Struct Request 

pub struct Request {

    pub model: String,
    pub input: Vec<OutputItem>,
    pub tools: Option<Vec<ToolDefinition>>,
    pub tool_choice: Option<ToolChoice>,
    pub stream: bool,
    pub temperature: Option<f64>,
    pub top_p: Option<f64>,
    pub truncation: Option<Box<TruncationConfig>>,
    pub max_output_tokens: Option<u64>,
    pub max_tool_calls: Option<u64>,
    pub stop: Option<Vec<String>>,
    pub presence_penalty: Option<f64>,
    pub frequency_penalty: Option<f64>,
    pub logit_bias: Option<HashMap<String, f64>>,
    pub logprobs: Option<bool>,
    pub top_logprobs: Option<u32>,
    pub user: Option<String>,
    pub service_tier: Option<String>,
    pub reasoning: Option<Box<ReasoningConfig>>,
    pub store: Option<bool>,
    pub previous_response_id: Option<String>,
    pub include: Option<Vec<String>>,
    pub metadata: Option<Value>,
}

The main request object per the Open Responses specification.

Fields

model: String

The model to use for the request.

input: Vec<OutputItem>

The input items that form the context for the model. Per the spec, these are polymorphic items (messages, tool outputs, etc.).

tools: Option<Vec<ToolDefinition>>

Tools available to the model.

tool_choice: Option<ToolChoice>

Tool choice parameter.

stream: bool

Whether to stream the response.

temperature: Option<f64>

Sampling temperature.

top_p: Option<f64>

Nucleus sampling parameter.

truncation: Option<Box<TruncationConfig>>

Truncation configuration.

max_output_tokens: Option<u64>

Maximum output tokens allowed.

max_tool_calls: Option<u64>

Maximum tool calls allowed in a single request.

stop: Option<Vec<String>>

Stop sequences for the model.

presence_penalty: Option<f64>

Presence penalty.

frequency_penalty: Option<f64>

Frequency penalty.

logit_bias: Option<HashMap<String, f64>>

Logit bias for token sampling.

logprobs: Option<bool>

Whether to return log probabilities.

top_logprobs: Option<u32>

Number of top log probabilities to return.

user: Option<String>

User ID for tracking and rate limiting.

service_tier: Option<String>

Service tier requested.

reasoning: Option<Box<ReasoningConfig>>

Reasoning configuration.

store: Option<bool>

Whether to store the request/response.

previous_response_id: Option<String>

Optional ID of the previous response for server-side continuity.

include: Option<Vec<String>>

Optional response fields to include.

metadata: Option<Value>

Metadata for the request.

Implementations

impl Request

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

Creates a new request with the given model and input.

pub fn from_message(model: impl Into<String>, text: impl Into<String>) -> Self

Convenience method to create a request from a single user message.

Trait Implementations

impl Clone for Request

fn clone(&self) -> Request

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Request

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Request

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Request

fn eq(&self, other: &Request) -> 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 Request

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 Request