Struct ChatCompletionRequest 

pub struct ChatCompletionRequest {

    pub model: String,
    pub messages: Vec<ChatMessage>,
    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub max_tokens: Option<u32>,
    pub max_completion_tokens: Option<u32>,
    pub stream_options: Option<Value>,
    pub stream: Option<bool>,
    pub tools: Option<Vec<ToolDefinition>>,
    pub parallel_tool_calls: Option<bool>,
    pub tool_choice: Option<Value>,
    pub response_format: Option<Value>,
    pub stop: Option<Vec<String>>,
    pub presence_penalty: Option<f32>,
    pub frequency_penalty: Option<f32>,
    pub seed: Option<i64>,
    pub user: Option<String>,
}

Request payload for /chat/completions.

Fields

model: String

Model ID to query (e.g. gpt-4o-mini, anthropic/claude-3.5-sonnet).

messages: Vec<ChatMessage>

List of conversation messages.

temperature: Option<f32>

Sampling temperature between 0.0 and 2.0.

top_p: Option<f32>

Nucleus sampling probability cutoff (top-p).

max_tokens: Option<u32>

Maximum number of tokens to generate in the completion.

max_completion_tokens: Option<u32>

Upper bound on completion tokens, used by reasoning models (e.g. o1/o3).

stream_options: Option<Value>

Options for streaming responses, such as requesting token usage.

stream: Option<bool>

Whether to stream back partial progress via Server-Sent Events.

tools: Option<Vec<ToolDefinition>>

List of tools available to the model.

parallel_tool_calls: Option<bool>

Whether to enable parallel function calling during tool use.

tool_choice: Option<Value>

Tool choice policy (none, auto, required, or specific function).

response_format: Option<Value>

Output formatting requirement (e.g. {"type": "json_object"}).

stop: Option<Vec<String>>

Up to 4 sequences where the API will stop generating tokens.

presence_penalty: Option<f32>

Presence penalty between -2.0 and 2.0.

frequency_penalty: Option<f32>

Frequency penalty between -2.0 and 2.0.

seed: Option<i64>

Random seed for deterministic generation if supported by provider.

user: Option<String>

Optional end-user identifier for abuse detection.

Implementations

impl ChatCompletionRequest

pub fn new(model: impl Into<String>, messages: Vec<ChatMessage>) -> Self

Create a new chat completion request with required model and messages.

pub fn temperature(self, temperature: f32) -> Self

Set sampling temperature.

pub fn top_p(self, top_p: f32) -> Self

Set nucleus sampling probability.

pub fn max_tokens(self, max_tokens: u32) -> Self

Set maximum tokens to generate.

pub fn max_completion_tokens(self, max_completion_tokens: u32) -> Self

Set maximum completion tokens for reasoning models (e.g. o1/o3).

pub fn include_usage(self) -> Self

Request token usage statistics in the final streaming chunk.

pub fn stream(self, stream: bool) -> Self

Set streaming flag.

pub fn tools(self, tools: Vec<ToolDefinition>) -> Self

Attach tool definitions, omitting the parameter if empty.

pub fn parallel_tool_calls(self, parallel: bool) -> Self

Set whether parallel function calling is allowed during tool execution.

pub fn stop(self, stop: Vec<String>) -> Self

Set stop sequences.

pub fn stop_sequence(self, stop: impl Into<String>) -> Self

Append a single stop sequence to the request.

pub fn json_mode(self) -> Self

Set response format to JSON object ({"type": "json_object"}).

pub fn presence_penalty(self, presence_penalty: f32) -> Self

Set presence penalty between -2.0 and 2.0.

pub fn frequency_penalty(self, frequency_penalty: f32) -> Self

Set frequency penalty between -2.0 and 2.0.

pub fn seed(self, seed: i64) -> Self

Set random seed for deterministic sampling.

pub fn user(self, user: impl Into<String>) -> Self

Set end-user identifier.

pub fn tool_choice(self, tool_choice: Value) -> Self

Set tool choice policy (none, auto, required, or specific function).

pub fn response_format(self, response_format: Value) -> Self

Set arbitrary response format requirement.

Trait Implementations

impl Clone for ChatCompletionRequest

fn clone(&self) -> ChatCompletionRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChatCompletionRequest

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ChatCompletionRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ChatCompletionRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.