NVIDIA: Nemotron 3 Super

120B / 12B

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.

Context
1.0M
Max output
262K
Input price
$0.3/1M tokens
Output price
$2.4/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDnvidia/nemotron-3-super-120b-a12b
Provider OpenRouter
Creator NVIDIA
Family—
License—
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters120B / 12B
Architecture—
Context window1.0M tokens
Max input—
Max output262K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.3
Output
$2.4
Cache write
—
Cache read
$0.15
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/nvidia/nemotron-3-super-120b-a12b