Nemotron 3.5 Super VL

NVIDIA

An open-weight multimodal mixture-of-experts model for specialized agents, visual reasoning, coding, and tool use.

Specs

Model

Family
Nemotron
Variant
3.5 Super VL
Parameters
120B total / 12B active (MoE)
Weights
Open

Limits

Context
1,048,576 tokens
Max output
8,192 tokens

Modalities

Input
Text Image Video
Output
Text

Pricing

Input
Free
Output
Free

Capabilities

Reasoning
Yes
Reasoning control
On / off
Tool calling
Yes
Attachments
Yes

Dates

Announced
15 Oct 2026
Released
15 Oct 2026

NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning

Always-on agents are taking on longer, more complex enterprise workflows. A single request can involve reading a document, checking information across sources, following company policy…

Michelle Horton
developer.nvidia.com

More from NVIDIA

All models

Nemotron 3.5 Lightning

NVIDIA

A customizable open 30B MoE model with 3B active parameters, providing optimal high-volume execution for autonomous agents.

OpenMDW-1.113w ago

Keep up with the tools

An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.