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.
Monthly input tokens
30,000,000
@ 1,000,000/day
Monthly output tokens
15,000,000
@ 500,000/day
Self-host GPU
—
needs 542 GB VRAM
Self-host monthly
—
24/7 on cheapest provider
API pricing — cheapest first
Monthly bill at 30,000,000 input + 15,000,000 output tokens.
No single GPU fits
This model doesn't fit on any single rentable GPU at FP16. Drop to a lower precision (INT4 / INT8) or split across multiple GPUs.