LiteLLM
ActiveAI gateway that puts 100+ LLM providers behind one OpenAI-compatible API with keys and budgets.
- ★ 61.8k
- ⟳ Oct 22, 2026
- Open core
- min 4 GB RAM
- from €19.99/mo
LLM gateway & observability
Route, meter, budget and trace LLM calls across providers.
Quick answer
We track 2 self-hostable llm gateway & observability apps: LiteLLM, Langfuse. Most GitHub stars: LiteLLM (61.8k). Lowest official hardware: LiteLLM (minimum 1 vCPU · 4 GB RAM), from about €19.99/month on our reference server.
Last updated
LLM gateway & observability: side-by-side
| App | License | Official hardware | Est. server cost | GitHub stars | Status |
|---|---|---|---|---|---|
| LiteLLM | MIT (core) + LiteLLM Enterprise License (enterprise directory) (Open core) | minimum 1 vCPU · 4 GB RAM | from €19.99/mo | 61.8k | Active |
| Langfuse | MIT (core) + Langfuse Enterprise License (ee directories) (Open core) | recommended 4 vCPU · 16 GB RAM · 100 GB disk (no separate minimum published) | from €69.99/mo | 36.2k | Active |
All llm gateway & observability apps
Langfuse
ActiveLLM observability with tracing, prompt management, evaluations and cost tracking.
- ★ 36.2k
- ⟳ Oct 22, 2026
- Open core
- rec. 16 GB RAM
- from €69.99/mo