Private AI
Nvidia's Nemotron 3 Nano Omni 30B-A3B reasoning model. It accepts multimodal context on supported providers and returns text responses for perception and agentic workflows.
Added Apr 28, 2026
Model weightsContext Window
256.0K
Max Output
65.5K
Input Price (Auto)
$0.11/1M
Output Price (Auto)
$0.44/1M
Cache Read (Auto)
$0.055/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
14.9
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
46.9%
Better than 23% of models compared
HLE
Humanity's Last Exam
5.3%
Better than 39% of models compared
IFBench
Instruction-following benchmark
63.2%
Better than 74% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
45.3%
Better than 49% of models compared
AA-LCR
Long context reasoning evaluation
35.7%
Better than 48% of models compared
SciCode
Python programming for scientific computing
27.8%
Better than 37% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
8.3%
Last updated Jul 15, 2026
Artificial AnalysisBetter than 42% of models compared
