tensorix
nvidia/nemotron-3-super-120b-a12b
Nemotron 3 Super by NVIDIA, a hybrid Mamba-Transformer MoE model with 120B total and 12B active parameters. Features a 1M token context window, optimized for agentic reasoning, multi-step task planning and high-volume workloads.
Provider:
tensorix
Model type:
chat
Location:
europe
Context Window
1000000
Intelligence Rating
Speed Rating
Cost Efficiency Rating
Pricing
$
0.04
Input tokens per million
$
0.2
Output tokens per million
Features
Tool Calling
Supported
JSON Mode
Supported
Reasoning
Supported
