MiniMax: MiniMax M2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

37.4 Coding Index*57.0 tokens/sec*$0.12/1M input tokens†Free in Kilo
*Artificial Analysis‡Kilo Code Leaderboard†OpenRouterPinchBench

Totally Free. Only in Kilo

Use this model completely free in Kilo Code. No credits required. Get AI coding that actually works, from architecture and planning to coding, debugging and deployment.

Release Date
February 12, 2026
Context Window
196,608 tokens
Max Output
65,536 tokens
Input Modalities
text

Try MiniMax: MiniMax M2.5 in Kilo Code

Experience this model with the most popular open source coding agent. Free to start, pay only for AI usage. Use in popular IDEs like VS Code, JetBrains, command line, or cloud agents.

2.3M+

Downloads

500+

models supported

Free

to Start

Get Started with Kilo

Access 500+ models including MiniMax: MiniMax M2.5 and many more in Kilo Code

Benchmarking MiniMax: MiniMax M2.5

Coding Performance

Coding benchmarks and performance metrics for development tasks

Coding Benchmarks

Artificial Analysis Coding Index

37.4%

Overall coding capability score

SciCode

42.6%

Scientific computing & algorithms

TerminalBench Hard

34.8%

CLI & terminal command generation

LCR (Long Context Reasoning)

66.0%

Understanding large codebases

IFBench

71.6%

Instruction following accuracy

Speed & Efficiency

Output Speed

57.0 tokens/sec

Median output tokens per second

Performance metrics from Artificial Analysis

Real-World Usage

Real-world usage statistics from the Kilo Code community

Weekly Token Usage

Mode Rankings (Last Week)

Where this model ranks for each built-in mode

Architect

Plan and design before implementation

No data

Code

Write, modify, and refactor code

No data

Ask

Get answers and explanations

#90

Debug

Diagnose and fix software issues

No data

Orchestrator

Coordinate tasks across multiple modes

No data

Real-world metrics from the Kilo Code Leaderboard

Pricing

Cost per 1 million tokens

Input Tokens
$0.12
per 1M tokens
Output Tokens
$0.99
per 1M tokens

Example Cost

Analyzing a 10,000 line codebase (≈40k input tokens, 10k output tokens) costs approximately $0.0146

Coding Capabilities

Features and parameters relevant to coding tasks

Coding Features

Function Calling
Can call external functions/APIs
Tool Choice
Control over function selection
Structured Outputs
JSON schema validation
Reasoning Tokens
Extended thinking for complex problems

Pricing details from OpenRouter

Technical Details

Architecture and implementation specifications

Model ID
minimax/minimax-m2.5
Artificial Analysis Slug
minimax-m2-5
Created
February 12, 2026
Tokenizer
Other
Input Modalities
text
Context Window
196,608 tokens
Max Completion Tokens
65,536 tokens
Input Price
$0.12 per 1M tokens
Output Price
$0.99 per 1M tokens
Cache Read Price
$0.00 per 1M tokens
Content Moderation
Disabled

Ready to try MiniMax: MiniMax M2.5?

Install Kilo Code and start using MiniMax: MiniMax M2.5 for your coding projects today. Choose from 500+ AI models with complete freedom.

Get Started with Kilo