Minimax M2.1
Minimax builds Minimax M 2.1, a chat model exceling at code generation and reasoning, with a notable context window of 196,608 tokens. It delivers strong performance in certain benchmarks, such as the Intelligence Index, MMLU-Pro, LiveCodeBench, and HLE, where it ranks in the top 25% or better.
Input
Output
Context
205K
Max Output
8K
Parameters
228.7B
Technical Specifications
Model TypeChat
Context Window204,800 tokens
Max Output Tokens8,192 tokens
Parameters228.7B
Release DateDec 20, 2025
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
23.2%
HLE
66.3%
AA-LCR
83.0%
GPQA
85.4%
Tau2-Bench
82.7%
AIME 2025
69.9%
IFBench
40.7%
SciCode
87.5%
MMLU Pro
82.7
Math
81.0%
LiveCodeBench
32.1
Intelligence
28.8%
Terminal-Bench Hard
Estimated GPU Requirements for Minimax M2.1
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Minimax
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 28, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.