Model specification · NVIDIA
Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
SpecificationsReported values
- Context window
- 1M
- Maximum output
- 16K
- Architecture
- text->text
- Tokenizer
- Other
- Knowledge cutoff
- —
- Moderated
- No
- Input modalities
- text
- Output modalities
- text
Full pricingUSD where reported
| Price | Standard | free |
|---|---|---|
| Input | $0.085 / M | free / M |
| Output | $0.400 / M | free / M |
Benchmark indexesReported indexes
- Intelligence
- 25.4
- Coding
- 37.7
- Agentic
- 8.7
- Design Arena Elo
- —
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.00125 |
| Long analysis | 100K / 4K × 1 | 50% | $0.010 |
| Workday | 20K / 2K × 1,000 | 30% | $2.50 |
More from NVIDIAAll NVIDIA models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| Nemotron 3 Ultra | 512K | $0.600 | $3.60 | 37.8 |
| Nemotron 3 Nano 30B A3B | 262K | $0.050 | $0.200 | 14.2 |