AI TOOLS RADAR
All models / NVIDIA
nvidia logo
nvidia

NVIDIA: Nemotron 3.5 Super VL

Source description (English)

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

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,048,576 tokens
Maximum output
235,929 tokens
Architecture
text+image+video->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.15
per 1M tokens
Output
$0.5
per 1M tokens
Cache read
$0.02
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
No
Default parameters
No
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body 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","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimagevideo
Output
text
Reasoning

No

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

5 providers

Checked: October 20, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Crusoe

bf16
Context
262K
Maximum output
236K
Input
$0.1
Output
$0.4
Cache read
$0.08
Cache write
Not provided

Together

Not provided
Context
262K
Maximum output
236K
Input
$0.15
Output
$0.5
Cache read
$0.02
Cache write
Not provided

DeepInfra

fp4
Context
262K
Maximum output
236K
Input
$0.15
Output
$0.5
Cache read
$0.02
Cache write
Not provided

CoreWeave

nvfp4
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.5
Cache read
$0.02
Cache write
Not provided

Venice

fp4
Context
262K
Maximum output
33K
Input
$0.25
Output
$1.25
Cache read
$0.125
Cache write
Not provided
nvidia

4 models

All models
nvidia logonvidia

NVIDIA: Nemotron 3.5 Embed 1B (free)

Nemotron 3.5 Embed 1B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be...

Context
33K
Input
text · image
Output
embeddings
Input: Freeper 1M tokens
View model details →
nvidia logonvidia

NVIDIA: Nemotron 3.5 Embed 8B (free)

Nemotron 3.5 Embed 8B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be...

Context
33K
Input
text · image
Output
embeddings
Input: Freeper 1M tokens
View model details →
nvidia logonvidia

NVIDIA: Nemotron 3.5 Rerank 8B (free)

Input: text, image · Output: rerank

Context
33K
Input
text · image
Output
rerank
Input: Free per 1M tokensOutput: Free per 1M tokens
View model details →
nvidia logonvidia

NVIDIA: Nemotron 3.5 Super VL (free)

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

Context
1M
Input
text · image · video
Output
text
Input: FreeOutput: Freeper 1M tokens
View model details →