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.

Qwen: Qwen3.8 27B
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 H100 NVL
needs 74 GB VRAM
Self-host monthly
$675
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
$0.2 $2.5 $43.5 −$631.5 Open →
OpenRouter
$0.214 $2.55 $44.67 −$630.33 Open →

Self-host on Nvidia H100 NVL

Cheapest fitting GPU for Qwen: Qwen3.8 27B at FP16. Live at Clore.ai at $0.938/hr → $675/month at 24/7 utilisation.

Related tools