Nemotron 3 Super
NVIDIA · 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...
Nemotron 3 Super ranks #202 of 377 models in the default AI Benchmark Hub order (quality first, then cost). At $1.35 blended per million tokens, it is cheaper than 45% of models with published API pricing. Its 1,048,576-token context window is 4.0× the catalog median (262,144 tokens).
Context
Max output: 262144
Pricing
Output / 1M: 2.40
Blend / 1M: 1.35
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $1.35per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $1.35 |
| 10,000,000 | $13.50 |
| 100,000,000 | $135.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from NVIDIA
- Nemotron 3 Nano Omni$0.00 / 1M
- Nemotron 3.5 Lightning$0.14 / 1M
- Nemotron 3 Nano 30B A3B$0.15 / 1M
- Nemotron 3.5 Content Safety$0.20 / 1M
- Nemotron 3.5 Super VL$0.33 / 1M
Closest API price
- R1 0528$1.33 / 1M
- MiniMax M1$1.38 / 1M
- o4 Mini (batch)$1.38 / 1M
- o3 Mini (batch)$1.38 / 1M
- Moondream 3 Preview$1.40 / 1M