by Meta AI

Llama 4 Scout (17Bx16E).

text open weights datacenter 109B params 262K ctx
Smallest GPU
2× Nvidia Q RTX 8000
$0.54/hr
API pricing

What it costs per month across providers.

Estimate your monthly bill for Llama 4 Scout (17Bx16E) across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.

100,000 1,000,000,000
100,000 500,000,000

No priced API access rows on file for Llama 4 Scout (17Bx16E) yet.

Self-host alternative

Rent the GPU instead of paying per token.

Full breakdown →

For an open-weights model like Llama 4 Scout (17Bx16E), you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month. Power is included in a rental's hourly price.

GPU rental
$394.78
2× Nvidia Q RTX 8000 @ $0.54/hr
Self-host total
$394.78
per month
Quantisation
INT4
picked for lowest VRAM

Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.

Full calculator
Want to compare token volumes across other models too? Open the standalone API pricing tool →