Nemotron 3 Super 120B A12B
by stepping stone AG · family nemotron · listed Mar 2026RTW
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
Current rates USD per 1M tokens
Input$2.38
Output$5.95
Cache read$0.357
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B- Context window
- 131K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Jun 2025
- Released
- 2026-03-11
- Last updated
- 2026-03-11
← All stepping stone AG listings