Minimax M2.7
Minimax M 2.7, developed by Minimax, is a chat model exceling at code generation and reasoning, with a notable context window of 204,800 tokens. It demonstrates strong capabilities in professional software engineering, including log analysis, bug troubleshooting, and system-level reasoning.
Input
Output
Context
205K
Max Output
197K
Parameters
228.7B
Technical Specifications
Model TypeChat
Context Window204,800 tokens
Max Output Tokens196,608 tokens
Parameters228.7B
Release DateApr 9, 2026
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
28.1%
HLE
68.7%
AA-LCR
87.4%
GPQA
84.8%
Tau2-Bench
75.7%
IFBench
47.0%
SciCode
8.9%
Tau2 Banking
52.6
Coding
38.1
Intelligence
39.4%
Terminal-Bench Hard
55.4%
Terminal-Bench 2.1
Estimated GPU Requirements for Minimax M2.7
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 8, 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.