MiniMax M1

MiniMax-M1: The World's First Open-Weight, Large-Scale Hybrid Attention Inference Model MiniMax-M1 adopts a Mixture of Experts (MoE) architecture and integrates the Flash Attention mechanism. The mod

Context
1M
Max output
40K
Input price
$0.55/1M tokens
Output price
$2.2/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDminimaxai/minimax-m1-80k
Provider Novita AI
Creator minimaxai
Familyminimax
License—
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window1M tokens
Max input—
Max output40K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.novita.ai/v3/openai/v1/chat/completions

Pricing

Input
$0.55
Output
$2.2
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: minimax

ModelContextMax outPricing
MiniMax M3.1 Flash1M524K$0.15$0.6
MiniMax M2.1205K131K$0.3$1.2
MiniMax M2.5205K131K$0.3$1.2
MiniMax M2.7205K131K$0.3$1.2
MiniMax M2205K131K$0.3$1.2
MiniMax M31M131K$0.3$1.2
MiniMax M11M40K$0.55$2.2
MiniMax M2.5 Highspeed205K131K$0.6$2.4
MiniMax M2.7-highspeed205K131K$0.6$2.4

API

GET/v1/models/novita/minimaxai/minimax-m1-80k