OpenAI::ReasoningEffortEnum1
Inherits Enum < Comparable < Value < Object
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
Constants
Constructors
Instance methods
Serializes this enum member by name.
For non-flags enums, the serialization is a JSON string. The value is the
member name (see #to_s) transformed with String#underscore.
enum Stages
INITIAL
SECOND_STAGE
end
Stages::INITIAL.to_json # => %("initial")
Stages::SECOND_STAGE.to_json # => %("second_stage")
For flags enums, the serialization is a JSON array including every flagged
member individually serialized in the same way as a member of a non-flags enum.
None is serialized as an empty array, All as an array containing
all members.
@[Flags]
enum Sides
LEFT
RIGHT
end
Sides::LEFT.to_json # => %(["left"])
(Sides::LEFT | Sides::RIGHT).to_json # => %(["left","right"])
Sides::All.to_json # => %(["left","right"])
Sides::None.to_json # => %([])
ValueConverter.to_json offers a different serialization strategy based on the
member value.