Nemotron 3 Super 120B A12B
Nemotron 3 Super 120B A12B is NVIDIA's language model, available from 2 providers. A 120B-parameter hybrid Mamba-Transformer MoE model activating 12B parameters, from NVIDIA's Nemotron 3 Super series for compute-efficient complex reasoning.
NVIDIA's language model, available from 2 providers. A 120B-parameter hybrid Mamba-Transformer MoE model activating 12B parameters, from NVIDIA's Nemotron 3 Super series for compute-efficient complex reasoning.36.0#38 |
31.2#44 |
0.8#41 |
0.2#23 |
0.7#13 |
1.02s#236 |
0.4#87 |
0.6#32 |
0.3#40 |
0.7#63 |
160.8#34 |
Capabilities
Input1/5
β
Β·
Β·
Β·
Β·
Output1/5
β
Β·
Β·
Β·
Β·
Capabilities0/13
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Pricing by Provider
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
 OpenRouter | $0.100 | $0.500 | $0.100 |
 Vercel AI Gateway | $0.150 | $0.650 | N/A |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Nemotron 3 Super 120B A12B | β | β | β | β | Current |
| Nemotron 3 Super | β | β | β | β | Available |
| Nemotron 3 Super 120B | β | β | β | β | Available |
| Llama Nemotron Super 49B v1.5 | β | β | β | β | Available |
| Nemotron 1.5 Super 49B | β | β | β | β | Available |
| Llama 3.3 Nemotron Super 49B v1 | β | β | β | β | Available |
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Nemotron 4 15B | β | β | β | β | β |
| Nemotron Super 3 120B | β | 256K | $0.150 | $0.650 | |
| Nemotron Super 3 120B A12B | β | 262K | $0.090 | $0.450 | |
| Nemotron Nano 3 30B | β | 262K | $0.060 | $0.240 | |
| Nemotron 3 Nano 30B A3B | β | 262K | $0.050 | $0.200 | |
| Nemotron 3 | β | β | β | β | β |
| Nemotron 2 Nano 12B VL | Nano | 131K | β | β | |
| Nemotron Cascade 2 30B A3B | β | β | β | β | β |
| ProteinMPNN 1.0 2 | β | β | β | β | β |
| Nemotron 3 Nano 30B | Nano | 262K | β | β |