Hy3 pricing.

Prices checked

Hy3 costs $0.13 in and $0.53 out per million tokens from Tencent; the cheapest price is $0.11 at NanoGPT, checked .

Tencent's own price

Tencent

$0.23/M tokens

$0.13 in · $0.53 out

74% below the typical price of the 392 text models we track.

Cheapest price

NanoGPT

$0.11/M tokens

$0.07 in · $0.26 out

50% less than Tencent, and the provider says why.

tool callingreasoningstructured outputopen weights262k contextreleased 6 Jul 2026

Every provider selling Hy3

  1. 1

    NanoGPT

    Resells

    $0.07 in · $0.26 out

    $0.11/M tokens
  2. 2

    DeepInfra

    Same as maker

    $0.13 in · $0.53 out

    $0.23/M tokens
  3. 3

    OpenRouter

    Same as maker

    $0.13 in · $0.53 out

    $0.23/M tokens
  4. 4

    LLM Gateway

    Same as maker

    $0.13 in · $0.53 out

    $0.23/M tokens
  5. 5

    Kilo Gateway

    Same as maker

    $0.13 in · $0.53 out

    $0.23/M tokens
  6. 6

    Eden AI

    Same as maker

    $0.13 in · $0.53 out · 256k context here

    $0.23/M tokens
  7. 7

    SiliconFlow

    Same as maker

    $0.13 in · $0.53 out

    $0.23/M tokens
  8. 8

    Tencent

    Same as maker

    $0.13 in · $0.53 out

    $0.23/M tokens
  9. 9

    Nous Portal

    Same as maker

    $0.13 in · $0.53 out

    $0.23/M tokens
  10. 10

    Impossibl

    Same as maker

    $0.13 in · $0.53 out

    a new price, being checked
    $0.23/M tokens
  11. 11

    TrustedRouter

    Costs more

    $0.14 in · $0.56 out

    $0.24/M tokens
  12. 12

    $0.14 in · $0.58 out

    $0.25/M tokens
  13. 13

    Jalapeno Cloud

    Costs more

    $0.14 in · $0.58 out · 203k context here

    $0.25/M tokens
  14. 14

    $0.14 in · $0.58 out

    $0.25/M tokens
  15. 15

    OpenCode Go

    Costs more

    $0.14 in · $0.58 out · 256k context here

    $0.25/M tokens
  16. 16

    Requesty

    Costs more

    $0.14 in · $0.58 out

    $0.25/M tokens
  17. 17

    Novita

    Costs more

    $0.14 in · $0.58 out

    $0.25/M tokens
  18. 18

    GMI Cloud

    Costs more

    $0.14 in · $0.58 out

    $0.25/M tokens
  19. 19

    LLMTR

    Costs more

    $0.14 in · $0.58 out · 197k context here

    $0.25/M tokens
  20. 20

    Poe

    Costs more

    $0.14 in · $0.59 out

    $0.25/M tokens
  21. 21

    ZenMux

    Costs more

    $0.15 in · $0.59 out

    $0.26/M tokens
  22. 22

    AIHubMix

    Costs more

    $0.17 in · $0.57 out · 256k context here

    $0.27/M tokens
  23. 23

    Phala (RedPill)

    Costs more

    $0.15 in · $0.64 out

    $0.27/M tokens
  24. 24

    CrossModel

    Costs more

    $0.16 in · $0.64 out

    $0.28/M tokens
  25. 25

    OrcaRouter

    Costs more

    $0.18 in · $0.59 out · 256k context here

    $0.28/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. Tencent TokenHub

    Free tier

    given away with limits

    free
  2. Tencent Token Plan

    Free tier

    given away with limits

    free
  3. Kenari

    Not ranked

    $0.27 in · $1.10 out · 256k context here

    $0.48/M tokens
  4. Featherless

    Not ranked

    $1 in · $4 out · 33k context here

    $1.75/M tokens

Something else wrong?

What it costs for your work
pages a month
$0.11

A month at Tencent's own price

$0.06

A month at NanoGPT, the cheapest

$0.06

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 Tencent'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.
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 Hy3 does, cheapest first. Each percentage is against Hy3's cheapest price, $0.11 per M tokens.

Frequently asked

Who sells Hy3 cheapest?
NanoGPT, at $0.07 in and $0.26 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 Hy3 open weights?
Yes. Tencent publishes the weights, so anyone may host Hy3, which is why 29 providers sell it and why their prices differ so much.
How much context does Hy3 hold?
262,144 tokens in one call, which is about 262k, and it can call your own functions.
How does Hy3 compare with the rest of the market?
At $0.23 per million tokens, Tencent's own price is 74% below the typical $0.88 across the 392 text models we track.

More from Tencent