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.

granite-4.2-8b
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 Tesla M40 24GB
needs 23 GB VRAM
Self-host monthly
$77
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
$0.06 $0.25 $5.55 −$71.85 Open →
OpenRouter
$0.06 $0.25 $5.55 −$71.85 Open →

Self-host on Nvidia Tesla M40 24GB

Cheapest fitting GPU for granite-4.2-8b at FP16. Live at Clore.ai at $0.108/hr → $77/month at 24/7 utilisation.

Related tools