Enum ThinkingType 

pub enum ThinkingType {
    Enabled,
    Disabled,
}

Controls thinking/reasoning capabilities in AI models.

This enum determines whether a model should engage in step-by-step reasoning when processing requests. Thinking mode can improve accuracy for complex tasks but may increase response time and token usage.

Variants

• Enabled - Model performs explicit reasoning steps before responding
• Disabled - Model responds directly without showing reasoning process

Usage

let client = ChatCompletion::new(model, messages, api_key)
    .with_thinking(ThinkingType::Enabled);

Model Compatibility

Thinking capabilities are available only on models that implement the ThinkEnable trait, such as GLM-4.5 series models.

Variants

Enabled

Enable thinking capabilities for enhanced reasoning.

When enabled, the model will show its reasoning process step-by-step, which can improve accuracy for complex logical or analytical tasks.

Disabled

Disable thinking capabilities for direct responses.

When disabled, the model responds directly without showing intermediate reasoning steps, resulting in faster responses and lower token usage.

Trait Implementations

impl Clone for ThinkingType

fn clone(&self) -> ThinkingType

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ThinkingType

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

Formats the value using the given formatter.

impl Serialize for ThinkingType

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

where __S: Serializer,

Serialize this value into the given Serde serializer.