Struct Response 

pub struct Response {

    pub background: Option<bool>,
    pub completed_at: Option<f64>,
    pub conversation: Option<Conversation2>,
    pub created_at: f64,
    pub error: ResponseError,
    pub id: String,
    pub incomplete_details: ResponseIncompleteDetails,
    pub instructions: ResponseInstructions,
    pub max_output_tokens: Option<i64>,
    pub max_tool_calls: Option<i64>,
    pub metadata: Metadata,
    pub model: ModelIdsResponses,
    pub object: ResponseObject,
    pub output: Vec<OutputItem>,
    pub output_text: Option<String>,
    pub parallel_tool_calls: bool,
    pub previous_response_id: Option<String>,
    pub prompt: Option<Prompt>,
    pub prompt_cache_key: Option<String>,
    pub prompt_cache_retention: Option<ResponsePromptCacheRetention>,
    pub reasoning: Option<Reasoning>,
    pub safety_identifier: Option<ResponseSafetyIdentifier>,
    pub service_tier: Option<ServiceTier>,
    pub status: Option<ResponseStatus>,
    pub temperature: f64,
    pub text: Option<ResponseTextParam>,
    pub tool_choice: ToolChoiceParam,
    pub tools: ToolsArray,
    pub top_logprobs: Option<i64>,
    pub top_p: f64,
    pub truncation: Option<ResponseTruncation>,
    pub usage: Option<ResponseUsage>,
    pub user: Option<String>,
}

Response

JSON schema

{
 "title": "The response object",
 "allOf": [
   {
     "$ref": "#/components/schemas/ModelResponseProperties"
   },
   {
     "$ref": "#/components/schemas/ResponseProperties"
   },
   {
     "type": "object",
     "required": [
       "created_at",
       "error",
       "id",
       "incomplete_details",
       "instructions",
       "metadata",
       "model",
       "object",
       "output",
       "parallel_tool_calls",
       "temperature",
       "tool_choice",
       "tools",
       "top_p"
     ],
     "properties": {
       "completed_at": {
         "anyOf": [
           {
             "description": "Unix timestamp (in seconds) of when this Response was completed.\nOnly present when the status is `completed`.\n",
             "type": "number",
             "format": "unixtime"
           }
         ]
       },
       "conversation": {
         "anyOf": [
           {
             "$ref": "#/components/schemas/Conversation-2"
           }
         ]
       },
       "created_at": {
         "description": "Unix timestamp (in seconds) of when this Response was created.\n",
         "type": "number",
         "format": "unixtime"
       },
       "error": {
         "$ref": "#/components/schemas/ResponseError"
       },
       "id": {
         "description": "Unique identifier for this Response.\n",
         "type": "string"
       },
       "incomplete_details": {
         "anyOf": [
           {
             "description": "Details about why the response is incomplete.\n",
             "type": "object",
             "properties": {
               "reason": {
                 "description": "The reason why the response is incomplete.",
                 "type": "string",
                 "enum": [
                   "max_output_tokens",
                   "content_filter"
                 ]
               }
             }
           }
         ]
       },
       "instructions": {
         "anyOf": [
           {
             "description": "A system (or developer) message inserted into the model's context.\n\nWhen using along with `previous_response_id`, the instructions from a previous\nresponse will not be carried over to the next response. This makes it simple\nto swap out system (or developer) messages in new responses.\n",
             "oneOf": [
               {
                 "description": "A text input to the model, equivalent to a text input with the\n`developer` role.\n",
                 "type": "string"
               },
               {
                 "title": "Input item list",
                 "description": "A list of one or many input items to the model, containing\ndifferent content types.\n",
                 "type": "array",
                 "items": {
                   "$ref": "#/components/schemas/InputItem"
                 }
               }
             ]
           }
         ]
       },
       "max_output_tokens": {
         "anyOf": [
           {
             "description": "An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning).\n",
             "type": "integer"
           }
         ]
       },
       "object": {
         "description": "The object type of this resource - always set to `response`.\n",
         "type": "string",
         "enum": [
           "response"
         ],
         "x-stainless-const": true
       },
       "output": {
         "description": "An array of content items generated by the model.\n\n- The length and order of items in the `output` array is dependent\n  on the model's response.\n- Rather than accessing the first item in the `output` array and\n  assuming it's an `assistant` message with the content generated by\n  the model, you might consider using the `output_text` property where\n  supported in SDKs.\n",
         "type": "array",
         "items": {
           "$ref": "#/components/schemas/OutputItem"
         }
       },
       "output_text": {
         "anyOf": [
           {
             "description": "SDK-only convenience property that contains the aggregated text output\nfrom all `output_text` items in the `output` array, if any are present.\nSupported in the Python and JavaScript SDKs.\n",
             "type": "string",
             "x-oaiSupportedSDKs": [
               "python",
               "javascript"
             ]
           }
         ]
       },
       "parallel_tool_calls": {
         "description": "Whether to allow the model to run tool calls in parallel.\n",
         "type": "boolean"
       },
       "status": {
         "description": "The status of the response generation. One of `completed`, `failed`,\n`in_progress`, `cancelled`, `queued`, or `incomplete`.\n",
         "type": "string",
         "enum": [
           "completed",
           "failed",
           "in_progress",
           "cancelled",
           "queued",
           "incomplete"
         ]
       },
       "usage": {
         "$ref": "#/components/schemas/ResponseUsage"
       }
     }
   }
 ]
}

Fields

background: Option<bool>

completed_at: Option<f64>

conversation: Option<Conversation2>

created_at: f64

Unix timestamp (in seconds) of when this Response was created.

error: ResponseError

id: String

Unique identifier for this Response.

incomplete_details: ResponseIncompleteDetails

instructions: ResponseInstructions

max_output_tokens: Option<i64>

max_tool_calls: Option<i64>

metadata: Metadata

model: ModelIdsResponses

object: ResponseObject

The object type of this resource - always set to response.

output: Vec<OutputItem>

An array of content items generated by the model.

• The length and order of items in the output array is dependent on the model’s response.
• Rather than accessing the first item in the output array and assuming it’s an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.

output_text: Option<String>

parallel_tool_calls: bool

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

previous_response_id: Option<String>

prompt: Option<Prompt>

prompt_cache_key: Option<String>

Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.

prompt_cache_retention: Option<ResponsePromptCacheRetention>

reasoning: Option<Reasoning>

safety_identifier: Option<ResponseSafetyIdentifier>

A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.

service_tier: Option<ServiceTier>

status: Option<ResponseStatus>

The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.

temperature: f64

text: Option<ResponseTextParam>

tool_choice: ToolChoiceParam

tools: ToolsArray

top_logprobs: Option<i64>

top_p: f64

truncation: Option<ResponseTruncation>

usage: Option<ResponseUsage>

user: Option<String>

This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

Trait Implementations

impl Clone for Response

fn clone(&self) -> Response

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Response

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Response

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Response

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

where __S: Serializer,

Serialize this value into the given Serde serializer.