Nemotron 3.5 Super VL pricing.

Prices checked

Nemotron 3.5 Super VL costs $0.15 in and $0.50 out per million tokens from OpenRouter; the cheapest price is $0.18 at Kilo Gateway, checked .

OpenRouter's own price

OpenRouter

$0.24/M tokens

$0.15 in · $0.50 out

73% below the typical price of the 399 text models we track.

Cheapest price

Kilo Gateway

$0.18/M tokens

$0.10 in · $0.40 out

26% less than OpenRouter, and the provider says why.

tool callingreads imagesreasoningstructured outputopen weights1M contextreleased 15 Oct 2026

Every provider selling Nemotron 3.5 Super VL

  1. 1

    NanoGPT

    Same as maker

    $0.15 in · $0.02 out · 262k context here

    $0.12/M tokens
  2. 2

    $0.10 in · $0.40 out · 262k context here

    $0.18/M tokens
  3. 3

    Crusoe

    Runs it themselves

    $0.10 in · $0.40 out · 262k context here

    $0.18/M tokens
  4. 4

    $0.10 in · $0.40 out

    $0.18/M tokens
  5. 5

    $0.11 in · $0.42 out · 262k context here

    $0.18/M tokens
  6. 6

    OpenRouter

    Same as maker

    $0.15 in · $0.50 out

    $0.24/M tokens
  7. 7

    Together AI

    Same as maker

    $0.15 in · $0.50 out · 262k context here

    $0.24/M tokens
  8. 8

    DeepInfra

    Same as maker

    $0.15 in · $0.50 out · 262k context here

    $0.24/M tokens
  9. 9

    CoreWeave

    Same as maker

    $0.15 in · $0.50 out

    $0.24/M tokens
  10. 10

    Eden AI

    Same as maker

    $0.15 in · $0.50 out · 262k context here

    $0.24/M tokens
  11. 11

    LLMTR

    Same as maker

    $0.15 in · $0.50 out · 262k context here

    $0.24/M tokens
  12. 12

    $0.20 in · $0.50 out

    $0.28/M tokens
  13. 13

    Baseten

    Costs more

    $0.20 in · $0.50 out

    $0.28/M tokens
  14. 14

    $0.18 in · $0.65 out · 262k context here

    $0.30/M tokens
  15. 15

    $0.30 in · $0.65 out

    $0.39/M tokens
  16. 16

    $0.30 in · $0.90 out

    $0.45/M tokens
  17. 17

    Venice

    Costs more

    $0.25 in · $1.25 out · 262k context here

    $0.50/M tokens
What it costs for your work
pages a month
$0.12

A month at OpenRouter's own price

$0.08

A month at Kilo Gateway, the cheapest

$0.04

What you save

A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.

How we count

Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below OpenRouter's own is listed as cheapest only when the provider says why. NVIDIA trained Nemotron 3.5 Super VL and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.

Same as maker
Sold by someone else at the price the maker charges.
Resells
The provider sells another company's endpoint, at a margin of its own or at the maker's price.
Runs it themselves
The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
Credits
Priced in credits or points that convert to dollars, so the rate moves when the conversion does.
Costs more
Sold by someone else for more than the maker charges.

Similar models

Models from other labs that do what Nemotron 3.5 Super VL does, cheapest first. Each percentage is against Nemotron 3.5 Super VL's cheapest price, $0.18 per M tokens.

Frequently asked

Who sells Nemotron 3.5 Super VL cheapest?
Kilo Gateway, at $0.10 in and $0.40 out per million tokens, checked 21 Oct 2026. The provider sells another company's endpoint, at a margin of its own or at the maker's price.
Is Nemotron 3.5 Super VL open weights?
Yes. NVIDIA publishes the weights, so anyone may host Nemotron 3.5 Super VL, which is why 17 providers sell it and why their prices differ so much.
How much context does Nemotron 3.5 Super VL hold?
1,048,576 tokens in one call, which is about 1M, and it can call your own functions.
How does Nemotron 3.5 Super VL compare with the rest of the market?
At $0.24 per million tokens, OpenRouter's own price is 73% below the typical $0.89 across the 399 text models we track.

More from NVIDIA