By means of the system prompt in theReasoning: highparameter configurations that significantly increase the transparency of the model's reasoning process. At high reasoning levels, the model displays the complete Chain-of-Thought, producing 40% more explanatory content than the base model. This is especially important for scenarios such as academic research and complex problem solving, and supports the use of the model through theReasoning languageThe parameter specifies the output language to enable cross-language knowledge inference.
This answer comes from the articleCollection of scripts and tutorials for fine-tuning OpenAI GPT OSS modelsThe
May not be reproduced without permission:AI productivity tools " Inference level settings affect the level of detail of model outputs
