DeepSeek V4 Pro pricing.

Prices checked

DeepSeek V4 Pro costs $0.66 in and $1.98 out per million tokens from DeepSeek; the cheapest price is $0.28 at TrustedRouter, checked .

DeepSeek's own price

DeepSeek

$0.99/M tokens

$0.66 in · $1.98 out

12% above the typical price of the 392 text models we track.

Cheapest price

TrustedRouter

$0.28/M tokens

$0.16 in · $0.63 out

72% less than DeepSeek, and the provider says why.

tool callingreasoningstructured outputopen weights1M contextreleased 13 Aug 2026

Every provider selling DeepSeek V4 Pro

  1. 1

    $0.16 in · $0.63 out

    $0.28/M tokens
  2. 2

    routing.run

    Runs it themselves

    $0.35 in · $0.70 out

    $0.43/M tokens
  3. 3

    EBCloud

    Runs it themselves

    $0.43 in · $0.86 out

    $0.54/M tokens
  4. 4

    Sail Research

    Lower precision (fp4)

    $0.45 in · $0.80 out

    price from , a change is being checked
    $0.54/M tokens
  5. 5

    TokenGo

    Runs it themselves

    $0.43 in · $0.87 out

    $0.54/M tokens
  6. 6

    Modelis

    Runs it themselves

    $0.43 in · $0.87 out

    $0.54/M tokens
  7. 7

    RunInfra

    Resells

    $0.60 in · $1.90 out

    $0.92/M tokens
  8. 8

    StreamLake

    Costs more

    $0.79 in · $1.58 out

    $0.99/M tokens
  9. 9

    OpenRouter

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  10. 10

    LLM Gateway

    Same as maker

    $0.66 in · $1.98 out · 1.1M context here

    $0.99/M tokens
  11. 11

    CommandCode

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  12. 12

    Vercel AI Gateway

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  13. 13

    OrcaRouter

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  14. 14

    OpenCode Go

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  15. 15

    ClinePass

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  16. 16

    Ollama Cloud

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  17. 17

    Ollama Cloud

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  18. 18

    Tempr Gateway

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  19. 19

    DeepSeek

    Maker's price

    $0.66 in · $1.98 out

    $0.99/M tokens
  20. 20

    ZenMux

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  21. 21

    StreamLake

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  22. 22

    LLMTR

    Same as maker

    $0.66 in · $1.98 out

    $0.99/M tokens
  23. 23

    Poe

    Same as maker

    $0.67 in · $2 out

    $1.00/M tokens
  24. 24

    NanoGPT

    Costs more

    $1.32 in · $0.04 out

    price from , a change is being checked
    $1.00/M tokens
  25. 25

    NanoGPT

    Costs more

    $1.32 in · $0.04 out

    price from , a change is being checked
    $1.00/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. Alibaba Token Plan

    Free tier

    given away with limits

    free
  2. Volcengine Ark Coding Plan

    Free tier

    given away with limits

    free
  3. SCNet Token Plan

    Free tier

    given away with limits

    free
  4. Alibaba Token Plan (China)

    Free tier

    given away with limits

    free
  5. SenseNova (China)

    Free tier

    given away with limits

    free
  6. Kenari

    Not ranked

    $1 in · $2 out

    $1.25/M tokens
  7. ai&

    Not ranked

    $1 in · $2.50 out

    $1.38/M tokens
  8. Featherless

    Not ranked

    $1.60 in · $3.20 out · 262k context here

    $2/M tokens

Something else wrong?

What it costs for your work
pages a month
$0.51

A month at DeepSeek's own price

$0.13

A month at TrustedRouter, the cheapest

$0.38

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.

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.
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.
Credits
Priced in credits or points that convert to dollars, so the rate moves when the conversion does.
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 DeepSeek V4 Pro does, cheapest first. Each percentage is against DeepSeek V4 Pro's cheapest price, $0.28 per M tokens.

Frequently asked

Who sells DeepSeek V4 Pro cheapest?
TrustedRouter, at $0.16 in and $0.63 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 DeepSeek V4 Pro open weights?
Yes. DeepSeek publishes the weights, so anyone may host DeepSeek V4 Pro, which is why 94 providers sell it and why their prices differ so much.
How much context does DeepSeek V4 Pro hold?
1,048,576 tokens in one call, which is about 1M, and it can call your own functions.
How does DeepSeek V4 Pro compare with the rest of the market?
At $0.99 per million tokens, DeepSeek's own price is 12% above the typical $0.88 across the 392 text models we track.

More from DeepSeek