/ Models

Language models

NVIDIA: Nemotron 3 Super (free)

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...

Maker
Nvidia
Context window
262K
Max output
262K
Input / 1M
free
Output / 1M
free
1M in + 1M out
free

Everything else

Max output262K
Input / 1Mfree
Output / 1Mfree
Cache read / 1M
Cache write / 1M
1M in + 1M outfree
Takestext
Returnstext
Toolsyes
Reasoningoptional · medium, low
Open weightsyes
Released2026-03-11
Knowledge cutoff
Retires
Catalog idnvidia/nemotron-3-super-120b-a12b:free

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models