RentGPU RentGPU
Trouver un GPU →
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.

Nvidia Nemotron Nano 9B V2
10,000 100,000,000
10,000 100,000,000
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 24 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.

Provider $/M in $/M out Monthly vs self-host
DeepInfra
$0.04 $0.16 $3.6 −$169.2 Open →
Together AI
$0.06 $0.25 $5.55 −$167.25 Open →

Self-host on Nvidia RTX 4090D

Cheapest fitting GPU for Nvidia Nemotron Nano 9B V2 at FP16. Live at io.net at $0.24/hr → $172/month at 24/7 utilisation.

Related tools