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 2 Instruct (1.5B)
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 4070 Ti Super
needs 13 GB VRAM
Self-host monthly
$42
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
$0.02 $0.02 $0.9 −$41.29 Open →

Self-host on Nvidia RTX 4070 Ti Super

Cheapest fitting GPU for Qwen 2 Instruct (1.5B) at FP16. Live at Vast.ai at $0.059/hr → $42/month at 24/7 utilisation.

Related tools