Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Developer Tools
  4. /
  5. LiteLLM Proxy
Developer Tools
LiteLLM Proxy icon

LiteLLM Proxy

by BerriAI

LiteLLM is an open-source, self-hosted AI gateway that puts many model providers behind one OpenAI-compatible API. It adds virtual keys, spend tracking, routing and an admin UI.

API·Freemium

Visit litellm.ai(opens in a new tab)

About LiteLLM Proxy

Key features of LiteLLM Proxy

  • One OpenAI-compatible API in front of 140+ providers
  • Virtual keys with per-key budgets, rate limits and model access
  • Spend tracking by key, team and user
  • Routing with retries, fallbacks and load balancing
  • Admin UI for models, keys, teams, logs and audit logs
  • SSO and team scoping
  • Guardrails and access to MCP servers and agents through the same gateway
  • Python SDK with the same unified interface

Who LiteLLM Proxy is for

  • Platform teams managing LLM access for an organization
  • Developers who want one API across providers
  • Teams that need to cap and attribute LLM spend
  • Organizations that must self-host their AI traffic

How to use LiteLLM Proxy

  1. 1

    Step 1: Start the gateway with the quickstart script or the Docker Compose file; it runs on port 4000 with a Postgres database.

  2. 2

    Step 2: Log in to the Admin UI with the master key you generated.

  3. 3

    Step 3: Add a model by choosing a provider and pasting its API key, then test the connection.

  4. 4

    Step 4: Create a virtual key with the budget and limits you want.

  5. 5

    Step 5: Point any OpenAI SDK at the gateway URL using the virtual key and send requests.

  6. 6

    Step 6: Watch spend and request logs in the Admin UI.

LiteLLM Proxy FAQ

Is LiteLLM Proxy open source?

Yes. The site describes it as open source and self-hosted, and you can run it with a single command or Docker.

Does my data go to LiteLLM when I self-host?

The docs state that no data or telemetry is stored on LiteLLM servers when you self-host. Usage telemetry is off by default.

Do I need to change my application code to use it?

Any client that works with the OpenAI API works with the gateway by changing the base URL and key.

Does it support SSO and audit logs?

The site lists SSO login scoped by team, project or app, and the docs mention audit logs.

Details

Pricing
FreemiumOpen source and self-hosted. The site points to a sales contact for enterprise needs; no plan prices are listed on the pages.
Type
API
Platforms
  • API
  • CLI
Categories
Developer ToolsAI
Added
Sep 17, 2026
BerriAI iconPublisherBerriAI

Built from public sources

We put this page together from LiteLLM Proxy’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with LiteLLM Proxy.

Work at LiteLLM Proxy? Claim the listing to manage it yourself.

Something wrong here?

Related tools

See more
TwelveLabs iconTwelveLabsTwelveLabs · Usage-basedVideo understanding API for searching, analyzing, embedding and generating insights from video content.Developer Tools · Usage-basedDeepInfra iconDeepInfraDeepInfra · Usage-basedServerless inference platform providing API access to open language, embedding, image and speech models.Developer Tools · Usage-basedAllora Network iconAllora NetworkAllora · Contact for pricingAllora is a decentralized network where machine learning models compete to produce predictions, which the network combines into one aggregated inference. Developers can query it over REST or SDKs.Developer Tools · Contact for pricing