Inference.net model pricing.

Prices checked

Inference.net sells 64 prices on 57 models, from $0.06 per million tokens, checked .

Every model Inference.net sells

  1. 1

    Gemma 3 4B

    Same as maker

    $0.05 in · $0.10 out

    $0.06/M tokens
    View
  2. 2

    $0.03 in · $0.20 out

    $0.07/M tokens
    View
  3. 3

    $0.05 in · $0.33 out

    $0.12/M tokens
    View
  4. 4

    Gemma 3 27B

    Costs more

    $0.09 in · $0.25 out

    $0.13/M tokens
    View
  5. 5

    GPT-5 Nano

    Same as maker

    $0.05 in · $0.40 out

    $0.14/M tokens
    View
  6. 6

    GLM-5.3-Flash

    Lower precision (fp4)

    $0.11 in · $0.35 out

    $0.17/M tokens
    View
  7. 7

    $0.10 in · $0.40 out

    $0.18/M tokens
    View
  8. 8

    GPT-4.1 nano

    Same as maker

    $0.10 in · $0.40 out

    $0.18/M tokens
    View
  9. 9

    GLM-5.3-Flash

    Runs it themselves

    $0.10 in · $0.45 out

    $0.19/M tokens
    View
  10. 10

    DeepSeek V4.1 Flash 1017

    Lower precision (fp8)

    $0.08 in · $0.55 out

    $0.20/M tokens
    View
  11. 11

    $0.13 in · $0.40 out

    $0.20/M tokens
    View
  12. 12

    GPT-6 Luna

    Same as maker

    $0.10 in · $0.50 out

    $0.20/M tokens
    View
  13. 13

    Qwen3 30B A3B

    Costs more

    $0.12 in · $0.50 out

    $0.21/M tokens
    View
  14. 14

    GPT-4o mini

    Same as maker

    $0.15 in · $0.60 out

    $0.26/M tokens
    View
  15. 15

    $0.23 in · $0.62 out

    $0.33/M tokens
    View
  16. 16

    Qwen3 14B

    Runs it themselves

    $0.23 in · $0.91 out

    $0.40/M tokens
    View
  17. 17

    GPT-5.6 Luna

    Same as maker

    $0.20 in · $1.20 out

    $0.45/M tokens
    View
  18. 18

    $0.30 in · $1 out

    $0.47/M tokens
    View
  19. 19

    $0.25 in · $1.50 out

    $0.56/M tokens
    View
  20. 20

    GPT-5 Mini

    Same as maker

    $0.25 in · $2 out

    $0.69/M tokens
    View
  21. 21

    GPT-4.1 mini

    Same as maker

    $0.40 in · $1.60 out

    $0.70/M tokens
    View
  22. 22

    Qwen3.7 Plus

    Same as maker

    $0.40 in · $1.60 out

    $0.70/M tokens
    View
  23. 23

    Gemini 2.5 Flash

    Same as maker

    $0.30 in · $2.50 out

    $0.85/M tokens
    View
  24. 24

    $0.30 in · $2.50 out

    $0.85/M tokens
    View
  25. 25

    DeepSeek V3.2

    Costs more

    $0.70 in · $2 out

    $1.03/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. $0.10 in · $0.50 out

    $0.20/M tokens
    View
  2. $0.10 in · $0.55 out

    $0.21/M tokens
    View
  3. GLM-5.3

    Not ranked

    $0.18 in · $4.40 out

    $1.24/M tokens
    View
  4. Kimi K3

    Not ranked

    $0.24 in · $10.80 out

    $2.88/M tokens
    View

Where to start

Kind

Open network

based in US

Free tier

No

every price is paid

Frequently asked

What is Inference.net?
Serves open-weight models on a distributed GPU network. It sells 57 of the models we track, and trades as Inference.net, based in US.
Is Inference.net cheaper than buying from the maker?
13 of its 64 prices are below the maker's own price, and 8 of those come with a published reason, so they can lead a ranking. 4 are listed and not ranked, because nothing accounts for the gap.
Does Inference.net train on what you send it?
Inference.net does not say whether it trains on what you send it. It does not say how long it keeps requests.
How current are these Inference.net prices?
They come from its own public catalog, read every 3 days; the reading on this page is from 31 Oct 2026. Prices exclude tax.

Models it sells

Other open networks

Where to go next