NVIDIA: Nemotron 3 Super

Other

Text

Paid

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. Built on a hybrid Mamba-Transformer...

Parameters

Context Window

1,000,000

tokens

Input Price

$0.085

per 1M tokens

Output Price

$0.4

per 1M tokens

Capabilities

Model capabilities and supported modalities

Performance

Reasoning

Math

Coding

Knowledge

Modalities

Input Modalities

text

Output Modalities

text

LLM Price Calculator

Calculate the cost of using this model

Input Tokens (0.00000008/token)$0.000127

Output Tokens (0.00000040/token)$0.001200

Common Scenarios:

Input Cost:$0.000127

Output Cost:$0.001200

Total Cost:$0.001327

Estimated usage: 4,500 tokens

Monthly Cost Estimator

Based on different usage levels

Light Usage

$0.0049

~10 requests

Moderate Usage

$0.0485

~100 requests

Heavy Usage

$0.4850

~1000 requests

Enterprise

$4.8500

~10,000 requests

Note: Estimates based on current token count settings per request.

Last Updated: 2026/08/15