use_thinking flag. use_thinking=True makes the model emit reasoning_content before its answer; use_thinking=False turns it off for a faster, cheaper response. Leaving it unset (None) uses the model default.
thinking_mode.py
Run the Example
1
Set up your virtual environment
2
Install dependencies
3
Export your Xiaomi MiMo API key
4
Run the example
Save the code above as
thinking_mode.py, then run: