Struct ChatRequest 

pub struct ChatRequest {

    pub messages: Vec<Message>,
    pub model: Option<String>,
    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub n: Option<i32>,
    pub stream: Option<bool>,
    pub stream_options: Option<StreamOptions>,
    pub stop: Option<Vec<String>>,
    pub max_completion_tokens: Option<i32>,
    pub max_tokens: Option<i32>,
    pub presence_penalty: Option<f32>,
    pub frequency_penalty: Option<f32>,
    pub logit_bias: Option<Value>,
    pub logprobs: Option<bool>,
    pub top_logprobs: Option<i32>,
    pub user: Option<String>,
    pub response_format: Option<ResponseFormat>,
    pub seed: Option<i32>,
    pub tools: Option<Vec<Tool>>,
    pub tool_choice: Option<ToolChoice>,
    pub parallel_tool_calls: Option<bool>,
    pub search_parameters: Option<SearchParameters>,
    pub web_search_options: Option<WebSearchOptions>,
    pub reasoning_effort: Option<String>,
    pub deferred: Option<bool>,
    pub bootstrap_host: Option<String>,
    pub bootstrap_room: Option<i64>,
}

The chat request body for /v1/chat/completions endpoint.

Fields

messages: Vec<Message>

A list of messages that make up the chat conversation.

model: Option<String>

Model name for the model to use.

temperature: Option<f32>

What sampling temperature to use, between 0 and 2.

top_p: Option<f32>

An alternative to sampling with temperature, called nucleus sampling.

n: Option<i32>

How many chat completion choices to generate for each input message.

stream: Option<bool>

If set, partial message deltas will be sent as server-sent events.

stream_options: Option<StreamOptions>

Options for streaming response.

stop: Option<Vec<String>>

(Not supported by reasoning models) Up to 4 sequences where the API will stop generating.

max_completion_tokens: Option<i32>

An upper bound for the number of tokens that can be generated for a completion.

max_tokens: Option<i32>

[DEPRECATED] The maximum number of tokens that can be generated.

presence_penalty: Option<f32>

(Not supported by grok-3 and reasoning models) Presence penalty.

frequency_penalty: Option<f32>

(Not supported by reasoning models) Frequency penalty.

logit_bias: Option<Value>

(Unsupported) A JSON object that maps tokens to an associated bias value.

logprobs: Option<bool>

Whether to return log probabilities of the output tokens.

top_logprobs: Option<i32>

Number of most likely tokens to return at each token position.

user: Option<String>

A unique identifier representing your end-user.

response_format: Option<ResponseFormat>

An object specifying the format that the model must output.

seed: Option<i32>

If specified, system will make a best effort to sample deterministically.

tools: Option<Vec<Tool>>

A list of tools the model may call.

tool_choice: Option<ToolChoice>

Controls which (if any) tool is called by the model.

parallel_tool_calls: Option<bool>

If set to false, the model can perform maximum one tool call.

search_parameters: Option<SearchParameters>

Set the parameters to be used for searched data.

web_search_options: Option<WebSearchOptions>

Options to control the web search.

reasoning_effort: Option<String>

Constrains how hard a reasoning model thinks before responding.

deferred: Option<bool>

If set to true, the request returns a request_id for deferred completion.

bootstrap_host: Option<String>

(Internal) Bootstrap host address for disaggregated prefill/decode.

bootstrap_room: Option<i64>

(Internal) Bootstrap room ID for disaggregated prefill/decode.

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 Default for ChatRequest

fn default() -> ChatRequest

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ChatRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ChatRequest

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

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.

impl StructuralPartialEq for ChatRequest