Kuraberu AI models, home

AI models

Sections

Prime Inference model pricing.

Prices checked

Prime Inference sells 67 prices on 67 models, from $0.13 per million tokens, checked .

Every model Prime Inference sells

  1. 1

    gpt-oss-20b

    Costs more

    $0.07 in · $0.30 out

    $0.13/M tokens
  2. 2

    GPT-5 Nano

    Same as maker

    $0.05 in · $0.40 out

    $0.14/M tokens
  3. 3

    Gemma 3 27B

    Costs more

    $0.12 in · $0.30 out

    $0.16/M tokens
  4. 4

    Mistral Nemo

    Costs more

    $0.17 in · $0.17 out

    $0.17/M tokens
  5. 5

    GPT-4.1 nano

    Same as maker

    $0.10 in · $0.40 out

    $0.18/M tokens
  6. 6

    GPT-6 Luna

    Same as maker

    $0.10 in · $0.50 out

    $0.20/M tokens
  7. 7

    Qwen3 30B A3B

    Costs more

    $0.13 in · $0.52 out

    $0.23/M tokens
  8. 8

    GLM-5.3-Flash

    Same as maker

    $0.15 in · $0.50 out

    $0.24/M tokens
  9. 9

    GPT-4o mini

    Same as maker

    $0.15 in · $0.60 out

    $0.26/M tokens
  10. 10

    Mistral Small 4

    Costs more

    $0.17 in · $0.66 out

    $0.29/M tokens
  11. 11

    Qwen3-VL 30B-A3B

    Same as maker

    $0.20 in · $0.70 out

    $0.33/M tokens
  12. 12

    gpt-oss-120b

    Costs more

    $0.35 in · $0.75 out

    $0.45/M tokens
  13. 13

    GPT-5.6 Luna

    Same as maker

    $0.20 in · $1.20 out

    $0.45/M tokens
  14. 14

    GPT-5.4 nano

    Same as maker

    $0.20 in · $1.25 out

    $0.46/M tokens
  15. 15

    DeepSeek V4.1 Flash 1017

    Costs more

    $0.30 in · $1.20 out

    $0.52/M tokens
  16. 16

    Qwen3 Coder Next

    Costs more

    $0.30 in · $1.50 out

    $0.60/M tokens
  17. 17

    Qwen3-VL 235B-A22B

    Runs it themselves

    $0.30 in · $1.50 out

    $0.60/M tokens
  18. 18

    DeepSeek V4 Flash 0731

    Costs more

    $0.44 in · $1.32 out

    $0.66/M tokens
  19. 19

    GPT-5 Mini

    Same as maker

    $0.25 in · $2 out

    $0.69/M tokens
  20. 20

    GPT-4.1 mini

    Same as maker

    $0.40 in · $1.60 out

    $0.70/M tokens
  21. 21

    Mistral Large 2.1

    Runs it themselves

    $0.50 in · $1.50 out

    $0.75/M tokens
  22. 22

    Kimi K2 0905

    Same as maker

    $0.60 in · $2.50 out

    $1.08/M tokens
  23. 23

    Gemini 3 Flash Preview

    Same as maker

    $0.50 in · $3 out

    $1.13/M tokens
  24. 24

    Llama 3.3 70B Instruct

    Costs more

    $1.04 in · $2.25 out

    $1.34/M tokens
  25. 25

    Gemini 3.8 Flash

    Same as maker

    $0.75 in · $3.75 out

    $1.50/M tokens

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. Grok 4.7

    Not ranked

    $1.60 in · $4.80 out

    $2.40/M tokens

  2. GPT-4o

    Not ranked

    $2.50 in · $10 out

    $4.38/M tokens
Where these prices come from

Where to start

Cheapest

gpt-oss-20b

131k context · tool calling · reasoning

Prime Inference

$0.13/M tokens

The least you pay per million tokens at Prime Inference.

Biggest saving

Mistral Large 2.1

131k context · tool calling · open weights

Prime Inference

$0.75/M tokens

75% less than you pay Mistral AI for it.

Most widely sold

GLM-5.3

1M context · tool calling · reasoning

Prime Inference

$2.15/M tokens

103 providers sell it, so you can hold this price against theirs.

Kind

Router

Many makers' models, one API and one bill.

Free tier

No

every price is paid

Frequently asked

What is Prime Inference?
Many makers' models, one API and one bill. It sells 67 of the models we track.
Is Prime Inference cheaper than buying from the maker?
5 of its 67 prices are below the maker's own price, and 2 of those come with a published reason, so they can lead a ranking. 2 are listed and not ranked, because nothing accounts for the gap.
Does Prime Inference train on what you send it?
Prime Inference does not say whether it trains on what you send it. It does not say how long it keeps requests.
How current are these Prime Inference prices?
They come from the public catalogs we read, read every day; the reading on this page is from 21 Oct 2026. Prices exclude tax.

Models it sells

GLM-5.3GLM-5.2DeepSeek V4 Flash 0731GLM-5.3-FlashDeepSeek V4 ProKimi K3

Other routers

NanoGPTOpenRouterKilo GatewayEden AITrustedRouterNous Portal

Where to go next

All providersAll modelsToday's rankings