NVIDIA Nemotron 3 Super 120B A12B (Reasoning) is a text-based AI model by NVIDIA. It features 365 tok/s output speed, $0.30/1M input tokens pricing. It scores 36.0 on the intelligence index.
Output Speed
365 tok/s
Latency (TTFT)
0.54s
Blended Price
$0.41/M
| Input (Prompt) | $0.30 |
| Output (Completion) | $0.75 |
| Cache Read | Free |
| Cache Write | Free |
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
NVIDIA Nemotron 3 Super 120B A12B (Reasoning) costs $0.30/1M input tokens and $0.75/1M output tokens.
NVIDIA Nemotron 3 Super 120B A12B (Reasoning) has a moderate coding score of 31.2. It can handle basic programming tasks but may not be the best for complex coding.
NVIDIA Nemotron 3 Super 120B A12B (Reasoning) generates output at 365 tok/s. Time to first token is 0.54s.
No, NVIDIA Nemotron 3 Super 120B A12B (Reasoning) is a paid model. Check the free models page for zero-cost alternatives.
Last updated:
See the alternatives section above for models with similar capabilities. You can also compare NVIDIA Nemotron 3 Super 120B A12B (Reasoning) head-to-head with any model on our comparison page.