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 5000 Ada

needs 32 GB VRAM

Self-host monthly

$316

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	$0.06	$0.06	$2.7	−$314.1	Open →
DeepInfra	$0.4	$0.4	$18.0	−$298.8	Open →

Cheapest fitting GPU for MythoMax 13B at FP16. Live at TensorDock at $0.44/hr → $316/month at 24/7 utilisation.