MModel Price Map

← All models

Pioneer

Nemotron 3 Super 120B A12B

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8

Prices and limits

Input price per 1M tokens
$0.09
Output price per 1M tokens
$0.45
Cached input per 1M tokens
$0.09
Blended price per 1M (our estimate)
$0.18
Context window
256,000
Max output tokens
32,000
Accepts
Text
Produces
Text
Released
Mar 11, 2026
Last updated
Mar 11, 2026
Knowledge cutoff
—
Open weights
Yes
Confirm on the provider’s page ↗

Wrong price, or a provider that wants its listing corrected or removed? Email ceo@uniholix.com. We reply within 5 business days.

Price changes

Models whose price changed in the catalogue, newest first. We compare prices every day.

No price changes recorded yet. When a model’s price changes, it appears here.