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 4090D
needs 22 GB VRAM
Self-host monthly
$172
24/7 on cheapest provider
API pricing — cheapest first
Monthly bill at 30,000,000 input + 15,000,000 output tokens.
Self-host on Nvidia RTX 4090D
Cheapest fitting GPU for Mistral: Ministral 3 8B 2512 at FP16. Live at io.net at $0.24/hr → $172/month at 24/7 utilisation.