Enterprise DNAEnterprise DNA
LModelsLong context
NVIDIA logo

Nemotron 3 Super

by NVIDIA

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. B

N3

Models

Nemotron 3 Super

Added 10 July 2026

#nvidia

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...

How to use / API access

Call via OpenRouter with model id `nvidia/nemotron-3-super-120b-a12b`.

  • openrouter · nvidia/nemotron-3-super-120b-a12b Docs

OpenRouter id: nvidia/nemotron-3-super-120b-a12b

Benchmarks

  • Intelligence Index (artificial-analysis): 12.8 index
  • Coding Index (artificial-analysis): 37.7 index
  • Agentic Index (artificial-analysis): 1.7 index

Notes

Nemotron 3 Super is listed in the EDNA Models directory from the OpenRouter catalogue.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

USAGE / OPENROUTER

How much Nemotron 3 Super is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
525B ▼26.6%
Requests, last 7 days
15.3M
Tool calls, last 7 days
6.3M
Intelligence score
12.8
Average cost per request
0.8¢
Price per million tokens
$0.3 in · $2.4 out
0100B200B19 Sept: 47.2B tokens, 1.7M requests20 Sept: 49.3B tokens, 1.7M requests21 Sept: 44.6B tokens, 1.6M requests22 Sept: 47.1B tokens, 1.7M requests23 Sept: 49.7B tokens, 1.7M requests24 Sept: 48.7B tokens, 1.8M requests25 Sept: 40.6B tokens, 1.5M requests26 Sept: 51.2B tokens, 1.7M requests27 Sept: 51.7B tokens, 1.8M requests28 Sept: 48B tokens, 1.8M requests29 Sept: 49.1B tokens, 1.8M requests30 Sept: 51.2B tokens, 1.9M requests1 Oct: 58.2B tokens, 1.8M requests2 Oct: 59.5B tokens, 2M requests3 Oct: 62.3B tokens, 2.2M requests4 Oct: 63.4B tokens, 2M requests5 Oct: 81.6B tokens, 2.4M requests6 Oct: 99.2B tokens, 2.7M requests7 Oct: 96.4B tokens, 2.6M requests8 Oct: 96.2B tokens, 2.7M requests9 Oct: 99.9B tokens, 2.7M requests10 Oct: 80.2B tokens, 2.4M requests11 Oct: 83.5B tokens, 2.4M requests12 Oct: 89.5B tokens, 2.5M requests13 Oct: 97.5B tokens, 2.7M requests14 Oct: 168B tokens, 3.6M requests15 Oct: 136B tokens, 3.2M requests16 Oct: 107B tokens, 3.2M requests17 Oct: 95.7B tokens, 2.8M requests18 Oct: 80.2B tokens, 2.4M requests19 Oct: 75.6B tokens, 2.4M requests20 Oct: 28.5B tokens, 1.1M requests21 Oct: 2.2B tokens, 240K requests19 Sept3 Oct17 Oct21 OctSee where it ranks on the leaderboard →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Check the source

Price date: 2026-10-18. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 12.8 (2026-10-18) ↗Coding Index: 37.7 (2026-10-18) ↗Agentic Index: 1.7 (2026-10-18) ↗
Compare this model with alternatives →