Tool · Run a model

Self-host vs API — at what volume does renting a GPU win?

Open-weight models can run on rented GPUs (~$1–$4/hr for an A100 / H100) or via per-token APIs. Plug in your numbers; we'll show the breakeven curve.

Monthly input tokens

30,000,000

@ 1,000,000/day

Monthly output tokens

15,000,000

@ 500,000/day

Self-host GPU

Nvidia GH200

needs 82 GB VRAM

Self-host monthly

$1,648

24/7 on cheapest provider

Self-host on Nvidia GH200

Cheapest fitting GPU for Qwen2.5 32B at FP16. Live at Lambda Labs at $2.29/hr → $1,648/month at 24/7 utilisation.