Back to Models
minimax/minimax-m2-5
Not Available
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 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.
2/12/2026
196,608 tokens
Specifications
Modalities
Input
text
Output
text
Supported Parameters
frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
parallel_tool_calls
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p
Max Output Tokens
65,536Reasoning Configuration
- Default
- Thinking on
- Turning thinking off
- Not possible (always thinks)
Frequently asked questions
- Is MiniMax M2.5 available on FastMetal?
- Not at the moment. MiniMax M2.7, from the same lab, is available on the FastMetal API today.
- What is the context window of MiniMax M2.5?
- 196,608 tokens, shared between the prompt and the response.