RentGPU RentGPU
GPU finden →
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.

Ornith-1.0-35B
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 6000 MaxQ
needs 96 GB VRAM
Self-host monthly
$913
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
$0.1 $0.75 $14.25 −$899.36 Open →

Self-host on Nvidia RTX PRO 6000 MaxQ

Cheapest fitting GPU for Ornith-1.0-35B at FP16. Live at Vast.ai at $1.269/hr → $913/month at 24/7 utilisation.

Related tools