Nemotron 3 Nano Omni
Open multimodal model for unified video, audio, image, and text reasoning.
NVIDIA's open multimodal model that unifies video, audio, image, and text understanding for enterprise-grade reasoning, transcription, document intelligence, and GUI automation workflows.
Pricing
Model profile · Current snapshot
Input / 1M
$0.20
Output / 1M
$0.60
Blended / 1M
$0.30
Output TPS
154
TTFT (s)
0.7
Model Intelligence
Context window
256,000 tokens
Arena ranking
10
Benchmarkable
Yes
Model level
release
Intelligence Index
10.1
Coding Index
5.9
Math Index
26.7
MMLU Pro
0.65
GPQA
0.44
HLE
0.05
LiveCodeBench
0.35
SciCode
0.18
AIME 2025
0.27
IFBench
0.26
LCR
0.17
TerminalBench Hard
0
TAU2
0.19
Recent stories
0 linked stories
No linked stories yet.