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.

Sao10K: Llama 3.1 Euryale 70B v2.2
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
AMD AMD MI300X
needs 180 GB VRAM
Self-host monthly
$1,404
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
$0.85 $0.85 $38.25 −$1,365.75 Open →

Self-host on AMD AMD MI300X

Cheapest fitting GPU for Sao10K: Llama 3.1 Euryale 70B v2.2 at FP16. Live at TensorWave at $1.95/hr → $1,404/month at 24/7 utilisation.

Related tools