modelbenchmark.io

nemotron-3-super

NVIDIA · nemotron-3-super

Compare

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

Specification

most-agreed values

Context
262K
Max output
66K
Released
2026-03-11
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.015
Output
$0.60
Cache read
$0.015

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
ollama-cloud$0.015$0.60$0.015262K66K

More from NVIDIA

most-hosted first