MiniMax M2.5

minimax

MiniMax M2.5 is a SOTA large language model designed for real-world productivity, achieving 80.2% on SWE-Bench Verified and 51.3% on Multi-SWE-Bench. A 230B MoE model (10B active) capable of handling the entire development process of complex systems across Web, Android, iOS, Windows, and Mac platforms. Excels at coding, agentic tool use, search, and office productivity. With a 200K shared context window, 131K max output, and ~60 tps output speed, it delivers peak performance at exceptional value.

Try Now

Capabilities

Tool Use

Extended Thinking

Example Use Cases

Complex full-stack development across platforms

Need SOTA coding with tool calling

Large-scale code generation and refactoring

Technical Specifications

Context Window

204,800 tokens

Max Output

131,072 tokens

Cache Miss Cost

$0.30 per 1M tokens

Non-Reasoning Cost

$1.20 per 1M tokens

Cache Read Cost

$0.03 per 1M tokens

Cache Write Cost

$0.375 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls