NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b

Cheaper than 88% of paidReasoningToolsJSON

Use via OpenRouter ↗

Intelligence

—

Design Elo

—

Speed

—

tokens/sec

Latency

—

first token

Input price

$0.085

39th cheapest

Context

16K max out

How it compares

Cheaper than88%

of all ranked models

Overview

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...

Providers & pricing (3)

Provider	In $/M	Out $/M	Context	Uptime
DeepInfrabf16	$0.085	$0.400	262K	88.4%
DigitalOcean	$0.210	$0.455	1M	98%
Nebiusfp4	$0.300	$0.900	262K	100%

Specifications

Context window1M

Max output16K

Knowledge cutoff—

Input modalitiestext

Output modalitiestext

Prompt caching—

Cache read price—

ModeratedNo

Open weightsnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 ↗

Nemotron 3 Super FAQ

How much does Nemotron 3 Super cost?

Nemotron 3 Super costs $0.085 per million input tokens and $0.400 per million output tokens via OpenRouter, making it 39th cheapest of 332 paid models.