PioneerNemotron 3 Super 120B A12B model ID, context window & pricing
nemotron
Quick facts
Model ID nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
Source Pioneer
Context Window 1000000
Pricing $0.09 input / $0.45 output per 1M tokens
Capabilities tool calling, reasoning, temperature control, open weights
Model overview
Nemotron 3 Super 120B A12B is an AI model from Pioneer with 1000000 token context window and text input support.
Published pricing is $0.09 input and $0.45 output per 1M tokens.
- Workloads that use text inputs with text outputs.
- Agent and tool workflows that need function calling.
- Reasoning-heavy prompts where stepwise problem solving matters.
Model ID nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
Provider Pioneer
Family nemotron
Status -
Knowledge Cutoff -
Release Date 2026-03-11
Input Modalities text
Output Modalities text
Context Window 1000000
Input Limit -
Output Limit 32000
Tool Calling Yes
Reasoning Yes
Structured Output -
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.09
Output Cost / 1M tokens $0.45
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.09
Cache Write Cost / 1M tokens $0.09