Minimax 2.1
MinimaxCompact
ThinkingTool Use
About this model
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
Performance Tier
Compact
Minimax 2.1 is a compact model from Minimax : optimized for speed and affordability.
Small, fast, and affordable. Optimized for speed and low cost, great for high-volume or simple tasks.
Pricing
This model is included in Elosia plansAffordable
Low cost. Suitable for sustained use and high-volume interactions.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.300 |
| Output (completion) | $1.20 |
| Cache read | $0.030 |
Capabilities
Context Length205K
Max Output Tokens131K
TokenizerOther
Inputtext
Outputtext
Release DateDecember 23, 2025
Benchmarks
General Intelligence
MMLU
80%
Mathematics
MATH-500
70%
AIME 2025
81%
Programming
HumanEval
78%
Reasoning
Humanity's Last Exam
22%
Where does Minimax 2.1 stand?
Compare its performance index against every other model.
Recommended Use Cases
General ChatCreative WritingSummarization
Strengths
- Good general-purpose model with strong creative abilities
- Competitive pricing for its capability level
- Supports long context for document analysis
Limitations
- Less well-known with smaller community and ecosystem
- Limited documentation and integration options
Frequently asked questions
Resources
This model may use your data for training
