Skip to main content
NVIDIAOct 16, 2026

NVIDIA Nemotron 3.5 Super VL 120B

nvidia-nemotron-3-5-super-vl-120b-a12bPrivateOpen weights

NVIDIA Nemotron 3.5 Super VL is an open multimodal vision-language model for specialized agents. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, combining reasoning, instruction following, and tool use for long-running agentic workflows.

$0.20/$0.50
per 1M in / out
256K
context window
100K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 38%81.8%
Blended pricecheaper than 85%$0.28
Context windowlarger than 32%256K
Max outputlarger than 54%100K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InTextImageVideo
OutText
Streamingstream: true
Function callingtoolsStructured outputsresponse_formatReasoningAlways onVisionUp to 10 images
Video inputUp to 1 videos
Web searchenable_web_search
Prompt cachingReads at $0.04
Optimized for codeTuned for software work

Not supportedaudio input, X search and log probabilities

Benchmarks

GPQA Diamond
81.8%82nd of 139 · 6 score higher for less, including GPT-6 Luna, DeepSeek V4 Flash 0423 and Google Gemma 4 31B Instruct

Specs

Model ID
nvidia-nemotron-3-5-super-vl-120b-a12b
Endpoint
POST /api/v1/chat/completions
Context window
262,144 tokens
Max output
102,400 tokens
Reasoning
Always on
Precision
FP4
Privacy
Private
Added
Oct 16, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
NVIDIA Nemotron 3.5 Super VL 120B$0.20$0.5081.8%256K100K——
GLM 5.3 Flash Uncensored$0.165$0.5585.4%1M128K——
GLM 5.3 Flash E2EE$0.16$0.54—1M32K——
MiniMax M3.1 Flash$0.1875$0.7576.8%1M128K——
GLM 5.3 Flash$0.15$0.5075.1%1M128K——

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$0.20per 1M tokens
Cached input$0.0480% off input
Output$0.50per 1M tokens

Estimate a workload

$0.0006per request
$6.50for 10,000 requests

Blended price against similar models

NVIDIA Nemotron 3.5 Super VL 120B$0.275

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia-nemotron-3-5-super-vl-120b-a12b",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelnvidia-nemotron-3-5-super-vl-120b-a12bRequired
messagestext · image_url · video_urlContent parts the model reads
max_completion_tokensUp to 102,400Counts reasoning tokens
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations