Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b
- context
- 262K
- modalities
- text → text
- capabilities
- Tool use, Reasoning, Structured output, Low cost
Overview
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...
Providers
- DeepInfraView DeepInfra
- DekaLLMView DekaLLM
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| DeepInfra | $0.085 | $0.40 |
| DekaLLM | $0.08 | $0.45 |
DeepInfra
- input / 1M
- $0.085
- output / 1M
- $0.40
DekaLLM
- input / 1M
- $0.08
- output / 1M
- $0.45
Use this model
through Nautili
Route requests to Nemotron 3 Super through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.