Reasoning interface

gpt-5 and o-series models only Configuration options for reasoning models.

Properties

context
effort
generate_summary
mode	Controls the reasoning execution mode for the request. When returned on a response, this is the effective execution mode.
summary

context?: "auto" | "current_turn" | "all_turns"

"auto" | "current_turn" | "all_turns"

effort?: ReasoningEffort

generate_summary?: "auto" | "concise" | "detailed"

"auto" | "concise" | "detailed"

Controls the reasoning execution mode for the request. When returned on a response, this is the effective execution mode.

mode?: string

string

summary?: "auto" | "concise" | "detailed"

"auto" | "concise" | "detailed"