Model Square
Minimax

MiniMax-M2.5

MiniMax (minimax.io)·Usage-based billing

Prior MiniMax coding model for agent workflows, office edits, and automation

TPS
—
Average latency
—
Success rate
—

Pricing

Base Price

Input
$0.3/ 1M
Output
$1.2/ 1M
Cached input$0.03/ 1M
Cache write$0.375/ 1M

Pricing by Group

GroupRatioInputOutputCacheCache Write
default
1x
$0.3
$1.2
$0.03
$0.375

Prices shown per 1M tokens

Model

ProviderMiniMax (minimax.io)
TypeUsage-based billing
Groups
default
Endpoints
openai
Tags
ReasoningToolsOpenWeights204.8K
MiniMax-M2.5