MiniMax M2.7

MiniMax

MiniMax M2.7 is the latest generation of the MiniMax M-series, a 230B MoE model with 10B active parameters. It delivers enhanced agentic capabilities including tool calling, reasoning, and multi-step task execution. With a 200K shared context window, 131K max output, and ~60 tps output speed, it builds on the strengths of M2.5 with improved performance across coding, agent workflows, and real-world productivity tasks.

Try Now

Capabilities

Thinking

Tool Use

Example Use Cases

Agentic workflows with strong tool calling

Full-stack development across platforms

Complex coding and reasoning tasks

Technical Specifications

Context Window

204,800 tokens

Max Output

131,072 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.30

Non-Reasoning Output

$1.20

Cache Read Input

$0.06

Cache Write Input

$0.375

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19