Skip to content

NVIDIA · Chat

Nemotron 3.5 Super VL

NVIDIA 🇺🇸ChatOpen weights. One of its sources says the weights are publicly available.
From Aiml API's listing:
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots and video as input and answers in text, with optional reasoning, tool calling and structured outputs.
llminfo IQ
125.9
Market median price
$0.2375 blended / 1M
Max context
1M
Listings
45

Evidence and sources

🤗 nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16llminfo IQ 125.9, ranked among chat models. From 18 benchmarks. A fair amount of data behind it.How llminfo IQ is computedGood value (60.2). Cheaper per task than its benchmark results predict. From 4 benchmarks with measured task costs. A fair amount of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTypical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate.Median 159,709 output tokens per task with reasoning off.How the Yap score worksMaker HQ: US (source)
All rankings: #11 on OpenRouter today #14 on OpenRouter this month #16 on OpenRouter this week #114 on NanoGPT recentlySources: DeepInfra data, IO Intelligence (io.net) data, Models.dev data, AI/ML API dataPrimary data from DeepInfra from IO Intelligence (io.net): name from Models.dev: weights availability from AI/ML API: primary mode, description
Tags from its sources:instructtoolsreasoningvision

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 9 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Images
Video
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt caching

Listings

 Aihubmixnemotron-3.5-super-vl-free · freeSource: AIHubMix data docsNot published by the provider$0.00$0.00——
 Flowdotnvidia/nemotron-3.5-super-vl:free · freeSource: FlowDot data1M$0.00$0.00——
 Kilonvidia/nemotron-3.5-super-vl:free · freeSources: Kilo AI Gateway data, Models.dev data1M$0.00$0.00——
 OpenRouterInference by NVIDIA NIMnvidia/nemotron-3.5-super-vl:free · freeSource: OpenRouter data docs869K$0.00$0.001151,118ms
 Opencodenemotron-3.5-super-vl-free · freeSource: OpenCode Zen dataNot published by the provider$0.00$0.00——
 NanoGPTInference by DarkbloomRegions: GLBnvidia/nemotron-3.5-super-vl · nvfp4Source: NanoGPTNot published by the provider$0.063cache read $0.0394$0.3675——
 Fastrouternvidia/nemotron-3.5-super-vlSource: FastRouter data262K$0.15cache read $0.02$0.50——
 Nous Portalnvidia/nemotron-3.5-super-vlSource: Nous Portal Inference Gateway data262K$0.15cache read $0.02$0.47——
 Wavespeednvidia/nemotron-3.5-super-vlSource: WaveSpeed AI data1M$0.15cache read $0.02$0.50——
 DeepInfranvidia/NVIDIA-Nemotron-3.5-Super-VL · fp4Sources: DeepInfra data, LiteLLM data262K$0.15cache read $0.02$0.50——
Show all 42 listings

Showing 10 of 42: the cheapest per 1M input tokens from each provider.

Also sold by Cheapest Token, Commandcode, Cortecs AI, Digitalocean, Ionet, Nebius AI Studio, Together AI, Vercel.

3 listings without a price are hidden.

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

Source: OpenRouter benchmark exports
15 Oct 2026 version · 90-day results
Across 11 providers lowest 62.7% median 72.6% highest 74.9%OpenRouter's automatic routing 72.9%
Show results from 11 providers and OpenRouter's automatic routingHide results from 11 providers and OpenRouter's automatic routing
  • DeepInfra
  • Nebius
  • Together
  • OpenRouter's automatic routing
  • PrimaLabs
  • CoreWeave
  • Darkbloom
  • Venice
  • Io Net
  • BaseTen
  • PrimeIntellect
  • Crusoe

Science

GPQA Diamond12 results
Source: OpenRouter benchmark exports
15 Oct 2026 version · 90-day results
Across 11 providers lowest 84.6% median 87.8% highest 91.7%OpenRouter's automatic routing 86.8%
Show results from 11 providers and OpenRouter's automatic routingHide results from 11 providers and OpenRouter's automatic routing
  • Io Net
  • PrimeIntellect
  • BaseTen
  • CoreWeave
  • PrimaLabs
  • DeepInfra
  • Nebius
  • Together
  • OpenRouter's automatic routing
  • Darkbloom
  • Venice
  • Crusoe

Human preference

Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Reasoning

Other

Data credits: Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)

Also known as: deepinfra/nvidia/nvidia-nemotron-3.5-super-vl, nebius/nvidia/nemotron-3.5-super-vl, nemotron-3.5-super-vl-free, nvidia-nemotron-3.5-super-vl, nvidia/nemotron-3.5-super-vl, nvidia/nemotron-3.5-super-vl:free, nvidia/nvidia-nemotron-3.5-super-vl, together_ai/nvidia/nvidia-nemotron-3.5-super-vl

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works