DeepSeek V3 0324 pricing.

Prices checked

DeepSeek V3 0324 costs $0.27 in and $1.10 out per million tokens from DeepSeek; the cheapest price is $0.20 at Hyperbolic, checked .

DeepSeek's own price

DeepSeek

$0.48/M tokens

$0.27 in · $1.10 out

46% below the typical price of the 392 text models we track.

Cheapest price

Hyperbolic

$0.20/M tokens

$0.20 in · $0.20 out

58% less than DeepSeek, and the provider says why.

tool callingstructured outputopen weights164k contextreleased 24 Mar 2025

Every provider selling DeepSeek V3 0324

  1. 1

    Hyperbolic

    Runs it themselves

    $0.20 in · $0.20 out · 33k context here

    $0.20/M tokens
  2. 2

    Lambda

    Runs it themselves

    $0.20 in · $0.60 out · 131k context here

    $0.30/M tokens
  3. 3

    NanoGPT

    Resells

    $0.20 in · $0.77 out · 128k context here

    $0.34/M tokens
  4. 4

    Submodel

    Runs it themselves

    $0.20 in · $0.80 out · 75k context here

    $0.35/M tokens
  5. 5

    DeepInfra

    Runs it themselves

    $0.24 in · $0.90 out

    $0.41/M tokens
  6. 6

    GMI Cloud

    Costs more

    $0.28 in · $0.88 out

    $0.43/M tokens
  7. 7

    $0.25 in · $1 out

    $0.44/M tokens
  8. 8

    $0.25 in · $1 out

    $0.44/M tokens
  9. 9

    TrustedRouter

    Costs more

    $0.30 in · $0.94 out

    $0.46/M tokens
  10. 10

    Eden AI

    Costs more

    $0.32 in · $0.89 out

    $0.46/M tokens
  11. 11

    DeepInfra

    Costs more

    $0.32 in · $0.89 out

    $0.46/M tokens
  12. 12

    Merge Gateway

    Same as maker

    $0.27 in · $1.10 out

    $0.48/M tokens
  13. 13

    DeepSeek

    Maker's price

    $0.27 in · $1.10 out · 66k context here

    $0.48/M tokens
  14. 14

    Meganova

    Same as maker

    $0.28 in · $1.10 out

    $0.48/M tokens
  15. 15

    D.Run (China)

    Costs more

    $0.28 in · $1.10 out · 131k context here

    $0.49/M tokens
  16. 16

    Jiekou

    Costs more

    $0.28 in · $1.14 out

    $0.49/M tokens
  17. 17

    $0.29 in · $1.15 out · 66k context here

    $0.50/M tokens
  18. 18

    OpenRouter

    Costs more

    $0.29 in · $1.14 out

    $0.50/M tokens
  19. 19

    Kilo Gateway

    Costs more

    $0.29 in · $1.14 out · 128k context here

    $0.50/M tokens
  20. 20

    GMI Cloud

    Costs more

    $0.29 in · $1.14 out · 128k context here

    $0.50/M tokens
  21. 21

    Nous Portal

    Costs more

    $0.29 in · $1.14 out

    $0.50/M tokens
  22. 22

    Qiniu

    Costs more

    $0.29 in · $1.16 out · 128k context here

    $0.51/M tokens
  23. 23

    $0.30 in · $1.20 out

    $0.52/M tokens
  24. 24

    AI/ML API

    Costs more

    $0.31 in · $1.21 out · 128k context here

    $0.53/M tokens
  25. 25

    $0.40 in · $1.30 out

    price from , a change is being checked
    $0.63/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. Featherless

    Not ranked

    $0.39 in · $1.63 out · 131k context here

    $0.70/M tokens

Something else wrong?

What it costs for your work
pages a month
$0.23

A month at DeepSeek's own price

$0.13

A month at Hyperbolic, the cheapest

$0.10

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 DeepSeek's own is listed as cheapest only when the provider says why.

Runs it themselves
The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
Resells
The provider sells another company's endpoint, at a margin of its own or at the maker's price.
Costs more
Sold by someone else for more than the maker charges.
Same as maker
Sold by someone else at the price the maker charges.
Maker's price
What the lab that trained the model charges on its own API. Every other row is measured against it.
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 DeepSeek V3 0324 does, cheapest first. Each percentage is against DeepSeek V3 0324's cheapest price, $0.20 per M tokens.

Frequently asked

Who sells DeepSeek V3 0324 cheapest?
Hyperbolic, at $0.20 in and $0.20 out per million tokens, checked 31 Oct 2026. The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
Is DeepSeek V3 0324 open weights?
Yes. DeepSeek publishes the weights, so anyone may host DeepSeek V3 0324, which is why 31 providers sell it and why their prices differ so much.
How much context does DeepSeek V3 0324 hold?
163,840 tokens in one call, which is about 164k, and it can call your own functions.
How does DeepSeek V3 0324 compare with the rest of the market?
At $0.48 per million tokens, DeepSeek's own price is 46% below the typical $0.88 across the 392 text models we track.

More from DeepSeek