Skip to content
ShilpBot
AI Models

NVIDIA Nemotron 3.5 Super VL (Free): Specs, Limits and How to Use It

NVIDIA Nemotron 3.5 Super VL free: open multimodal mixture-of-experts model, text/image/video input, 1M context. Specs, limits, test prompts and how to...

By ShilpBot Team · Published · 3 min read

Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA with 12 billion active parameters out of 120 billion in total. The listing says it takes text, images, documents, GUI screenshots and video.

GUI screenshots are the interesting part. Models that can read an interface can describe what is on screen, which is the first step towards agents that operate software. It also accepts video, which few free models do.

Specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

NVIDIA Nemotron 3.5 Super VL quick facts

DetailValue
DeveloperNVIDIA
Model IDnvidia/nemotron-3.5-super-vl:free
Added to the catalogue2026-10-15
TypeOpen multimodal mixture-of-experts model
Parameters12B active / 120B total
Context windowabout 1M tokens (1,000,000)
Maximum output131,072 tokens
Input typestext, image, video
PriceFree (paid listing: $0.15 in / $0.50 out per 1M tokens)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Reasoning: supported, effort not adjustable.

What NVIDIA Nemotron 3.5 Super VL is good for

  • Describing and troubleshooting user interfaces from screenshots.
  • Extracting information from documents and forms supplied as images.
  • Summarising short video clips, since video input is listed.

Limits of NVIDIA Nemotron 3.5 Super VL

  • Video and image inputs use many tokens. Check how your tool counts them before sending large files.
  • Do not upload screenshots that contain personal data, tokens or customer information to a free endpoint.
  • Visual models can misread small text. Verify extracted numbers against the source.

How NVIDIA Nemotron 3.5 Super VL compares

  • NVIDIA Nemotron 3 Nano Omni: It has a larger context window (1,000,000 against 256,000 tokens); its output cap is 131,072 tokens against 65,536; it does not accept audio input; it activates 12B parameters per token against 3B.
  • Google Gemma 4 31B: It has a larger context window (1,000,000 against 262,144 tokens); its output cap is 131,072 tokens against 32,768; it activates 12B parameters per token against 30.7B.
  • inclusionAI Ling 3.2 Flash: It has a smaller context window (1,000,000 against 1,048,576 tokens); its output cap is 131,072 tokens against 262,144; it also accepts video input.

Calling NVIDIA Nemotron 3.5 Super VL from code

Use the model ID nvidia/nemotron-3.5-super-vl:free with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nvidia/nemotron-3.5-super-vl:free", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what NVIDIA Nemotron 3.5 Super VL can do

  1. Upload a screenshot of a settings page and ask it to list every toggle and its current state.
  2. Upload a photographed invoice and ask for line items as a table, then check the total yourself.
  3. Give it a short screen recording and ask it to write the steps shown as a numbered how-to.

What NVIDIA Nemotron 3.5 Super VL costs

The free listing costs nothing, but the same model also has a paid listing at about $0.15 per million input tokens and $0.50 per million output tokens. As a rough guide, sending 1 million input tokens and receiving 100,000 output tokens would cost about $0.20 on the paid listing. Use the free tier to test, and move to the paid route if you need steadier availability. Free pricing is set by the provider and can change at any time, so check the model page before you plan around it.

Keep reading

All free models are compared in our free AI chat models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

Does Nemotron 3.5 Super VL support video?

Yes. The catalogue lists text, image and video input, and the description also mentions documents and GUI screenshots.

Is NVIDIA Nemotron 3.5 Super VL free, and what are its limits?

As of 2026-11-16 the catalogue lists it at zero price. About 1M tokens (1,000,000) context window, up to 131,072 output tokens, model ID nvidia/nemotron-3.5-super-vl:free. Free use can be rate limited and providers may change it.

#NVIDIA Nemotron 3.5 Super VL#NVIDIA free model#free AI model#AI chat model#multimodal model#Kilo Gateway#OpenRouter