Nemotron 3 Ultra pricing.

Prices checked

Nemotron 3 Ultra costs $0.60 in and $2.40 out per million tokens from OpenRouter; the cheapest price is $0.74 at Kilo Gateway, checked .

OpenRouter's own price

OpenRouter

$1.05/M tokens

$0.60 in · $2.40 out

19% above the typical price of the 392 text models we track.

Cheapest price

Kilo Gateway

$0.74/M tokens

$0.40 in · $1.76 out

30% less than OpenRouter, and the provider says why.

tool callingreasoningstructured outputopen weights262k contextreleased 4 Jun 2026

Every provider selling Nemotron 3 Ultra

  1. 1

    $0.40 in · $1.76 out · 203k context here

    $0.74/M tokens
  2. 2

    CoreWeave

    Runs it themselves

    $0.50 in · $2.15 out

    $0.91/M tokens
  3. 3

    DeepInfra

    Runs it themselves

    $0.50 in · $2.20 out

    $0.93/M tokens
  4. 4

    DeepInfra

    Lower precision (fp4)

    $0.50 in · $2.20 out

    $0.93/M tokens
  5. 5

    $0.53 in · $2.27 out

    $0.96/M tokens
  6. 6

    NanoGPT

    Resells

    $0.50 in · $2.50 out · 1M context here

    $1/M tokens
  7. 7

    NanoGPT

    Resells

    $0.50 in · $2.50 out · 512k context here

    $1/M tokens
  8. 8

    OpenRouter

    Same as maker

    $0.60 in · $2.40 out

    $1.05/M tokens
  9. 9

    CommandCode

    Same as maker

    $0.60 in · $2.40 out · 1M context here

    $1.05/M tokens
  10. 10

    Vercel AI Gateway

    Same as maker

    $0.60 in · $2.40 out · 1M context here

    $1.05/M tokens
  11. 11

    Baseten

    Same as maker

    $0.60 in · $2.40 out · 203k context here

    $1.05/M tokens
  12. 12

    Baseten

    Same as maker

    $0.60 in · $2.40 out · 203k context here

    $1.05/M tokens
  13. 13

    Nous Portal

    Same as maker

    $0.60 in · $2.40 out

    $1.05/M tokens
  14. 14

    Impossibl

    Same as maker

    $0.60 in · $2.40 out

    $1.05/M tokens
  15. 15

    Venice

    Costs more

    $0.63 in · $3.13 out · 256k context here

    $1.25/M tokens
  16. 16

    Venice

    Costs more

    $0.63 in · $3.13 out · 256k context here

    $1.25/M tokens
  17. 17

    Eden AI

    Same as maker

    $0.60 in · $3.50 out · 1M context here

    $1.33/M tokens
  18. 18

    Together AI

    Same as maker

    $0.60 in · $3.60 out · 512k context here

    $1.35/M tokens
  19. 19

    $1 in · $3 out · 1M context here

    $1.50/M tokens
  20. 20

    Requesty

    Costs more

    $1 in · $3 out · 1M context here

    $1.50/M tokens
  21. 21

    DeepInfra

    Costs more

    $1 in · $5 out

    $2/M tokens
  22. 22

    Eden AI

    Costs more

    $1 in · $5 out

    $2/M tokens
  23. 23

    Thinking Machines

    Costs more

    $1.80 in · $6.23 out · 66k context here

    $2.91/M tokens

Not ranked

Below the maker's own price with nothing published to account for it, from a catalog we could not read reliably, or a free tier, which is a limit rather than a price. Why

  1. NVIDIA build

    Free tier

    given away with limits

    free
  2. LLMTR

    Free tier

    given away with limits

    free
  3. Kenari

    Not ranked

    $1.20 in · $7.50 out · 1M context here

    $2.78/M tokens

Something else wrong?

What it costs for your work
pages a month
$0.50

A month at OpenRouter's own price

$0.35

A month at Kilo Gateway, the cheapest

$0.16

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 Ultra and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.

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.
Lower precision
The open weights, served at a lower precision than the maker's, so not quite the same product.
Same as maker
Sold by someone else at the price the maker charges.
Costs more
Sold by someone else for more than the maker charges.
Free tier
Given away inside a quota. A limit is not a price, so it is never called cheapest.
Not ranked
Below the maker's price on a closed model with nothing to account for it, or from a catalog we could not read reliably. Listed, and never a pick.

Similar models

Models from other labs that do what Nemotron 3 Ultra does, cheapest first. Each percentage is against Nemotron 3 Ultra's cheapest price, $0.74 per M tokens.

Frequently asked

Who sells Nemotron 3 Ultra cheapest?
Kilo Gateway, at $0.40 in and $1.76 out per million tokens, checked 31 Oct 2026. The provider sells another company's endpoint, at a margin of its own or at the maker's price.
Is Nemotron 3 Ultra open weights?
Yes. NVIDIA publishes the weights, so anyone may host Nemotron 3 Ultra, which is why 18 providers sell it and why their prices differ so much.
How much context does Nemotron 3 Ultra hold?
262,144 tokens in one call, which is about 262k, and it can call your own functions.
How does Nemotron 3 Ultra compare with the rest of the market?
At $1.05 per million tokens, OpenRouter's own price is 19% above the typical $0.88 across the 392 text models we track.

More from NVIDIA