Skip to content
NVIDIA

Nemotron 3.5 Super VL

Nemotron 3.5 Super VL is a large language model made by NVIDIA, added to the catalog on 15 Oct 2026. It has a context window of 1,048,576 tokens and costs $0.15 per 1M input tokens and $0.47 per 1M output tokens. It accepts text, images and video and produces text. Typical uses: summarising long documents, answering questions about images and working with video content.

Price checked ยท source: OpenRouter

What Nemotron 3.5 Super VL is

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA. It has 12B active parameters out of 120B total. It accepts text, images, and video. Its description also lists documents and GUI screenshots among the material it handles. It produces text. The listed capabilities include reasoning, tool support, structured outputs, and response-format settings.

The context window is 1,048,576 tokens, and the maximum output is 235,929 tokens. These limits provide room to submit large amounts of context and request extended text output. They can be relevant when a task involves lengthy documents, multiple pieces of visual material, or a combination of text, images, and video. The model's text output can present written responses to those inputs; its listed output modality is text rather than image or video. The facts do not specify a particular input resolution, video length, or document format, so those details should not be inferred from the modality list.

For applications that use tools, the model has tool support; structured outputs and response-format settings are also listed. These options suit workflows that need tool-enabled interaction or a response organized in a defined format. The stated reasoning support makes it relevant to tasks that involve working through text or visual context before producing a written answer. Overall, Nemotron 3.5 Super VL suits multimodal, text-producing tasks where a large context window is useful.

Key features

  • Accepts text, images, and video; its description also lists documents and GUI screenshots.
  • Produces text and supports reasoning.
  • Supports tools, structured outputs, and response-format settings.
  • Has a context window of 1,048,576 tokens.
  • Can produce up to 235,929 output tokens.

Typical uses

  • Summarising long documents
  • Answering questions about images
  • Working with video content
  • Interpreting GUI screenshots
  • Generating structured text responses

Nemotron 3.5 Super VL pricing

US dollars, list price through OpenRouter.

Checked
Nemotron 3.5 Super VL price list, by variant
ItemStandardFree
Input, per 1M tokens$0.15$0
Output, per 1M tokens$0.47$0
Cached input read, per 1M tokens$0.02n/a
Variants of Nemotron 3.5 Super VL that share this page
VariantModel id
Freenvidia/nemotron-3.5-super-vl:free

A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.

The price last changed on 21 Nov 2026. One price change has been recorded since Nemotron 3.5 Super VL was added.

Nemotron 3.5 Super VL price history, newest first, in US dollars per 1M tokens
DateInput /1MOutput /1M
$0.15$0.47
$0.15$0.50
What typical tasks cost with Nemotron 3.5 Super VL
What a task costsCost
Answer a short question500 in / 300 out$0.0002
Summarise a 50-page PDF25,000 in / 800 out$0.0041
Review a 2,000-line source file30,000 in / 2,000 out$0.0054
Read a 300-page contract set150,000 in / 1,500 out$0.023
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

Nemotron 3.5 Super VL specifications

Nemotron 3.5 Super VL limits and identity
Model idnvidia/nemotron-3.5-super-vl
Versionnemotron-3.5-super-vl-20261015
Context window1,048,576 tokensAbout 786,432 English words
Max output943,718 tokens
Knowledge cutoffNot published
Added to catalog15 Oct 2026
Nemotron 3.5 Super VL capabilities
Input typestext, image, video
Output typestext
Tool callingYes
Structured outputsYes
Reasoning effort controlNo
Content moderationNot applied by provider

Sample outputs

The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.

No output has been recorded for Nemotron 3.5 Super VL yet.

Compare Nemotron 3.5 Super VL

Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.

Nemotron 3.5 Super VL questions

How much does Nemotron 3.5 Super VL cost?

Nemotron 3.5 Super VL costs $0.15 per 1M input tokens and $0.47 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.0041.

What is the context window of Nemotron 3.5 Super VL?

1,048,576 tokens, or roughly 786,432 English words. It can write up to 943,718 tokens in one response.

Can Nemotron 3.5 Super VL read images and PDFs?

It accepts text, images and video as input. It produces text, so it cannot generate images.

How do I try Nemotron 3.5 Super VL?

Use the "Try Nemotron 3.5 Super VL" button on this page. It opens the chat with Nemotron 3.5 Super VL selected; you type the question and press send.

Try Nemotron 3.5 Super VL on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.