Struct ChatRequest 

pub struct ChatRequest {
    pub model: String,
    pub messages: Vec<ChatMessage>,
    pub temperature: Option<f32>,
    pub max_tokens: Option<u32>,
    pub stream: Option<bool>,
    pub tools: Option<Vec<Value>>,
    pub top_p: Option<f32>,
    pub frequency_penalty: Option<f32>,
    pub presence_penalty: Option<f32>,
    pub reasoning_effort: Option<String>,
}

A chat completion request

Fields

model: String

The model to use for completion

messages: Vec<ChatMessage>

The conversation messages

temperature: Option<f32>

Sampling temperature (0.0 to 2.0)

max_tokens: Option<u32>

Maximum number of tokens to generate

stream: Option<bool>

Whether to stream the response

tools: Option<Vec<Value>>

Tools available for the model to call

top_p: Option<f32>

Top-p sampling parameter

frequency_penalty: Option<f32>

Frequency penalty (-2.0 to 2.0).

⚠ Not supported by reasoning models (Grok 4, Grok 4.20 variants). Sending this field to a reasoning model will result in an API error.

presence_penalty: Option<f32>

Presence penalty (-2.0 to 2.0).

⚠ Not supported by reasoning models (Grok 4, Grok 4.20 variants). Sending this field to a reasoning model will result in an API error.

reasoning_effort: Option<String>

Reasoning effort level for models that support extended thinking. Valid values: "low", "medium", "high". Only send this for models that support it (e.g. grok-4.3, grok-3-mini). Sending it to unsupported models returns an API error.

Trait Implementations

impl Clone for ChatRequest

fn clone(&self) -> ChatRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChatRequest

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

Formats the value using the given formatter.

impl Serialize for ChatRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.