modelbenchmark.io

NVIDIA Nemotron 3 Super 120B (Public Preview)

nvidia-nemotron-3-super-120b

Compare

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

Specification

most-agreed values

Context
1M
Max output
33K
Released
2026-03-11
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.30
Output
$0.65
Cache read
$0.06

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
digitalocean$0.30$0.65$0.061M33K