Loaded Tokens. The latest AI news in five minutes or less.Get the briefing

vLLM

An Apache-licensed server for open-weight models.

Verdict
Use The public docs say it does what you need. We read the docs. We did not test it.
Maker
vLLM
Price / access
Free under Apache 2.0. You pay for the GPUs. Pricing source
Pricing checked
November 7, 2026
Primary source
docs.vllm.ai

We built this profile from public sources and didn't use the product ourselves. The price is what we saw on the day we checked, so it may have changed.

Who it’s for

Teams that need an API in front of weights they already have.

Why we said Use

What it is

An Apache-licensed server for open-weight models. See the official page. This profile describes public documentation, not a Loaded Tokens hands-on test.

Who it is for

Teams that need an API in front of weights they already have. The recommendation is scoped to that job.

The evidence behind Use

The license is Apache 2.0. Capacity, drivers, and the model card are the real project. The source page is the receipt. No speed ranking or reliability score is implied.

Pricing and the catch

Free under Apache 2.0. You pay for the GPUs. Public pricing or license checked November 7, 2026. Amounts are as stated on that page. Tax, region, annual billing, and extra usage can change the bill.

A sensible first workflow

Serve one model on hardware you control and point one internal client at it. This is a suggested evaluation, not a test we ran.

Bottom line: Use it to serve weights. It does not pick the model for you.

Sources

Updates that matter in five minutes or less.

Free, Tuesdays & Fridays. The latest AI news in five minutes or less.

A twice-a-week note, if you want it.