Nvidia Nemotron 3.5 Super VL

NVIDIA262K context

Open weightsVisionReasoningTool calling
Lowest · DeepInfra
$0.15 / $0.50
per 1M in / outPricing page

As of Nov 21, 2026, Nvidia Nemotron 3.5 Super VL costs $0.15 per million input tokens and $0.50 per million output tokens from Together AI. The cheapest of 3 providers is Together AI at $0.15 / $0.50. No price change since Appndo started tracking it on Oct 15, 2026. Recent price changes

Providers (3)

Sorted by your monthly estimate. Prices per million tokens.

  • Input / output
    $0.15 / $0.50
    Context
    262K
    Per month
    $2.50

    deepinfra/nvidia/NVIDIA-Nemotron-3.5-Super-VL

  • Input / output
    $0.15 / $0.50
    Context
    262K
    Per month
    $2.50

    together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL

  • Input / output
    $0.20 / $0.65
    Context
    262K
    Per month
    $3.30

    inferenceapis/nvidia/NVIDIA-Nemotron-3.5-Super-VL

Cloud and hosted providers may add regional pricing, minimums or platform fees. Supports: Vision, Reasoning, Tool calling.

Similar models

Common questions

How much does the Nvidia Nemotron 3.5 Super VL API cost?

As of Nov 21, 2026, Nvidia Nemotron 3.5 Super VL costs $0.15 per million input tokens and $0.50 per million output tokens from Together AI. Cached input costs $0.02 per million tokens.

Where is Nvidia Nemotron 3.5 Super VL cheapest?

As of Nov 21, 2026, the cheapest of 3 providers is Together AI at $0.15 per million input tokens and $0.50 per million output tokens. Appndo lists no official price from NVIDIA.

What is the context length of Nvidia Nemotron 3.5 Super VL?

Nvidia Nemotron 3.5 Super VL takes up to 262K tokens of context at Together AI.

How does Nvidia Nemotron 3.5 Super VL compare with similar models?

Nvidia Nemotron 3.5 Super VL has no LMArena score yet. Other NVIDIA models and their cheapest price per million input / output tokens: Nvidia Nemotron Nano 9B V2 ($0.04 / $0.16), Nvidia Nemotron 3 Ultra 550B A55B ($0.50 / $2.15), and Nemotron 3 Ultra 550B A55B ($0.80 / $2.60).

About this data

Prices come from LiteLLM's model cost map, with more providers from models.dev (both MIT licence), checked Nov 21, 2026; confirm on the provider's pricing page before you rely on a number.