Live ChatGPT LLM Responses
Live ChatGPT LLM Responses endpoint allows you to retrieve structured responses from a specific Chat GPT AI model, based on the input parameters.
Live ChatGPT LLM Responses endpoint allows you to retrieve structured responses from a specific Chat GPT AI model, based on the input parameters.
Instead of ‘login’ and ‘password’ use your credentials from https://app.dataforseo.com/api-access
<?php // You can download this file from here https://cdn.dataforseo.com/v3/examples/php/php_RestClient.zip require('RestClient.php'); $api_url = 'https://api.dataforseo.com/'; try { // Instead of 'login' and 'password' use your credentials from https://app.dataforseo.com/api-access $client = new RestClient($api_url, null, 'login', 'password'); } catch (RestClientException $e) { echo "n"; print "HTTP code: {$e->getHttpCode()}n"; print "Error code: {$e->getCode()}n"; print "Message: {$e->getMessage()}n"; print $e->getTraceAsString(); echo "n"; exit(); } $post_array = array(); // You can set only one task at a time $post_array[] = array( "system_message" => "communicate as if we are in a business meeting", "message_chain" => [ [ "role" => "user", "message" => "Hello, what’s up?" ], [ "role" => "ai", "message" => "Hello! I’m doing well, thank you. How can I assist you today? Are there any specific topics or projects you’d like to discuss in our meeting?" ] ], "max_output_tokens" => 200, "temperature" => 0.3, "top_p" => 0.5, "model_name" => "gpt-4.1-mini", "web_search" => true, "web_search_country_iso_code" => "FR", "web_search_city" => "Paris", "user_prompt" => "provide information on how relevant the amusement park business is in France now" ); if (count($post_array) > 0) { try { // POST /v3/serp/google/ai_mode/live/advanced // in addition to 'google' and 'ai_mode' you can also set other search engine and type parameters // the full list of possible parameters is available in documentation $result = $client->post('/v3/ai_optimization/chat_gpt/llm_responses/live', $post_array); print_r($result); // do something with post result } catch (RestClientException $e) { echo "n"; print "HTTP code: {$e->getHttpCode()}n"; print "Error code: {$e->getCode()}n"; print "Message: {$e->getMessage()}n"; print $e->getTraceAsString(); echo "n"; } $client = null; ?>
The above command returns JSON structured like this:
{ "version": "0.1.20250526", "status_code": 20000, "status_message": "Ok.", "time": "7.0440 sec.", "cost": 0.0292, "tasks_count": 1, "tasks_error": 0, "tasks": [ { "id": "07171158-1535-0612-0000-edcdefadd850", "status_code": 20000, "status_message": "Ok.", "time": "6.9804 sec.", "cost": 0.0292, "result_count": 1, "path": [ "v3", "ai_optimization", "chat_gpt", "llm_responses", "live" ], "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": 374, "output_tokens": 594, "web_search": true, "money_spent": 0.0286, "datetime": "2025-07-17 11:58:28 +00:00", "items": [ { "type": "message", "sections": [ { "type": "text", "text": "The amusement park industry in France remains a significant contributor to the country's economy and tourism sector. In 2024, the French amusement parks market generated approximately USD 3.25 billion in revenue and is projected to reach USD 4.27 billion by 2030, growing at a compound annual growth rate (CAGR) of 4.4% from 2025 to 2030. ([grandviewresearch.com](https://www.grandviewresearch.com/horizon/outlook/amusement-parks-market/france?utm_source=openai))\n\nFrance is home to several major amusement parks that attract millions of visitors annually. Disneyland Paris, Europe's most visited theme park, welcomed over 375 million visitors by 2022. In 2023, it generated a profit of $343 million for Disney. ([en.wikipedia.org](https://en.wikipedia.org/wiki/Disneyland_Paris?utm_source=openai)) Parc Astérix, another prominent park, achieved a record attendance of over 2.8 million visitors in 2023. ([en.wikipedia.org](https://en.wikipedia.org/wiki/Parc_Ast%C3%A9rix?utm_source=openai)) Le Puy du Fou, known for its historical theme, attracted 2.8 million visitors in 2024, making it the third most visited park in France that year. ([en.wikipedia.org](https://en.wikipedia.org/wiki/Le_Puy_du_Fou?utm_source=openai))\n\nThe industry is also witnessing technological advancements, with parks incorporating augmented reality (AR) and virtual reality (VR) attractions to enhance visitor experiences. Additionally, there is a growing emphasis on sustainability, with parks implementing eco-friendly practices such as recycling programs and energy-efficient operations. ([6wresearch.com](https://www.6wresearch.com/industry-report/france-amusement-park-market-outlook?utm_source=openai))\n\nHowever, the sector faces challenges, including rising operational costs and changing consumer preferences. In 2024, the average price of a hotel night in France increased by 26% since 2019, leading to shorter vacations and a shift towards budget-friendly accommodations. ([lemonde.fr](https://www.lemonde.fr/en/economy/article/2024/10/19/when-vacations-keep-getting-more-expensive_6729824_19.html?utm_source=openai)) Despite these challenges, the amusement park industry in France continues to be a vital and evolving part of the country's tourism landscape.\n\n\n## Rising Costs Impacting French Vacation Habits:\n- [When vacations keep getting more expensive](https://www.lemonde.fr/en/economy/article/2024/10/19/when-vacations-keep-getting-more-expensive_6729824_19.html?utm_source=openai) ", "annotations": [ { "title": "France Amusement Parks Market Size & Outlook, 2030", "url": "https://www.grandviewresearch.com/horizon/outlook/amusement-parks-market/france?utm_source=openai" }, { "title": "Disneyland Paris", "url": "https://en.wikipedia.org/wiki/Disneyland_Paris?utm_source=openai" }, { "title": "Parc Astérix", "url": "https://en.wikipedia.org/wiki/Parc_Ast%C3%A9rix?utm_source=openai" }, { "title": "Le Puy du Fou", "url": "https://en.wikipedia.org/wiki/Le_Puy_du_Fou?utm_source=openai" }, { "title": "France Amusement park Market (2025-2031) | Industry & Revenue", "url": "https://www.6wresearch.com/industry-report/france-amusement-park-market-outlook?utm_source=openai" }, { "title": "When vacations keep getting more expensive", "url": "https://www.lemonde.fr/en/economy/article/2024/10/19/when-vacations-keep-getting-more-expensive_6729824_19.html?utm_source=openai" }, { "title": "When vacations keep getting more expensive", "url": "https://www.lemonde.fr/en/economy/article/2024/10/19/when-vacations-keep-getting-more-expensive_6729824_19.html?utm_source=openai" } ] } ] } ] } ] } ] }
All POST data should be sent in the JSON format (UTF-8 encoding). The task setting is done using the POST method. When setting a task, you should send all task parameters in the task array of the generic POST array. You can send up to 2000 API calls per minute, each Live Chat GPT LLM Responses call can contain only one task.
Execution time for tasks set with the Live Chat GPT LLM Responses endpoint is currently up to 120 seconds.
Below you will find a detailed description of the fields you can use for setting a task.
Description of the fields for setting a task:
Field name | Type | Description |
---|---|---|
user_prompt |
string | prompt for the AI model required field the question or task you want to send to the AI model; you can specify up to 500 characters in the user_prompt field
|
model_name |
string | name of the AI model required field model_name consists of the actual model name and version name;if the basic model name is specified, its latest version will be set by default; for example, if gpt-4.1 is specified, the gpt-4.1-2025-04-14 will be set as model_name automatically;you can receive the list of available LLM models by making a separate request to the https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/models
|
max_output_tokens |
integer | maximum number of tokens in the AI response optional field minimum value for reasoning models (e.g., model_name starts with ‘o’): 1024 ;minimum value for non-reasoning models: 16 ;maximum value for reasoning models: 4096 ;maximum value for non-reasoning models: 2048 ;default value for both reasoning and non-reasoning models: 2048 ;Note: when web_search is set to true , the output token count may exceed the specified max_output_tokens limit |
temperature |
float | randomness of the AI response optional field higher values make output more diverse; lower values make output more focused; minimum value: 0 maximum value: 2 default value: 0.94 Note: not supported in o4-mini , o3-mini , o1-pro , o1 models |
top_p |
float | diversity of the AI response optional field controls diversity of the response by limiting token selection; minimum value: 0 maximum value: 1 default value: 0.92 Note: not supported in o4-mini , o3-mini , o1-pro , o1 models |
web_search |
boolean | enable web search optional field when enabled, the AI model can access and cite current web information; default value: false ;Note: refer to the Models endpoint for a list of models that support web_search ;
|
force_web_search |
boolean | force AI agent to use web search optional field to enable this parameter, web_search must also be enabled;when enabled, the AI model is forced to access and cite current web information; default value: false ;Note: even if the parameter is set to true , there is no guarantee web sources will be cited in the response
|
web_search_country_iso_code |
string | ISO country code of the location optional field required if web_search_city is specified;to enable this parameter, web_search must also be enabled;when enabled, the AI model will search the web from the country you specify; Note: not supported in o3-mini , o1-pro , o1 models
|
web_search_city |
string | city name of the location optional field Note: specify web_search_country_iso_code to use this parameterNote #2: not supported in o3-mini , o1-pro , o1 models |
system_message |
string | instructions for the AI behaviour optional field defines the AI’s role, tone, or specific behavior you can specify up to 500 characters in the system_message field |
message_chain |
array | conversation history optional field array of message objects representing previous conversation turns; each object must contain role and message parameters:role string with either user or ai role;message string with message content (max 500 characters);you can specify the maximum of 10 message objects in the array; example: "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?"}]
|
tag |
string | user-defined task identifier optional field the character limit is 255 you can use this parameter to identify the task and match it with the result you will find the specified tag value in the data object of the response |
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 |
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 |
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 |