NVIDIA: Nemotron 3 Ultra (free)
nvidia/nemotron-3-ultra-550b-a55b:free
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...
Prompt $/1M
free
Completion $/1M
free
Context
1,000,000 tok
Best provider
13 tok/s · Nvidia
Specs
- Model id
- nvidia/nemotron-3-ultra-550b-a55b:free
- Display name
- NVIDIA: Nemotron 3 Ultra (free)
- Modality
- text->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 1,000,000
- Max completion
- 65,536
- Prompt $/1M
- free
- Completion $/1M
- free
- Free tier
- yes
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Nvidiafastest | 13 |
| nvidiafastest | — |