Enterprise DNAEnterprise DNA

Open Source

LiteLLM

by BerriAI

A Python SDK and a self-hosted proxy, the LiteLLM AI Gateway, that let apps call more than 100 model providers through one OpenAI-format API, with virtual keys, budgets, fallbacks and spend tracking.

Our verdict

Source reviewedReviewed 22 Oct 2026 by Enterprise DNA editorial

A Python SDK and a self-hosted proxy, the LiteLLM AI Gateway, that let apps call more than 100 model providers through one OpenAI-format API, with virtual keys, budgets, fallbacks and spend tracking.

Best for: Platform teams running a shared gateway for several apps that need per-team keys, budgets and spend logs across providers.

Choose something else if: you cannot pin versions, patch quickly and rotate keys. LiteLLM's release pipeline was compromised twice in 2026, in March and October.

Source review

Using LiteLLM in practice

Where it runs

Self-hosted with Docker, Helm or Terraform. Prompts go only to the providers you configure, and telemetry is off by default when self-hosted.

How to install

For a quick test, install the proxy with uv and start it on one model. For a shared gateway, use the Docker Compose quickstart with Postgres, set a master key and pin an explicit version. Clients call http://localhost:4000.

Install commands

uv tool install 'litellm[proxy]'
litellm --model gpt-4o

As published in the linked sources. Not run by us.

What it costs

The open-source gateway is free to self-host. You pay your model providers directly, plus your own hosting. Enterprise adds governance and support, priced through sales on annual gateway capacity and never per token.

Prices and plans change. Check the linked sources before committing.

Why consider it

  • Very wide provider coverage behind one OpenAI-format API, from Python or over HTTP.
  • The open-source proxy includes virtual keys, budgets, rate limits, fallbacks, logging callbacks and an admin UI.

What to watch for

  • On 21 October 2026 a compromised release, 1.107.0 on PyPI and the Docker latest and main-stable tags, carried credential-stealing malware for a few hours. LiteLLM says to pin 1.106.2 or an earlier explicit version.
  • Budgets and virtual keys need a Postgres database.
  • Single sign-on beyond five users, audit logs and several guardrails need a paid Enterprise licence.

A first task to try

Start it locally with one provider key, send one request to http://localhost:4000, then find that request in the spend log.

Suggested exercise, not an installation test. We reviewed the linked documentation; no host compatibility is implied.

Other options to understand

Related tools can solve different parts of the same job. Compare fit before treating them as replacements.

Key facts

What we have checked

Latest prerelease version
1.111.0-dev.3
Checked GitHub
Days since the last commit
0
Checked GitHub
GitHub forks
13,265
Checked GitHub
GitHub stars
63,230
Checked GitHub
Days to a first reply on issues
0
Checked GitHub
Open issues
1,500
Checked GitHub
Releases in the last 90 days
100
Checked GitHub

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

Stars and usage

How LiteLLM is growing

GitHub stars

48,950 to 63,230

stars. 12 July 2026 to 13 Nov 2026, 5 readings.

Source: GitHub. Checked .

Health and security

Is LiteLLM looked after, and what do its setup files show

Health score

100 out of 100

Does someone look after this repository? It does not say the code is good or safe. Worked out from GitHub signals checked . How it is worked out

PartPointsWhat we saw
Recent activity30 of 30Last push 0 days ago
Releases15 of 15100 releases in 90 days
Issue replies20 of 20First reply in 0 days (median)
Maintainer15 of 15Owned by an organisation
Official sourceNot countedMCP servers only

Alternatives

Alternatives to LiteLLM

RecordTypeHow we knowChecked
AI GatewayAlternative to thisOpen sourceNamed in the listingNot dated
AI studioAlternative to thisOpen sourceNamed in the listingNot dated
BifrostAlternative to thisOpen sourceNamed in the listingNot dated
BitRouterAlternative to thisOpen sourceNamed in the listingNot dated
Continuum-AI-Corp/orcarouter-mcp-serverAlternative to thisMCP serverNamed in the listingNot dated
Correctover/mcp-serverAlternative to thisMCP serverNamed in the listingNot dated
EntrolyAlternative to thisOpen sourceNamed in the listingNot dated
GlideAlternative to thisOpen sourceNamed in the listingNot dated
GoModelAlternative to thisOpen sourceNamed in the listingNot dated
HypersigilAlternative to thisOpen sourceNamed in the listingNot dated
JamesANZ/cross-llm-mcpAlternative to thisMCP serverNamed in the listingNot dated
ManifestAlternative to thisAppNamed in the listingNot dated
Maxim AIAlternative to thisOpen sourceNamed in the listingNot dated
MirascopeAlternative to thisOpen sourceNamed in the listingNot dated
Modelz-LLMAlternative to thisOpen sourceNamed in the listingNot dated
OpenRouterAlternative to thisAppNamed in the listingNot dated
RelayAlternative to thisOpen sourceNamed in the listingNot dated
ReliableGPT 💪Alternative to thisOpen sourceNamed in the listingNot dated
sachinuppal/modelcostsaverAlternative to thisMCP serverNamed in the listingNot dated
smigolsmigol/llmkitAlternative to thisMCP serverNamed in the listingNot dated
spanlens/SpanlensAlternative to thisMCP serverNamed in the listingNot dated
TeamoRouterAlternative to thisOpen sourceNamed in the listingNot dated
TokenMixAlternative to thisOpen sourceNamed in the listingNot dated
TrueFoundryAlternative to thisOpen sourceNamed in the listingNot dated
Vercel AI GatewayAlternative to thisOpen sourceNamed in the listingNot dated
XiuRouterAlternative to thisOpen sourceNamed in the listingNot dated
ypollak2/llm-routerAlternative to thisMCP serverNamed in the listingNot dated
FastChatThis is an alternative to itOpen sourceNamed in the listingNot dated

Compare

Compare LiteLLM side by side

Sources

Where this comes from

  • GitHubOfficial

    Checked · Latest prerelease version

  • GitHubRegistry

    Checked · Days since the last commit, GitHub forks, GitHub stars, Days to a first reply on issues, Open issues, Releases in the last 90 days

  • Checked · Source review

  • Checked · Source review

  • PricingOur review

    Checked · Source review

  • Checked · Source review

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Released 1.111.0-dev.3

    Source: GitHub

  2. Released 1.111.0-dev.4

    Source: GitHub

  3. Released 1.110.0-rc.3

    Source: GitHub

  4. Released 1.107.0-rc.4

    Source: GitHub

  5. Released 1.108.9

    Source: GitHub

  6. Released 1.106.10

    Source: GitHub

  7. Released 1.108.8

    Source: GitHub

  8. Released 1.111.0-dev.2

    Source: GitHub

  9. Released 1.111.0-dev.1

    Source: GitHub

  10. Released 1.108.7

    Source: GitHub

  11. Released 1.110.0-rc.2

    Source: GitHub

  12. Released 1.109.1

    Source: GitHub

  13. Released 1.108.6

    Source: GitHub

  14. Released 1.106.9

    Source: GitHub

  15. Released 1.106.8

    Source: GitHub

  16. Released 1.109.0

    Source: GitHub

  17. Released 1.110.0-rc.1

    Source: GitHub

  18. Released 1.108.5

    Source: GitHub

  19. Released 1.104.9

    Source: GitHub

  20. Released 1.103.11

    Source: GitHub

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.