nvidia
NVIDIA: Nemotron 3 Super
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...
Input Cost
$0.09
per 1M tokens
Output Cost
$0.45
per 1M tokens
Context Window
1,000,000
tokens
Developer ID: nvidia/nemotron-3-super-120b-a12b
Related Models
nvidia
Free/1M
NVIDIA: Nemotron Nano 12B 2 VL (free)
NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model design...
nvidia
Free/1M
NVIDIA: Nemotron 3 Nano 30B A3B (free)
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficien...
nvidia
$0.50/1M
NVIDIA: Nemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA,...