AI models

vLLM

High-throughput model serving for GPUs.

open source self-hostable vLLM project · ?

The production engine for serving open models on your own GPUs.

Website ↗ Source ↗ Plan “AI models” with it

How you can run it

Way	Where the data lives	Price basis	Verdict
Host it myself	your own server or hardware	free	green — You run it yourself: no data leaves your own infrastructure.

Facts

Company / project	vLLM project (jurisdiction unknown)
Licence	Apache-2.0
Self-hosting footprint	8192 MB RAM · 4 vCPU · 50 GB — needs a GPU server
Commonly replaces	OpenAI API
Provenance	curated, verified 2026-09-04

Machine-readable: /api/tools/vllm.json. Something wrong? Tell us.