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

AMD MI300

needs 179 GB VRAM

Self-host monthly

—

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	$0.4	$0.4	$18.0	—	Open →
Groq	$0.59	$0.79	$29.55	—	Open →
Together AI	$0.88	$0.88	$39.6	—	Open →

Cheapest fitting GPU for Llama 3.1 70B at FP16.