by Thinking Machines

Inkling FP4.

text open weights datacenter 952B params 524K ctx
Cheapest input
$1.0/M
on Together AI
Cheapest output
$4.05/M
on Together AI
Smallest GPU
8× Nvidia A100 SXM4
$5.73/hr
API pricing

What it costs per month across providers.

Estimate your monthly bill for Inkling FP4 across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.

Cheapest
$18.1
Together AI
$/M input
$1.0
per million tokens
$/M output
$4.05
per million tokens
Providers
2
with priced rows
100,000 1,000,000,000
100,000 500,000,000
Monthly bill

Cheapest provider on the left.

Total monthly cost — input + output tokens combined.

Loading...
Per provider

Bill breakdown.

Provider Monthly total
$18.1 Sign up ↗
$18.1 Sign up ↗
Self-host alternative

Rent the GPU instead of paying per token.

Full breakdown →

For an open-weights model like Inkling FP4, 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
$4,180.86
8× Nvidia A100 SXM4 @ $5.73/hr
Self-host total
$4,180.86
per month
API beats self-host
+$4,162.76
API is cheaper here

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 →