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...
Prompt $/1M
$0.080
Completion $/1M
$0.450
Context
1,000,000 tok
Best provider
154 tok/s · Nebius
Specs
- Model id
- nvidia/nemotron-3-super-120b-a12b
- Display name
- NVIDIA: Nemotron 3 Super
- Modality
- text->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 1,000,000
- Max completion
- —
- Prompt $/1M
- $0.080
- Completion $/1M
- $0.450
- Free tier
- no
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 |
|---|---|
| Nebiusfastest | 154 |
| DeepInfra | 46 |
| DigitalOcean | 38 |
| DekaLLM | 35 |