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 RTX 4060 Ti

needs 14 GB VRAM

Self-host monthly

$36

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
OpenAI API	$0.039	$0.18	$3.87	−$32.85	Open →
OpenRouter	$0.039	$0.18	$3.87	−$32.85	Open →
DeepInfra	$0.039	$0.19	$4.02	−$32.7	Open →
Together AI	$0.15	$0.6	$13.5	−$23.22	Open →

Cheapest fitting GPU for GPT-OSS 120B at FP16. Live at Clore.ai at $0.051/hr → $36/month at 24/7 utilisation.