Enum ReasoningEffort 

#[non_exhaustive]
pub enum ReasoningEffort {
    None,
    Minimal,
    Low,
    Medium,
    High,
    Xhigh,
}

Defines the level of reasoning effort the model should apply

This enum controls how much computational effort the model invests in reasoning through complex problems before generating a response.

Model Support

Model	Supported Values
GPT-5.2, GPT-5.2-pro	none, low, medium, high, xhigh
GPT-5.1	none, low, medium, high
GPT-5-mini	minimal, medium, high
o1, o3, o4 series	low, medium, high

API Reference

Corresponds to the reasoning.effort parameter in the OpenAI Responses API.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

None

No reasoning tokens - fastest response (GPT-5.1/5.2 default)

Use this when you don’t need reasoning capabilities and want the fastest possible response time.

Minimal

Minimal reasoning effort - fastest response time

Use this for simple queries that don’t require deep analysis.

Low

Low reasoning effort - balanced performance

Use this for moderately complex queries that benefit from some reasoning.

Medium

Medium reasoning effort - comprehensive analysis

Use this for complex queries that require thorough consideration.

High

High reasoning effort - maximum thoughtfulness

Use this for very complex queries requiring deep, careful analysis.

Xhigh

Extra-high reasoning effort - quality-critical work (GPT-5.2 only)

Use this for the most demanding tasks requiring maximum reasoning quality. Only available on GPT-5.2 and GPT-5.2-pro models.

Trait Implementations

impl Clone for ReasoningEffort

fn clone(&self) -> ReasoningEffort

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ReasoningEffort

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Display for ReasoningEffort

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl FromStr for ReasoningEffort

type Err = ParseError

The associated error which can be returned from parsing.

fn from_str(s: &str) -> Result<ReasoningEffort, <Self as FromStr>::Err>

Parses a string s to return a value of this type.

impl PartialEq for ReasoningEffort

fn eq(&self, other: &ReasoningEffort) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl Serialize for ReasoningEffort

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ReasoningEffort

impl TryFrom<&str> for ReasoningEffort

type Error = ParseError

The type returned in the event of a conversion error.

fn try_from(s: &str) -> Result<ReasoningEffort, <Self as TryFrom<&str>>::Error>

Performs the conversion.