All models

MiniMax M2.7 Highspeed

MiniMax205K contextReasoningTool calling

As of Oct 14, 2026, MiniMax M2.7 Highspeed costs $0.60 per million input tokens and $2.40 per million output tokens from MiniMax. None of its 2 sellers is cheaper than MiniMax.

Official price from MiniMax

Pricing page

Per million tokens

Input
$0.60
Output
$2.40
Cached input
$0.06
Batch input / output
—
  • Writing to the prompt cache costs $0.375 per million tokens.
  • Up to 131K 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: $10.80 a month.

Where to buy it (2)

Sorted by your monthly estimate. Prices per million tokens.

  • MiniMaxOfficial

    Input / output
    $0.60 / $2.40
    Context
    205K
    Per month
    $10.80

    MiniMax-M2.7-highspeed

  • Input / output
    $0.60 / $2.40
    Context
    205K
    Per month
    $10.80

    novita/minimax/minimax-m2.7-highspeed

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

Similar models

About this data

Prices come from LiteLLM's model cost map, with more sellers from models.dev (both MIT licence), checked Oct 14, 2026; confirm on the seller's pricing page before you rely on a number.