Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

LiteLLM

litellm.ai

  • Free plan
  • Web
  • API
  • Self-hosted
7.2 Club score Visit litellm.ai

What LiteLLM is

LiteLLM is an open-source AI gateway and LLM proxy for platform teams. It gives applications one OpenAI-compatible API for connecting with more than 140 providers and over 1,800 models. Routing features include load balancing, lowest-cost selection, and automatically sending simple prompts to cheaper models. Teams can track usage and spending by key, user, team, organization, tool, agent, and MCP, then apply hard budgets and rate limits. Response and semantic caching can use Redis, S3, or GCS. LiteLLM runs through a self-hosted deployment, including air-gapped environments, with an official Helm chart or Terraform module. The maker describes self-hosting as keeping data inside your infrastructure without telemetry. Security controls include hardened non-root images, vulnerability scanning, SSO, JWT, RBAC, and secrets-manager integrations. The free Open Source plan is self-hosted and includes 100+ providers, virtual keys, spend tracking, budgets, rate limits, fallbacks, request and response logging, and Prometheus metrics. Enterprise adds SSO and SCIM, audit logs, key rotation, administrative controls, onboarding, and dedicated support.

Who it suits

LiteLLM suits platform teams that need one API across many AI providers and models. It also fits organizations that need routing, spend controls, self-hosted deployment, or air-gapped operation.

Good to know, and what to watch

  • OpenAI-compatible access to 140+ providers and 1,800+ models
  • Load balancing and lowest-cost routing
  • Hard budgets and rate limits
  • Self-hosted operation, including air-gapped environments
  • Response and semantic caching
  • Virtual keys and usage analytics
  • The Open Source plan is self-hosted
  • Enterprise is billed annually
  • Enterprise support and onboarding require the Enterprise plan

Enterprise

—

Open Source

Free

Free plan · 30-day trial

Getting started

  1. Open the LiteLLM website
  2. Choose the Open Source or Enterprise plan
  3. Deploy the gateway with the official Helm chart or Terraform module
  4. Run it in your infrastructure, including an air-gapped environment
  5. Use the OpenAI-compatible API for connected providers and models

Limits to check

The free Open Source plan is self-hosted and includes access to 100+ providers, virtual keys, spend tracking, budgets, rate limits, fallbacks, request and response logging, and Prometheus metrics. Enterprise capabilities such as SSO, SCIM, audit logs, key rotation, and dedicated support are on the Enterprise plan.

The verdict

Choose LiteLLM if your team needs a central gateway for multiple model providers with routing, accounting, and budget controls. Its self-hosted design suits infrastructure that must keep data within its own environment. Teams needing Enterprise administration and support should select that annual plan.

Questions people ask

Is LiteLLM free?

Yes. The Open Source plan costs nothing and is billed free forever for self-hosted use. A 30-day trial is also offered.

Which platforms does LiteLLM support?

LiteLLM is available through an API, self-hosted deployment, and web access.

How many providers and models can it connect?

The gateway offers one OpenAI-compatible API for 140+ providers and 1,800+ models. The Open Source plan lists 100+ providers.

Does LiteLLM support fallback routing and budgets?

Yes. It supports LLM fallbacks, hard budgets, rate limits, and routing options including load balancing and lowest-cost selection.

What does Enterprise add?

Enterprise includes SSO and SCIM, OIDC/JWT authentication, audit logs, secret managers, key rotation, organization and team administrators, onboarding, dedicated support, and listed 24/7 support with SLAs.

What the maker publishes

Caching
Response and semantic caching can use Redis, S3, or GCS. source
Data handling
LiteLLM says its self-hosted deployment has no telemetry and keeps data within the user's infrastructure. source
Deployment
The gateway can be self-hosted, including in air-gapped environments, and supports deployment with an official Helm chart or Terraform module. source
Enterprise access
The Enterprise plan includes SSO and SCIM, OIDC/JWT authentication, audit logs, secret managers, key rotation, and organization and team administrators. source
Integrations
The integrations documentation lists observability tools including Langfuse, Datadog, Grafana Cloud, OpenTelemetry, LangSmith, Arize/Phoenix, and Helicone. source
Intended users
The Enterprise plan is described for teams running LiteLLM in production, including high-volume and regulated deployments. source
Product
LiteLLM is an open-source AI gateway and LLM proxy for platform teams. source
Routing
LiteLLM supports load balancing, lowest-cost routing, and automatic routing of simple prompts to cheaper models. source
Security
The product page describes signed hardened non-root images, vulnerability scanning, SSO/JWT/RBAC controls, and secrets-manager integrations. source
Spend controls
It tracks usage and spend by key, user, team, organization, tool, agent, and MCP, and supports hard budgets and rate limits. source
Support
Enterprise includes dedicated support and onboarding, with 24/7 support and SLAs listed on the pricing page. source
Trial
The pricing FAQ offers an instant 30-day Enterprise trial key without a credit card. source
Unified access
The gateway provides one OpenAI-compatible API to 140+ providers and 1,800+ models. source

Checked against the maker's pages on 2 Oct 2026.