MiniMax-M2 pricing.

Prices checked

MiniMax-M2 costs $0.30 in and $1.20 out per million tokens from MiniMax; the cheapest price is $0.40 at LLM Gateway, checked .

MiniMax's own price

MiniMax

$0.52/M tokens

$0.30 in · $1.20 out

40% below the typical price of the 392 text models we track.

Cheapest price

LLM Gateway

$0.40/M tokens

$0.20 in · $1 out

24% less than MiniMax, and the provider says why.

tool callingreasoningopen weights205k contextreleased 27 Oct 2025

Every provider selling MiniMax-M2

  1. 1

    $0.20 in · $1 out · 197k context here

    $0.40/M tokens
  2. 2

    OpenRouter

    Resells

    $0.26 in · $1.02 out

    $0.45/M tokens
  3. 3

    $0.26 in · $1.02 out

    $0.45/M tokens
  4. 4

    MiniMax

    Resells

    $0.26 in · $1.02 out

    $0.45/M tokens
  5. 5

    $0.26 in · $1.02 out

    $0.45/M tokens
  6. 6

    NanoGPT

    Resells

    $0.17 in · $1.53 out · 200k context here

    $0.51/M tokens
  7. 7

    Vercel AI Gateway

    Same as maker

    $0.30 in · $1.20 out

    $0.52/M tokens
  8. 8

    MiniMax

    Maker's price

    $0.30 in · $1.20 out

    $0.52/M tokens
  9. 9

    $0.30 in · $1.20 out

    $0.52/M tokens
  10. 10

    Merge Gateway

    Same as maker

    $0.30 in · $1.20 out

    $0.52/M tokens
  11. 11

    Ofox

    Same as maker

    $0.30 in · $1.20 out

    $0.52/M tokens
  12. 12

    ZenMux

    Same as maker

    $0.30 in · $1.20 out · 204k context here

    $0.52/M tokens
  13. 13

    Eden AI

    Same as maker

    $0.30 in · $1.20 out

    $0.52/M tokens
  14. 14

    Fireworks AI

    Same as maker

    $0.30 in · $1.20 out · 197k context here

    $0.52/M tokens
  15. 15

    Novita

    Same as maker

    $0.30 in · $1.20 out

    $0.52/M tokens
  16. 16

    Requesty

    Same as maker

    $0.30 in · $1.20 out · 200k context here

    $0.52/M tokens
  17. 17

    Qiniu

    Same as maker

    $0.30 in · $1.22 out · 200k context here

    $0.53/M tokens
  18. 18

    MiniMax (China)

    Costs more

    $0.31 in · $1.25 out

    $0.55/M tokens
  19. 19

    TrustedRouter

    Costs more

    $0.32 in · $1.27 out

    $0.55/M tokens
  20. 20

    302.AI

    Costs more

    $0.33 in · $1.32 out · 1M context here

    $0.58/M tokens
  21. 21

    Cortecs

    Costs more

    $0.35 in · $1.41 out · 400k context here

    $0.61/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. MiniMax Token Plan (minimax.io)

    Free tier

    given away with limits

    free
  2. MiniMax Token Plan (minimax.cn)

    Free tier

    given away with limits

    free
  3. Featherless

    Not ranked

    $0.28 in · $1.11 out

    $0.49/M tokens

Something else wrong?

What it costs for your work
pages a month
$0.25

A month at MiniMax's own price

$0.18

A month at LLM Gateway, the cheapest

$0.07

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 MiniMax'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.
Credits
Priced in credits or points that convert to dollars, so the rate moves when the conversion does.
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.
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 MiniMax-M2 does, cheapest first. Each percentage is against MiniMax-M2's cheapest price, $0.40 per M tokens.

Frequently asked

Who sells MiniMax-M2 cheapest?
LLM Gateway, at $0.20 in and $1 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 MiniMax-M2 open weights?
Yes. MiniMax publishes the weights, so anyone may host MiniMax-M2, which is why 21 providers sell it and why their prices differ so much.
How much context does MiniMax-M2 hold?
204,800 tokens in one call, which is about 205k, and it can call your own functions.
How does MiniMax-M2 compare with the rest of the market?
At $0.52 per million tokens, MiniMax's own price is 40% below the typical $0.88 across the 392 text models we track.

More from MiniMax