MiniMax-M2.1
About MiniMax-M2.1
MiniMax-M2.1 is an open-source large language model optimized for agentic capabilities, excelling in coding, tool use, instruction following, and long-horizon planning. It supports multilingual software development and complex multi-step workflows, achieving 74.0 on SWE-bench Verified and outperforming Claude Sonnet 4.5 in multilingual scenarios
Discover how MiniMax-M2.1's agentic capabilities, coding prowess, and long-horizon planning solve complex, multi-step challenges across diverse domains.
Multilingual Code Agent
Automate full-stack development across diverse languages, from initial design to deployment, handling complex, multi-step coding tasks.
Use Case Example:
"Developed a complete e-commerce backend in Python and a React frontend, integrating a payment gateway and deploying to AWS, all via agentic planning."
Complex Workflow Automation
Design and execute intricate multi-step workflows by intelligently selecting and using various tools and APIs to achieve long-term goals.
Use Case Example:
"Automated a data pipeline: fetched from Salesforce, cleaned with a custom Python script, generated Tableau reports, adapting to schema changes."
Proactive System Remediation
Continuously monitor live systems, identify performance bottlenecks, security flaws, and logical errors, then generate and apply fixes.
Use Case Example:
"Detected a race condition in a Go microservice, automatically generated a mutex patch, and deployed it to staging for validation."
Advanced Technical Tutoring
Provide interactive, step-by-step guidance for learning complex programming concepts, debugging student code, and suggesting optimal solutions.
Use Case Example:
"Guided a student through building a PyTorch ML model, explaining layers, debugging tensor errors, and suggesting refactors for efficiency."
Metadata
Specification
State
Deprecated
Architecture
Transformer
Calibrated
No
Mixture of Experts
No
Total Parameters
230B
Activated Parameters
230B
Reasoning
No
Precision
FP8
Context length
197K
Max Tokens
131K
Compare with Other Models
See how this model stacks up against others.
MiniMaxAI
chat
MiniMax-M2.5
Release on: Feb 15, 2026
Total Context:
197K
Max output:
131K
Input:
$
0.3
/ M Tokens
Output:
$
1.2
/ M Tokens
MiniMaxAI
chat
MiniMax-M2.1
Release on: Dec 23, 2025
Total Context:
197K
Max output:
131K
Input:
$
0.29
/ M Tokens
Output:
$
1.2
/ M Tokens
MiniMaxAI
chat
MiniMax-M2
Release on: Oct 28, 2025
Total Context:
197K
Max output:
131K
Input:
$
0.3
/ M Tokens
Output:
$
1.2
/ M Tokens
MiniMaxAI
chat
MiniMax-M1-80k
Release on: Jun 17, 2025
Total Context:
131K
Max output:
131K
Input:
$
0.55
/ M Tokens
Output:
$
2.2
/ M Tokens
