Struct CreateResponse

pub struct CreateResponse {

    pub input: Input,
    pub model: String,
    pub include: Option<Vec<String>>,
    pub instructions: Option<String>,
    pub max_output_tokens: Option<u32>,
    pub metadata: Option<HashMap<String, String>>,
    pub parallel_tool_calls: Option<bool>,
    pub previous_response_id: Option<String>,
    pub reasoning: Option<ReasoningConfig>,
    pub service_tier: Option<ServiceTier>,
    pub store: Option<bool>,
    pub temperature: Option<f32>,
    pub text: Option<TextConfig>,
    pub tool_choice: Option<ToolChoice>,
    pub tools: Option<Vec<ToolDefinition>>,
    pub top_p: Option<f32>,
    pub truncation: Option<Truncation>,
    pub user: Option<String>,
}

Builder for a Responses API request.

Fields

input: Input

Text, image, or file inputs to the model, used to generate a response.

model: String

Model ID used to generate the response, like gpt-4o. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points.

include: Option<Vec<String>>

Specify additional output data to include in the model response.

Supported values:

• file_search_call.results Include the search results of the file search tool call.
• message.input_image.image_url Include image URLs from the input message.
• computer_call_output.output.image_url Include image URLs from the computer call output.
• reasoning.encrypted_content Include an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (for example, when the store parameter is set to false, or when an organization is enrolled in the zero-data- retention program).

If None, no additional data is returned.

instructions: Option<String>

Inserts a system (or developer) message as the first item in the model’s context.

When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

max_output_tokens: Option<u32>

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

metadata: Option<HashMap<String, String>>

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

parallel_tool_calls: Option<bool>

Whether to allow the model to run tool calls in parallel.

previous_response_id: Option<String>

The unique ID of the previous response to the model. Use this to create multi-turn conversations.

reasoning: Option<ReasoningConfig>

o-series models only: Configuration options for reasoning models.

service_tier: Option<ServiceTier>

Specifies the latency tier to use for processing the request.

This parameter is relevant for customers subscribed to the Scale tier service.

Supported values:

• auto
  • If the Project is Scale tier enabled, the system will utilize Scale tier credits until they are exhausted.
  • If the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee.
• default The request will be processed using the default service tier with a lower uptime SLA and no latency guarantee.
• flex The request will be processed with the Flex Processing service tier. Learn more.

When not set, the default behavior is auto.

When this parameter is set, the response body will include the service_tier utilized.

store: Option<bool>

Whether to store the generated model response for later retrieval via API.

temperature: Option<f32>

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

text: Option<TextConfig>

Configuration options for a text response from the model. Can be plain text or structured JSON data.

tool_choice: Option<ToolChoice>

How the model should select which tool (or tools) to use when generating a response.

tools: Option<Vec<ToolDefinition>>

An array of tools the model may call while generating a response. Can include built-in tools (file_search, web_search_preview, computer_use_preview) or custom function definitions.

top_p: Option<f32>

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

truncation: Option<Truncation>

The truncation strategy to use for the model response:

• auto: drop items in the middle to fit context window.
• disabled: error if exceeding context window.

user: Option<String>

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

Trait Implementations

impl Clone for CreateResponse

fn clone(&self) -> CreateResponse

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for CreateResponse

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

Formats the value using the given formatter.

impl Default for CreateResponse

fn default() -> CreateResponse

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for CreateResponse

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for CreateResponse

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

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 CreateResponse