modelbenchmark.io

Nemotron 3 Nano 30B A3B

NVIDIA · nvidia-nemotron-3-nano-30b-a3b-bf16

Compare

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Specification

most-agreed values

Context
66K
Max output
66K
Released
2025-12-15
Knowledge cutoff
2025-06-25
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.195
Output
$0.495
Cache read
$0.039

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
thinkingmachines$0.195$0.495$0.039—66K66K—

More from NVIDIA

most-hosted first