> ## Documentation Index
> Fetch the complete documentation index at: https://documentation.deepmask.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Nemotron 3 Super

> NVIDIA Nemotron 3 Super in DeepMask: an efficient text-only reasoning model with tool use and a 262K-token context window.

Nemotron 3 Super is NVIDIA's reasoning model in DeepMask. It is a Mixture-of-Experts model that activates only part of its network for each token, which keeps it efficient while it reasons through complex questions.

## About

Use Nemotron 3 Super for text-based reasoning, coding, and agentic tasks that call tools and connectors. It reads documents but not images.

## Specifications

| Specification | Value |
| - | - |
| Model provider | NVIDIA |
| Hosting | EU |
| Context window | 262K tokens |
| Max output | 131K tokens |
| Image input | No |
| Tool use | Yes |
| Reasoning | Built-in thinking |

[Try Nemotron 3 Super in DeepMask →](https://chat.deepmask.io/)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.