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 Quadro RTX 6000

needs 24 GB VRAM

Self-host monthly

$158

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
Zhipu BigModel	$0.4	$1.75	$38.25	−$120.15	Open →
DeepInfra	$0.4	$1.75	$38.25	−$120.15	Open →
Together AI	$0.45	$2.0	$43.5	−$114.9	Open →
OpenRouter	$0.6	$2.2	$51.0	−$107.4	Open →

Cheapest fitting GPU for GLM-4.7 at FP16. Live at Akash Network at $0.22/hr → $158/month at 24/7 utilisation.