Controls which reasoning items are rendered back to the model on later turns. If omitted or set to auto, the model determines the context mode. The gpt-5.6 model family defaults to all_turns; earlier models default to current_turn.

When returned on a response, this is the effective reasoning context mode used for the response.

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

Deprecated: use summary instead.

A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model’s reasoning process. One of auto, concise, or detailed.

Controls the reasoning execution mode for the request.

When returned on a response, this is the effective execution mode.

A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model’s reasoning process. One of auto, concise, or detailed.

concise is supported for computer-use-preview models and all reasoning models after gpt-5.