RentGPU RentGPU
Find a 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.

Mistral Nemo 12B
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 PRO 4500 SE
needs 32 GB VRAM
Self-host monthly
$360
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
$0.019 $0.03 $1.02 −$358.98 Open →
Mistral La Plateforme
$0.02 $0.03 $1.05 −$358.95 Open →

Self-host on Nvidia RTX PRO 4500 SE

Cheapest fitting GPU for Mistral Nemo 12B at FP16. Live at RunPod at $0.5/hr → $360/month at 24/7 utilisation.

Related tools