Model specification · NVIDIA

Nemotron 3 Nano 30B A3B

nvidia/nemotron-3-nano-30b-a3b

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

SpecificationsReported values
Context window
262K
Maximum output
236K
Architecture
text->text
Tokenizer
Other
Knowledge cutoff
—
Moderated
No
Input modalities
text
Output modalities
text
Full pricingUSD where reported
PriceStandard
Input$0.060 / M
Output$0.240 / M
Benchmark indexesReported indexes
Intelligence
8.9
Coding
14.4
Agentic
1
Design Arena Elo
—
Example workload costsStandard pricing only
WorkloadInput / outputCache shareEstimated cost
Quick check10K / 1K × 10%$0.00084
Long analysis100K / 4K × 150%$0.00696
Workday20K / 2K × 1,00030%$1.68
More from NVIDIAAll NVIDIA models
ModelContextInput / MOutput / MIntel.
Nemotron 3 Ultra262K$0.600$2.4023.4
Nemotron 3 Super262K$0.080$0.45013.6
Nemotron 3.5 Lightning262K$0.070$0.20013.6