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 Nvidia GeForce RTX 4080

needs 14 GB VRAM

Self-host monthly

$91

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	$0.03	$0.15	$3.15	−$88.51	Open →
DeepInfra	$0.037	$0.17	$3.66	−$88.0	Open →
OpenAI API	$0.039	$0.18	$3.87	−$87.79	Open →
Together AI	$0.15	$0.6	$13.5	−$78.16	Open →

Cheapest fitting GPU for GPT-OSS 120B at FP16. Live at Nosana at $0.127/hr → $91/month at 24/7 utilisation.