MiniMax M2

MiniMax

A Mixture-of-Experts model with 230B total parameters and only 10B activated per inference, delivering exceptional efficiency. Built for the agentic era with function calling, advanced reasoning, and real-time streaming capabilities. With a 200K shared context window and 128K max output (including chain-of-thought), it handles massive contexts for coding and agentic work. Superseded by MiniMax M2.1 with improved coding and refactoring capabilities.

Try Now

Capabilities

Thinking

Tool Use

Example Use Cases

Agentic workflows with function calling

Coding at scale with large context

Need efficient model with advanced reasoning

Technical Specifications

Context Window

204,800 tokens

Max Output

128,000 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.30

Non-Reasoning Output

$1.20

Cache Read Input

$0.03

Cache Write Input

$0.375

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Legacy

Made legacy on

Reason

Superseded by MiniMax M2.1

Recommended Replacement

MiniMax M2.7