modelbenchmark.io

Nemotron 3 Super 120B

NVIDIA · nemotron-3-120b-a12b

Compare

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

Specification

most-agreed values

Context
256K
Max output
256K
Released
2026-03-11
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.50
Output
$1.50

Rate limits

Requests per minute
300

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
cloudflare$0.50$1.50256K256K
cloudflare-workers-ai · cf$0.50$1.50256K256K

More from NVIDIA

most-hosted first