AI model · NVIDIA
Nemotron 3 Super (free)
Model ID: nvidia/nemotron-3-super-120b-a12b:free
- Input
- Free per 1M tokens
- Output
- Free per 1M tokens
- Context
- 262K tokens at once
- Max output
- 236K tokens per reply
- Released
- 11 Mar 2026 NVIDIA
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- YesFree to use
Takes text; gives text.
How its listing describes it
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...
Sources
- NVIDIA: Nemotron 3 Super (free) on OpenRouter — read 2 Oct 2026