gateway vs litellm
litellm is much bigger: 58.1k stars against 12.9k. Over the days we have tracked them gateway moved +3.2% and litellm +6.9%, so litellm is growing faster right now.
gateway leads on customization and setup ease. litellm does not take any axis by a clear margin.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
A tiny, high-performance LLM gateway that routes to 1,600+ models while providing built-in guardrails, retries, and load‑balancing.
- Stars
- 12.9k
- Tracked growth
- +3.2%
- Maturity
- ●●●●●
- Last commit
- 102d ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Uses your provider API keys; self-hosted or hosted enterprise plans.
A lightweight, production-ready self-hosted AI gateway that unifies 100+ LLM providers into a single OpenAI-compatible API with virtual keys, spend tracking, guardrails, and load balancing.
- Stars
- 58.1k
- Tracked growth
- +6.9%
- Maturity
- ●●●●●
- Last commit
- 12m ago
- Language
- Python
- License
- NOASSERTION
- Cost to run
- Self-hosted — your API keys (pay providers)
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | gateway | litellm |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Diff only | ●●●●● No repo context |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Guardrails & filters | ●●●●● Basic guardrails |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Custom rules & prompts | ●●●●● Configurable |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Self-hostable |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own keys | ●●●●● Bring-your-own-key |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command start | ●●●●● Config + API key |
Which one to pick
Pick gateway if…
Easy setup — Run a lightweight, self-hostable gateway in one command that centralizes routing, guardrails, and provider flexibility.
- Customization: Custom rules & prompts (5/5 against 3/5)
- Setup ease: One-command start (5/5 against 3/5)
Pick litellm if…
Unified multi-provider support — use one OpenAI-compatible API to call 100+ LLMs with a self-hosted gateway, virtual keys, and cost tracking.
What people want from each one
Portkey-AI/gateway
BerriAI/litellm
Questions people ask
Is gateway better than litellm?
gateway leads on customization and setup ease. litellm does not take any axis by a clear margin. gateway is worth picking when easy setup — Run a lightweight, self-hostable gateway in one command that centralizes routing, guardrails, and provider flexibility.
Which of gateway and litellm keeps my code private?
gateway: Self-hostable (4/5). litellm: Self-hostable (4/5).
What does each one cost to run?
gateway: Uses your provider API keys; self-hosted or hosted enterprise plans.. litellm: Self-hosted — your API keys (pay providers).
Full profiles: Portkey-AI/gateway and BerriAI/litellm. Everything else in Gateways & routing.