modelbenchmark.io

NVIDIA Nemotron Cascade 2

NVIDIA · nemotron-cascade-2-30b-a3b

Compare

Nemotron model for efficient reasoning, coding, and specialized AI agents

Specification

most-agreed values

Context
262K
Max output
131K
Released
2025-12-01
Knowledge cutoff
2024-07
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$0.60

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
vultr$0.15$0.60262K131K

More from NVIDIA

most-hosted first