Enum ReasoningEffort 

pub enum ReasoningEffort {
    None,
    Minimal,
    Low,
    Medium,
    High,
    XHigh,
    Max,
}

Effort levels available for reasoning-focused models.

The ladder is ordered from least to most reasoning, and spans the union of what the providers accept. No provider accepts every level, and the supported set varies by model within a provider, so each provider crate maps this to its own wire vocabulary and rejects a level its API does not have — rather than silently clamping to the nearest one, which would bill the caller for a depth they did not ask for.

Deliberately carries no as_str: the wire spelling is not shared. Minimal is "minimal" on OpenAI and Gemini and does not exist on Claude; XHigh and Max exist on Claude and OpenAI but not Gemini.

Variants

None

No reasoning at all: answer directly.

On Claude this disables thinking, which the API rejects on models whose thinking is always on.

Minimal

The least reasoning a model will do while still reasoning.

Low

Shallow reasoning, for latency-sensitive work.

Medium

Balanced reasoning depth.

High

Thorough reasoning. The default on current Claude models.

XHigh

Beyond High, where the extra depth pays for itself.

Max

The most reasoning available, for quality-first workloads.

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 Copy for ReasoningEffort

impl Debug for ReasoningEffort

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ReasoningEffort

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for ReasoningEffort

impl Ord for ReasoningEffort

fn cmp(&self, other: &ReasoningEffort) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

where Self: Sized,

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

where Self: Sized,

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

where Self: Sized,

Restrict a value to a certain interval.

fn clamp_to<R>(self, range: R) -> Self

where Self: Sized, R: ClampBounds<Self>,

🔬This is a nightly-only experimental API. (clamp_to)

Restrict a value to a certain range.

impl PartialEq for ReasoningEffort

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

Equality operator ==.

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

Inequality operator !=.

impl PartialOrd for ReasoningEffort

fn partial_cmp(&self, other: &ReasoningEffort) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

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

Tests less than (for self and other) and is used by the < operator.

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

Tests less than or equal to (for self and other) and is used by the <= operator.

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

Tests greater than (for self and other) and is used by the > operator.

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

Tests greater than or equal to (for self and other) and is used by the >= 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