallbacks, load balancing, and caching
Virtual keys, budgets, rate limits, and spend tracking
Guardrails, observability, SSO, audit, and air-gap options
Use cases
Unify access to many model providers
Build an internal AI gateway
Control budgets and rate limits
Add reliability and governance to model traffic
Pros
- Open-source gateway is free for production
- MIT licensed core
- Self-hosted and air-gapped deployment
Limitations
Enterprise pricing depends on annual request capacity, architecture, and support needs.
Proxy configuration, secrets, and logs require production security controls.
Pricing details
Billing options
Pricing note
The open-source gateway is free forever. Enterprise is priced by annual request capacity, deployment architecture, and support needs. A no-card 30-day Enterprise trial key is available.
Supported languages
- English
Integrations
140+ model providers
Langfuse
Arize Phoenix
LangSmith
OpenTelemetry
Presidio
Lakera
Secret managers
Please log in to join the discussion.