ai_optimization/chat_gpt/llm_responses/task_get

Get Chat GPT LLM Responses

‌
Chat GPT LLM Responses endpoint allows you to retrieve structured responses from a specific Chat GPT model, based on the input parameters.

Tasks using the Standard method may take up to 72 hours to complete. If the task is not completed within this time, it is marked as failed, and the $0.01 advance is refunded. It is also important to note that if your account balance is negative, you will not receive the results even if the task is completed successfully.

GET

Your account will be charged only for posting a task. You can get the results of the task within the next 30 days for free.
The cost can be calculated on the Pricing page.

Description of the fields for sending a request:

Field name	Type	Description
`id`	string	task identifier unique task identifier in our system in the UUID format you will be able to use it within 30 days to request the results of the task at any time

‌
As a response of the API server, you will receive JSON-encoded data containing a tasks array with the information specific to the set tasks.

Description of the fields in the results array:

Field name	Type	Description
`version`	string	the current version of the API
`status_code`	integer	general status code you can find the full list of the response codes here Note: we strongly recommend designing a necessary system for handling related exceptional or error conditions
`status_message`	string	general informational message you can find the full list of general informational messages here
`time`	string	execution time, seconds
`cost`	float	total tasks cost, USD
`tasks_count`	integer	the number of tasks in the `tasks`* array*
`tasks_error`	integer	the number of tasks in the `tasks`* array returned with an error*
`tasks`	array	array of tasks
`id`	string	task identifier unique task identifier in our system in the UUID format
`status_code`	integer	status code of the task generated by DataForSEO; can be within the following range: 10000-60000 you can find the full list of the response codes here
`status_message`	string	informational message of the task you can find the full list of general informational messages here
`time`	string	execution time, seconds
`cost`	float	cost of the task, USD includes the base task price plus the `money_spent` value
`result_count`	integer	number of elements in the `result` array
`path`	array	URL path
`data`	object	contains the same parameters that you specified in the POST request
`result`	array	array of results
`model_name`	string	name of the AI model used
`input_tokens`	integer	number of tokens in the input total count of tokens processed
`output_tokens`	integer	number of tokens in the output total count of tokens generated in the AI response
`reasoning_tokens`	integer	number of reasoning tokens total count of tokens used to generate reasoning content
`web_search`	boolean	indicates if web search was used
`money_spent`	float	cost of AI tokens, USD the price charged by the third-party AI model provider for according to its Pricing
`datetime`	string	date and time when the result was received in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00” example: `2019-11-15 12:57:46 +00:00`
`items`	array	array of response items contains structured AI response data
`reasoning`	object	element in the response
`type`	string	type of the element = 'reasoning' Note: this element is supported only in reasoning models and is not guaranteed to be returned
`sections`	array	reasoning chain sections array of objects containing the reasoning chain sections generated by the LLM
`type`	string	type of element='summary_text'
`text`	string	text of the reasoning chain section text of the reasoning chain section summarizing the model's thought process
`message`	object	element in the response
`type`	string	type of the element = 'message'
`sections`	array	array of content sections contains different parts of the AI response
`type`	string	type of element='text'
`text`	string	AI-generated text content
`annotations`	array	array of references used to generate the response equals `null` if the `web_search` parameter is not set to `true` Note: `annotations` may return empty even when `web_search` is `true`, as the AI will attempt to retrieve web information but may not find relevant results
`title`	string	the domain name or title of the quoted source
`url`	string	URL of the quoted source
`start_index`	integer	start of the annotation indexing
`end_index`	integer	end of the annotation indexing
`text`	string	annotated part of the quoted source
`fan_out_queries`	array	array of fan-out queries contains related search queries derived from the main query to provide a more comprehensive response

‌‌

Instead of ‘login’ and ‘password’ use your credentials from https://app.dataforseo.com/api-access

# Instead of 'login' and 'password' use your credentials from https://app.dataforseo.com/api-access 
login="login" 
password="password" 
cred="$(printf ${login}:${password} | base64)" 
id="02031608-0696-0110-0000-a81d0414edbe" 
curl --location --request GET "https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/task_get/${id}" 
--header "Authorization: Basic ${cred}"  
--header "Content-Type: application/json" 
--data-raw ""

<?php

/**
 * Method: GET
 * Endpoint: https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/task_get/$id
 * @see https://docs.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/task_get
 */

require_once __DIR__ . '/../../../../../lib/RestClient.php';
$config = require __DIR__ . '/../../../../../lib/config.php';

$client = new RestClient($config['base_url'], null, $config['login'], $config['password']);

try {
    $taskId = '07211938-0696-0613-0000-674a0f948d6b';
    $result = $client->get("/v3/ai_optimization/chat_gpt/llm_responses/task_get/{$taskId}");
    print_r($result);
    // do something with get result
} catch (RestClientException $e) {
    printf(
        "HTTP code: %dnError code: %dnMessage: %snTrace: %sn",
        $e->getHttpCode(),
        $e->getCode(),
        $e->getMessage(),
        $e->getTraceAsString()
    );
}

?>

const task_id = '02231934-2604-0066-2000-570459f04879';

const axios = require('axios');

axios({
    method: 'get',
    url: 'https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/task_get/' + task_id,
    auth: {
        username: 'login',
        password: 'password'
    },
    headers: {
        'content-type': 'application/json'
    }
}).then(function (response) {
    var result = response['data']['tasks'];
    // Result data
    console.log(result);
}).catch(function (error) {
    console.log(error);
});

"""
Method: GET
Endpoint: https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/task_get/$id
@see https://docs.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/task_get
"""

import sys
import os
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../../../../../')))
from lib.client import RestClient
from lib.config import username, password
client = RestClient(username, password)

try:
    task_id = '07211938-0696-0613-0000-674a0f948d6b'
    response = client.get(f'/v3/ai_optimization/chat_gpt/llm_responses/task_get/{task_id}')
    print(response)
    # do something with get result
except Exception as e:
    print(f'An error occurred: {e}')

using System;
using System.Linq;
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text;
using System.Collections.Generic;
using System.Threading.Tasks;
using Newtonsoft.Json;
namespace DataForSeoSdk;

public class AiOptimization
{

    private static readonly HttpClient _httpClient;
    
    static AiOptimization()
    {
        _httpClient = new HttpClient
        {
            BaseAddress = new Uri("https://api.dataforseo.com/")
        };
        _httpClient.DefaultRequestHeaders.Authorization =
            new AuthenticationHeaderValue("Basic", ApiConfig.Base64Auth);
    }
    
    /// <summary>
    /// Method: GET
    /// Endpoint: https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/task_get
    /// </summary>
    /// <see href="https://docs.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/task_get"/>
    
    public static async Task ChatgptLlmResponsesTaskGetById()
    {
		// use the task identifier that you recieved upon setting a task
	    string taskId = "07211938-0696-0613-0000-674a0f948d6b";
	    using var response = await _httpClient.GetAsync("/v3/ai_optimization/chat_gpt/llm_responses/task_get/" + taskId);
	    var result = JsonConvert.DeserializeObject<dynamic>(await response.Content.ReadAsStringAsync());
	    // you can find the full list of the response codes here https://docs.dataforseo.com/v3/appendix/errors
	    if (result.status_code == 20000)
	    {
	        // do something with result
	        Console.WriteLine(result);
	    }
	    else
	        Console.WriteLine($"error. Code: {result.status_code} Message: {result.status_message}");
    }

The above command returns JSON structured like this:

{
  "version": "0.1.20260717",
  "status_code": 20000,
  "status_message": "Ok.",
  "time": "4.8468 sec.",
  "cost": 0.029631,
  "tasks_count": 1,
  "tasks_error": 0,
  "tasks": [
    {
      "id": "02249714-1807-0791-0000-0423e705a8rr",
      "status_code": 20000,
      "status_message": "Ok.",
      "time": "0.0310 sec.",
      "cost": 0,
      "result_count": 1,
      "path": [
        "v3",
        "ai_optimization",
        "chat_gpt",
        "llm_responses",
        "task_get",
        "07241735-1535-0613-0000-0722e701b5ff"
      ],
      "data": {
        "api": "ai_optimization",
        "function": "llm_responses",
        "se": "chat_gpt",
        "system_message": "communicate as if we are in a business meeting",
        "message_chain": [
          {
            "role": "user",
            "message": "Hello, what's up?"
          },
          {
            "role": "ai",
            "message": "Hello! I’m doing well, thank you. How can I assist you today? Are there any specific topics or projects you’d like to discuss in our meeting?"
          }
        ],
        "temperature": 0.3,
        "top_p": 0.5,
        "web_search_country_iso_code": "FR",
        "web_search_city": "Paris",
        "model_name": "gpt-4.1-mini",
        "web_search": true,
        "user_prompt": "provide information on how relevant the amusement park business is in France now"
      },
      "result": [
        {
          "model_name": "gpt-4.1-mini-2025-04-14",
          "input_tokens": 8174,
          "output_tokens": 476,
          "reasoning_tokens": 0,
          "web_search": true,
          "money_spent": 0.0290312,
          "datetime": "2026-07-22 17:54:30 +00:00",
          "items": [
            {
              "type": "message",
              "sections": [
                {
                  "type": "text",
                  "text": "The amusement park industry in France remains a significant and dynamic sector as of 2024. In 2023, the industry achieved a turnover of approximately €2.5 billion, with major parks like Disneyland Paris, Parc Astérix, Puy du Fou, and Futuroscope accounting for 60% of the total attendance. ([latribune.fr](https://www.latribune.fr/entreprises/tourisme/2024-09-13/entre-creations-et-tensions-le-marche-des-parcs-de-loisirs-en-occitanie-joue-les-montagnes-russes-1006293.html?id=1950717847221315%5C&utm_source=openai))nnNotably, in 2024, Parc Astérix welcomed a record 2.84 million visitors, earning it the title of the best amusement park in France for the third consecutive year. ([ouest-france.fr](https://www.ouest-france.fr/tourisme/le-parc-asterix-est-elu-meilleur-parc-dattractions-de-france-decouvrez-ses-nouveaux-projets-710f3c5a-a5bb-11ef-b03c-14608f7369cf?utm_source=openai)) Similarly, Nigloland attracted 750,000 visitors, placing it among the top five parks in the country. ([parc-attraction-loisirs.fr](https://www.parc-attraction-loisirs.fr/2024/11/12/chiffre-frequentation-2024-nigloland/?utm_source=openai))nnThe Compagnie des Alpes, a leading operator in the sector, reported that its leisure parks generated €570.1 million in revenue in 2023/2024, surpassing the performance of its ski resorts. ([lechotouristique.com](https://www.lechotouristique.com/article/compagnie-des-alpes-pour-la-premiere-fois-les-parcs-de-loisirs-depassent-les-domaines-skiables?utm_source=openai))nnThese developments underscore the continued relevance and growth of the amusement park industry in France, driven by strong consumer demand and ongoing investments in new attractions and experiences. ",
                  "annotations": [
                    {
                      "title": "Entre créations et tensions, le marché des parcs de loisirs en Occitanie joue les montagnes russes",
                      "url": "https://www.latribune.fr/entreprises/tourisme/2024-09-13/entre-creations-et-tensions-le-marche-des-parcs-de-loisirs-en-occitanie-joue-les-montagnes-russes-1006293.html?id=1950717847221315%5C&utm_source=openai",
                      "start_index": 290,
                      "end_index": 516,
                      "text": "([latribune.fr](https://www.latribune.fr/entreprises/tourisme/2024-09-13/entre-creations-et-tensions-le-marche-des-parcs-de-loisirs-en-occitanie-joue-les-montagnes-russes-1006293.html?id=1950717847221315%5C&utm_source=openai))"
                    },
                    {
                      "title": "Le Parc Astérix est élu meilleur parc d’attractions de France : découvrez ses nouveaux projets",
                      "url": "https://www.ouest-france.fr/tourisme/le-parc-asterix-est-elu-meilleur-parc-dattractions-de-france-decouvrez-ses-nouveaux-projets-710f3c5a-a5bb-11ef-b03c-14608f7369cf?utm_source=openai",
                      "start_index": 680,
                      "end_index": 884,
                      "text": "([ouest-france.fr](https://www.ouest-france.fr/tourisme/le-parc-asterix-est-elu-meilleur-parc-dattractions-de-france-decouvrez-ses-nouveaux-projets-710f3c5a-a5bb-11ef-b03c-14608f7369cf?utm_source=openai))"
                    },
                    {
                      "title": "Parc Nigloland : bons chiffres en 2024 et nouveauté annoncée pour 2025",
                      "url": "https://www.parc-attraction-loisirs.fr/2024/11/12/chiffre-frequentation-2024-nigloland/?utm_source=openai",
                      "start_index": 986,
                      "end_index": 1123,
                      "text": "([parc-attraction-loisirs.fr](https://www.parc-attraction-loisirs.fr/2024/11/12/chiffre-frequentation-2024-nigloland/?utm_source=openai))"
                    },
                    {
                      "title": "Compagnie des Alpes : pour la première fois, les parcs de loisirs dépassent les domaines skiables",
                      "url": "https://www.lechotouristique.com/article/compagnie-des-alpes-pour-la-premiere-fois-les-parcs-de-loisirs-depassent-les-domaines-skiables?utm_source=openai",
                      "start_index": 1313,
                      "end_index": 1492,
                      "text": "([lechotouristique.com](https://www.lechotouristique.com/article/compagnie-des-alpes-pour-la-premiere-fois-les-parcs-de-loisirs-depassent-les-domaines-skiables?utm_source=openai))"
                    }
                  ]
                }
              ]
            }
          ],
          "fan_out_queries": [
            "current relevance of amusement park business in France 2024"
          ]
        }
      ]
    }
  ]
}