whichllm — Browse and compare AI model specs and pricing

Weights & Biases

NVIDIA Nemotron 3 Super 120B

nemotron

Model ID nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
Provider Weights & Biases
Family nemotron
Status -
Knowledge Cutoff -
Release Date 2026-03-11
Input Modalities text
Output Modalities text
Context Window 262144
Input Limit -
Output Limit 262144
Tool Calling Yes
Reasoning No
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.20
Output Cost / 1M tokens $0.80
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -