Model specification · NVIDIA
Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
SpecificationsReported values
- Context window
- 512K
- Maximum output
- —
- Architecture
- text->text
- Tokenizer
- Other
- Knowledge cutoff
- —
- Moderated
- No
- Input modalities
- text
- Output modalities
- text
Full pricingUSD where reported
| Price | Standard | free |
|---|---|---|
| Input | $0.600 / M | free / M |
| Output | $3.60 / M | free / M |
Benchmark indexesReported indexes
- Intelligence
- 37.8
- Coding
- 49.3
- Agentic
- 27.4
- Design Arena Elo
- 1153
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.00960 |
| Long analysis | 100K / 4K × 1 | 50% | $0.054 |
| Workday | 20K / 2K × 1,000 | 30% | $16.80 |
More from NVIDIAAll NVIDIA models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| Nemotron 3 Super | 1M | $0.085 | $0.400 | 25.4 |
| Nemotron 3 Nano 30B A3B | 262K | $0.050 | $0.200 | 14.2 |