whichllm — Browse and compare AI model specs and pricing

Nebius Token Factory

Nemotron-3-Super-120B-A12B

models.dev synced record

Model ID nvidia/nemotron-3-super-120b-a12b
Provider Nebius Token Factory
Family -
Status -
Knowledge Cutoff 2026-02
Release Date 2026-03-11
Input Modalities text
Output Modalities text
Context Window 256000
Input Limit 256000
Output Limit 32768
Tool Calling Yes
Reasoning Yes
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.30
Output Cost / 1M tokens $0.90
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -