Hugging Face Inference Providers model pricing.

Prices checked

Hugging Face Inference Providers sells 69 prices on 72 models, from $0.06 per million tokens, checked .

Every model Hugging Face Inference Providers sells

  1. 1

    $0.06 in · $0.06 out

    $0.06/M tokens
    View
  2. 2

    Gemma 3 4B

    Same as maker

    $0.05 in · $0.10 out

    $0.06/M tokens
    View
  3. 3

    Gemma 3 12B

    Same as maker

    $0.05 in · $0.15 out

    $0.08/M tokens
    View
  4. 4

    Qwen3 8B

    Resells

    $0.07 in · $0.18 out

    $0.10/M tokens
    View
  5. 5

    Gemma 3 27B

    Same as maker

    $0.08 in · $0.16 out

    $0.10/M tokens
    View
  6. 6

    $0.07 in · $0.26 out

    $0.12/M tokens
    View
  7. 7

    $0.10 in · $0.30 out

    $0.15/M tokens
    View
  8. 8

    $0.14 in · $0.28 out

    $0.18/M tokens
    View
  9. 9

    Llama Guard 4 12B

    Same as maker

    $0.18 in · $0.18 out

    $0.18/M tokens
    View
  10. 10

    Qwen3.5-9B

    Costs more

    $0.17 in · $0.25 out

    $0.19/M tokens
    View
  11. 11

    $0.13 in · $0.40 out

    $0.20/M tokens
    View
  12. 12

    gpt-oss-20b

    Costs more

    $0.10 in · $0.50 out

    $0.20/M tokens
    View
  13. 13

    $0.14 in · $0.40 out

    $0.21/M tokens
    View
  14. 14

    Qwen3 30B A3B

    Costs more

    $0.12 in · $0.50 out

    $0.21/M tokens
    View
  15. 15

    GLM-5.3-Flash

    Same as maker

    $0.15 in · $0.50 out

    $0.24/M tokens
    View
  16. 16

    Hy3

    Costs more

    $0.14 in · $0.58 out

    $0.25/M tokens
    View
  17. 17

    MiniMax-M3.1-Flash

    Same as maker

    $0.15 in · $0.60 out

    $0.26/M tokens
    View
  18. 18

    $0.13 in · $0.85 out

    $0.31/M tokens
    View
  19. 19

    DeepSeek V3.2

    Same as maker

    $0.28 in · $0.40 out

    $0.31/M tokens
    View
  20. 20

    Qwen3-VL 30B-A3B

    Same as maker

    $0.20 in · $0.70 out

    $0.33/M tokens
    View
  21. 21

    $0.15 in · $0.95 out

    $0.35/M tokens
    View
  22. 22

    gpt-oss-120b

    Costs more

    $0.25 in · $0.69 out

    $0.36/M tokens
    View
  23. 23

    Qwen3 32B

    Resells

    $0.29 in · $0.59 out

    $0.36/M tokens
    View
  24. 24

    $0.25 in · $1 out

    $0.44/M tokens
    View
  25. 25

    Step 3.7 Flash

    Same as maker

    $0.20 in · $1.15 out

    $0.44/M tokens
    View

Not ranked

Below the maker's own price with nothing published to account for it, or from a catalog we could not read reliably. Why

  1. $0.06 in · $0.20 out

    $0.10/M tokens
    View

Where to start

Kind

Router

based in US

Free tier

No

every price is paid

Where Hugging Face Inference Providers ranks

What Hugging Face Inference Providers charges per million tokens embedded

Priced on input alone, since an embedding model writes no output, so never held beside a chat model's blended price. Every embedding model

Embedding models, per 1M input tokens

  1. 1

    Qwen3 Embedding 4B

    No maker price

    Alibaba Cloud

    $0.01/M tokens
  2. 2

    Qwen3 Embedding 8B

    No maker price

    Alibaba Cloud

    $0.01/M tokens

Frequently asked

What is Hugging Face Inference Providers?
Routes to partner hosts at their price; each model's page lists the hosts with latency and throughput. It sells 72 of the models we track, and trades as Hugging Face, Inc., based in US.
Is Hugging Face Inference Providers cheaper than buying from the maker?
22 of its 69 prices are below the maker's own price, and 18 of those come with a published reason, so they can lead a ranking. 1 are listed and not ranked, because nothing accounts for the gap.
Does Hugging Face Inference Providers train on what you send it?
Hugging Face Inference Providers does not say whether it trains on what you send it. It does not say how long it keeps requests.
How current are these Hugging Face Inference Providers prices?
They come from the public catalogs we read, read every 3 days; the reading on this page is from 31 Oct 2026. Prices exclude tax.

Models it sells

Other routers

Where to go next