← model directory

nvidia

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b

↓ runs free on your own hardware

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...

specs & pricing
Type
text
Provider
nvidia
Model ID
nvidia/nemotron-3-super-120b-a12b
Capabilities
tools, reasoning
Context window
1M tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.099 / 1M tokens
Output price
$0.50 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.