PriceIndex
NV

Nemotron 3.5 Super VL Pricing & API Specs

nemotron-3.5-super-vl
APIProvider site

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... Built by NVIDIA.

Prices updated

Input price

$0.15

per 1M tokens · Standard

Output price

$0.50

per 1M tokens · Standard

Input limit

1M

tokens

Output limit

944K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF
Compare

Nemotron 3.5 Super VL price history

4 price records since 10/18/2026 · 2 changes

Nemotron 3.5 Super VL cost calculator

Input20M tokens
Output5M tokens

$5.50/month

Standard pricing

    Overview

    What is Nemotron 3.5 Super VL?

    Nemotron 3.5 Super VL is a text & reasoning and vision model from NVIDIA priced at $0.15 input and $0.50 output per 1M tokens, with a 1M context window. Its low input price suits high-volume work; no AA Intelligence score has been published yet.

    Price: DeepSeek V4.1 Flash 1017 (+$0.000)Price: Qwen3.8 Flash (−$0.008)Price: Qwen3.8 Omni Flash (−$0.008)

    Benchmarks

    Nemotron 3.5 Super VL benchmarks & speed

    How Nemotron 3.5 Super VL scores on standardized evaluations, and where it lands among every model we track.

    1151

    DesignArena Elo

    Better than 30% of 95 models

    Latency & design

    DesignArena win rate
    33.2%
    Design battles judged
    4,061

    Independent scores from Artificial Analysis and DesignArena · updated 10/30/2026. Higher is better; ranks compare against every model we track with that score.

    Rates

    Nemotron 3.5 Super VL pricing

    Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

    Input · Standard

    $0.15

    Per 1M tokens

    Cached input · Standard

    $0.08

    Per 1M tokens

    Capabilities

    Nemotron 3.5 Super VL Tools

    Tools available when using Nemotron 3.5 Super VL through supported provider APIs.

    JSON mode

    Supported

    Reasoning

    Supported

    Where to run it

    Nemotron 3.5 Super VL API providers

    10 providers serve Nemotron 3.5 Super VL. Prices are per 1M tokens; uptime is the last 24 hours.

    Darkbloomnvfp4
    Input
    $0.06
    Output
    $0.35
    Cached
    $0.01
    Context
    262K
    Uptime
    83.72%
    Crusoebf16
    Input
    $0.10
    Output
    $0.40
    Cached
    $0.08
    Context
    1M
    Uptime
    93.26%
    PrimeIntellectnvfp4
    Input
    $0.15
    Output
    $0.50
    Cached
    $0.02
    Context
    1M
    Uptime
    100%
    Io Netnvfp4
    Input
    $0.15
    Output
    $0.50
    Cached
    $0.02
    Context
    262K
    Uptime
    100%
    Together
    Input
    $0.15
    Output
    $0.50
    Cached
    $0.02
    Context
    262K
    Uptime
    99.93%
    DeepInfrafp4
    Input
    $0.15
    Output
    $0.50
    Cached
    $0.02
    Context
    262K
    Uptime
    100%
    CoreWeavenvfp4
    Input
    $0.15
    Output
    $0.50
    Cached
    $0.02
    Context
    1M
    Uptime
    100%
    Venicefp4
    Input
    $0.20
    Output
    $0.50
    Cached
    $0.04
    Context
    262K
    Uptime
    97.47%
    BaseTenfp4
    Input
    $0.20
    Output
    $0.50
    Cached
    $0.04
    Context
    1M
    Uptime
    100%
    Nebiusbf16
    Input
    $0.30
    Output
    $0.90
    Cached
    $0.06
    Context
    1M
    Uptime
    99.51%

    Strengths and limitations

    Strengths

    • Price rank 74 of 330 tracked models (1 = cheapest, by blended price).
    • Blended price at 3 input : 1 output is $0.24 per 1M tokens.
    • 1M input + 250K output tokens costs about $0.28.
    • Context window 1M vs a median of 262K (4.0× larger).

    Limitations

    • Generated tokens cost 3× more than input tokens, which matters for verbose responses.
    • Large context capacity does not guarantee consistent retrieval across the entire prompt.
    • Benchmarks are directional; test accuracy, latency and reliability on your own workload before committing.

    Public listed prices, checked Nov 9, 2026. Benchmarks as published by their sources. Confirm with the provider.

    Same provider

    More models from NVIDIA

    View provider →
    131K

    $0.20 in · $0.20 out

    View model
    262K

    $0.07 in · $0.20 out

    View model
    262K

    $0.06 in · $0.24 out

    View model
    1M

    $0.07 in · $0.40 out

    View model

    Frequently asked questions about Nemotron 3.5 Super VL

    Nemotron 3.5 Super VL is a text & reasoning and vision model from NVIDIA. 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...

    Nemotron 3.5 Super VL costs $0.15 per million input tokens and $0.50 per million output tokens on standard pricing. A workload of 20M input and 5M output tokens a month is about $5.50.

    Nemotron 3.5 Super VL accepts up to 1,048,576 tokens (1M) of input and can return up to 943,718 tokens in one response.

    Yes, Nemotron 3.5 Super VL supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, Structured outputs, JSON mode, Reasoning, Log probabilities, Deterministic seed, Prompt caching.

    Nemotron 3.5 Super VL accepts Text, Image, Video as input and produces Text as output.

    Nemotron 3.5 Super VL is available from 10 API providers: Darkbloom, Crusoe, PrimeIntellect, Io Net, Together, DeepInfra, CoreWeave, Venice and more. Prices can differ by provider.

    Nemotron 3.5 Super VL was released by NVIDIA in 2026-10-15.