Appndo
All models

MiniMax M2.5

MiniMax1M contextReasoningTool calling

LMArena score 1359 · #197 overall · #190 in coding (2026-10-13)

Official price from MiniMax

Per million tokens

Input
$0.30
Output
$1.20
Cached input
$0.03
Batch input / output
—
  • Writing to the prompt cache costs $0.375 per million tokens.
  • Up to 8K output tokens per request.

Estimate your monthly cost

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From MiniMax: $5.40 a month.

Where to buy it (7)

Sorted by your monthly estimate. Prices per million tokens.

  • Baseten

    Input / output
    $0.30 / $1.20
    Context
    —
    Per month
    $5.40

    baseten/MiniMaxAI/MiniMax-M2.5

  • Amazon Bedrock Converse

    Input / output
    $0.30 / $1.20
    Context
    196K
    Per month
    $5.40

    minimax.minimax-m2.5

  • FriendliAI

    Input / output
    $0.30 / $1.20
    Context
    197K
    Per month
    $5.40

    friendliai/MiniMaxAI/MiniMax-M2.5

  • MiniMaxOfficial

    Input / output
    $0.30 / $1.20
    Context
    1M
    Per month
    $5.40

    minimax/MiniMax-M2.5

  • Nebius

    Input / output
    $0.30 / $1.20
    Context
    197K
    Per month
    $5.40

    nebius/MiniMaxAI/MiniMax-M2.5

  • Novita AI

    Input / output
    $0.30 / $1.20
    Context
    205K
    Per month
    $5.40

    novita/minimax/minimax-m2.5

  • Tensormesh

    Input / output
    $0.30 / $1.20
    Context
    197K
    Per month
    $5.40

    tensormesh/MiniMaxAI/MiniMax-M2.5

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Reasoning, Tool calling.

Similar models