# litelm

> Updated 2026-09-12 · type: tool · category: ai-infrastructure · status: active · rev 1

litelm strips LiteLLM to its core: routing, translation, streaming and tool use for 19 providers in ~2,900 lines with two dependencies.

- Open source: yes (MIT)
- Self-hostable: yes
- Pricing model: free
- Best for: Builders whose agent stack needs multi-provider routing but not LiteLLM's full surface area, and who count dependencies as risk.
- Last verified: 2026-09-12

- **Canonical:** https://gtmstacker.com/registry/tool/litelm/
- **Source:** [github · kennethwolters/litelm](https://github.com/kennethwolters/litelm)
- **Tags:** ai-infrastructure, llm-routing, python, minimal, self-hostable
- **Repository:** https://github.com/kennethwolters/litelm

## Is litelm open source?

Yes, litelm is open source under the MIT license.

## How much does litelm cost?

litelm is free to use.

## Can I self-host litelm?

Yes, litelm can be self-hosted (the source is available under the MIT license).


---

Open-source Python library (MIT, 182★) that extracts the core of LiteLLM — model routing, message translation, streaming, tool use and embeddings across 19 providers — into ~2,900 lines with two dependencies (openai, httpx), keeping API compatibility with LiteLLM for drop-in migration.

## Provenance

- MIT independently WebFetch-verified 2026-09-12 (182★, 69 commits, September 2026 upstream-compatibility audit). Surfaced via the 2026-09-12 daily pull.
- Curated from the GTM Stacker signal registry (2026-09-12 pass: daily pull + viral-posts brief); license independently WebFetch-verified 2026-09-12.

## Why it matters for a GTM stack

Model routing sits under every multi-model agent workflow (including the cheap-worker routing pattern this registry cataloged with Spotify's shunt). A minimal, readable router is the version of that layer a lean team can audit after a supply-chain scare, and this year supplied several.