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 B300 SXM6 AC

needs 271 GB VRAM

Self-host monthly

$6,084

24/7 on cheapest provider

API pricing — cheapest first

Monthly bill at 30,000,000 input + 15,000,000 output tokens.

Provider	$/M in	$/M out	Monthly	vs self-host
OpenRouter	$0.13	$0.85	$16.65	−$6,067.35	Open →
Zhipu BigModel	$0.2	$0.8	$18.0	−$6,066.0	Open →
Zhipu BigModel	$0.2	$0.8	$18.0	−$6,066.0	Open →
z.ai	$0.2	$0.8	$18.0	−$6,066.0	Open →

Cheapest fitting GPU for GLM-4.5-Air at FP16. Live at Lium at $8.45/hr → $6,084/month at 24/7 utilisation.