Data API / DataForSEO / AI Optimization
Live ChatGPT LLM Scraper
Asks ChatGPT a keyword as a user would and returns the answer parsed. Returns keyword, location_code, language_code, model, datetime, markdown, sources, fan_out_queries and brand_entities - markdown is the answer as the assistant rendered it, sources the pages it cited, and brand_entities the brands it named. force_web_search makes it browse rather than answer from training. Wrapped in DataForSEO's envelope: data in tasks[0].result, outcome in tasks[0].status_code - a rejected request still returns HTTP 200. This is the endpoint for 'what does ChatGPT say about us'; for counting mentions across many answers use post_dataforseo_ai_llm_mentions_aggregated_metrics_live instead of scraping repeatedly. The raw form is post_dataforseo_ai_chat_gpt_llm_scraper_live_html.
Parameters
No path, query, or header parameters.
Request body
keywordstringRequiredkeyword required field you can specify up to 2000 characters in the keyword field all %## will be decoded (plus character ‘+’ will be decoded to a space character) if you need to use the “%” character for your keyword, please specify it as “%25”; if you need to use the “+” character for your keyword, please specify it as “%2B”learn more about rules and limitations of keyword and keywords fields in DataForSEO APIs in this Help Center article
location_namestringOptionalfull name of search engine location required field if you don't specify location_code if you use this field, you don't need to specify location_code you can receive the list of available locations of the search engine with their location_name by making a separate request to the https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_scraper/locations example: United States
location_codeintegerOptionalsearch engine location code required field if you don't specify location_name if you use this field, you don't need to specify location_name you can receive the list of available locations of the search engines with their location_code by making a separate request to the https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_scraper/locations example: 2840
language_namestringOptionalfull name of search engine language required field if you don't specify language_code; if you use this field, you don't need to specify language_code; you can receive the list of available languages of the search engine with their language_name by making a separate request to the https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_scraper/languages
language_codestringOptionalsearch engine language code required field if you don't specify language_name; if you use this field, you don't need to specify language_name; you can receive the list of available languages of the search engine with their language_code by making a separate request to the https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_scraper/languages
force_web_searchbooleanOptionalforce AI agent to use web search optional field 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
tagstringOptionaluser-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
Example request
curl -X POST "https://openapi.felo.ai/v1/beta/dataforseo/ai_optimization/chat_gpt/llm_scraper/live/advanced" \
-H "Authorization: Bearer $FELO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"keyword": "<string>",
"location_name": "<string>",
"location_code": 0,
"language_name": "<string>",
"language_code": "<string>",
"force_web_search": false,
"tag": "<string>"
}'Response
Response fields
versionstringOptionalthe current version of the API
status_codeintegerOptionalgeneral 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_messagestringOptionalgeneral informational message you can find the full list of general informational messages here
timestringOptionalexecution time, seconds
costnumberOptionaltotal tasks cost, USD
tasks_countintegerOptionalthe number of tasks in the tasks array
tasks_errorintegerOptionalthe number of tasks in the tasks array returned with an error
tasksstring[]Optionalarray of tasks
idstringOptionaltask identifier unique task identifier in our system in the UUID format
status_codeintegerOptionalstatus 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_messagestringOptionalinformational message of the task you can find the full list of general informational messages here
timestringOptionalexecution time, seconds
costnumberOptionalcost of the task, USD
result_countintegerOptionalnumber of elements in the result array
pathstring[]OptionalURL path
dataobjectOptionalcontains the same parameters that you specified in the POST request
resultstring[]Optionalarray of results
keywordstringOptionalkeyword received in a POST array the keyword is returned with decoded %## (plus symbol '+' will be decoded to a space character)
location_codeintegerOptionallocation code in a POST array
language_codestringOptionallanguage code in a POST array
modelstringOptionalindicates the model version
check_urlstringOptionaldirect URL to search engine results you can use it to make sure that we provided exact results
datetimestringOptionaldate 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
markdownstringOptionalcontent of the element in markdown format content of the result formatted in the markdown markup language
search_resultsstring[]Optionalarray of search results all web search outputs the model retrieved when looking up information, including duplicates and unused entries
typestringOptionaltype of element='chatgpt_search_result'n
urlstringOptionalresult URL
domainstringOptionalresult domain
titlestringOptionalresult title
descriptionstringOptionalresult description
breadcrumbstringOptionalbreadcrumb
sourcesstring[]Optionalarray of sources the sources the model actually cited or relied on in its final answer
typestringOptionaltype of element='chat_gpt_source'
titlestringOptionalsource title
snippetstringOptionalsource description
domainstringOptionalsource domain
urlstringOptionalsource URL
thumbnailstringOptionalsource thumbnail
source_namestringOptionalsource name
publication_datestringOptionaldate and time when the result was published in the format: “year-month-date:minutes:UTC_difference_hours:UTC_difference_minutes” example: 2019-11-15 12:57:46 +00:00
markdownstringOptionalcontent of the element in markdown format content of the result formatted in the markdown markup language
fan_out_queriesstring[]Optionalarray of fan-out queries contains related search queries derived from the main query to provide a more comprehensive response
brand_entitiesstring[]Optionalarray of brand entities contains information on brands mentioned in the response
typestringOptionaltype of the element = 'chat_gpt_brand_entity'
titlestringOptionalname of the brand
categorystringOptionalcategory of the brand
markdownstringOptionalbrand name in markdown format contains brand name formatted in the markdown markup language
urlsstring[]Optionalarray of URLs and domains relevant to the brand
urlstringOptionalURL
domainstringOptionaldomain
se_results_countintegerOptionaltotal number of results
item_typesstring[]Optionaltypes of search results contains types of search results (items) found in SERP. possible item types: chat_gpt_text, chat_gpt_table, chat_gpt_navigation_list, chat_gpt_images, chat_gpt_local_businesses, chat_gpt_products
items_countintegerOptionalthe number of results returned in the items array
itemsstring[]Optionalelements of ChatGPT results
chat_gpt_textobjectOptionalelement in the response
typestringOptionaltype of element='chat_gpt_text'
rank_groupintegerOptionalgroup rank in SERP position within a group of elements with identical type values positions of elements with different type values are omitted from rank_group
rank_absoluteintegerOptionalabsolute rank in SERP absolute position among all the elements in SERP
markdownstringOptionalcontent of the element in markdown format content of the result formatted in the markdown markup language
sourcesstring[]Optionalarray of sources
typestringOptionaltype of element='chat_gpt_source'n
titlestringOptionalsource title
snippetstringOptionalsource description
domainstringOptionalsource domain in SERP
urlstringOptionalsource URL
thumbnailstringOptionalsource thumbnail
source_namestringOptionalsource name
publication_datestringOptionaldate and time when the result was published in the format: “year-month-date:minutes:UTC_difference_hours:UTC_difference_minutes” example: 2019-11-15 12:57:46 +00:00
markdownstringOptionalcontent of the element in markdown format content of the result formatted in the markdown markup language
brand_entitiesstring[]Optionalarray of brand entities contains information on brands mentioned in the text
typestringOptionaltype of the element = 'chat_gpt_brand_entity'
titlestringOptionalname of the brand
categorystringOptionalcategory of the brand
markdownstringOptionalbrand name in markdown format contains brand name formatted in the markdown markup language
urlsstring[]Optionalarray of URLs and domains relevant to the brand
urlstringOptionalURL
domainstringOptionaldomain
chat_gpt_tableobjectOptionalelement in the response
typestringOptionaltype of element='chat_gpt_table'
rank_groupintegerOptionalgroup rank in SERP position within a group of elements with identical type values positions of elements with different type values are omitted from rank_group
rank_absoluteintegerOptionalabsolute rank in SERP absolute position among all the elements in SERP
textstringOptionaltext of the element
markdownstringOptionalcontent of the element in markdown format content of the result formatted in the markdown markup language
tableobjectOptionaltable present in the element the header and content of the table present in the element
table_headerstring[]Optionalcontent in the header of the table
table_contentstring[]Optionalarray of contents of the table present in the element each array represents the table row
brand_entitiesstring[]Optionalarray of brand entities contains information on brands mentioned in the table
typestringOptionaltype of the element = 'chat_gpt_brand_entity'
titlestringOptionalname of the brand
categorystringOptionalcategory of the brand
markdownstringOptionalbrand name in markdown format contains brand name formatted in the markdown markup language
urlsstring[]Optionalarray of URLs and domains relevant to the brand
urlstringOptionalURL
domainstringOptionaldomain
chat_gpt_navigation_listobjectOptionalelement in the response
typestringOptionaltype of element='chat_gpt_navigation_list'
rank_groupintegerOptionalgroup rank in SERP position within a group of elements with identical type values positions of elements with different type values are omitted from rank_group
rank_absoluteintegerOptionalabsolute rank in SERP absolute position among all the elements in SERP
titlestringOptionaltitle of the element
sourcesstring[]Optionalarray of sources
typestringOptionaltype of element='chat_gpt_source'
titlestringOptionalsource title
snippetstringOptionalsource description
domainstringOptionalsource domain in SERP
urlstringOptionalsource URL
thumbnailstringOptionalsource thumbnail
source_namestringOptionalsource name
publication_datestringOptionaldate and time when the result was published in the format: “year-month-date:minutes:UTC_difference_hours:UTC_difference_minutes” example: 2019-11-15 12:57:46 +00:00
markdownstringOptionalcontent of the element in markdown format content of the result formatted in the markdown markup language
chat_gpt_imagesobjectOptionalelement in the response
typestringOptionaltype of element='chat_gpt_images'
rank_groupintegerOptionalgroup rank in SERP position within a group of elements with identical type values positions of elements with different type values are omitted from rank_group
rank_absoluteintegerOptionalabsolute rank in SERP absolute position among all the elements in SERP
markdownstringOptionalcontent of the element in markdown format content of the result formatted in the markdown markup language
itemsstring[]Optionalitems present in the element
typestringOptionaltype of element = 'chat_gpt_images_element'
altstringOptionalalt tag of the image
urlstringOptionalrelevant URL
image_urlstringOptionalURL of the image the URL leading to the image on the original resource or DataForSEO storage (in case the original source is not available)
markdownstringOptionalcontent of the element in markdown format content of the result formatted in the markdown markup language
chat_gpt_local_businessesobjectOptionalelement in the response
typestringOptionaltype of element='chat_gpt_local_businesses'
rank_groupintegerOptionalgroup rank in SERP position within a group of elements with identical type values positions of elements with different type values are omitted from rank_group
rank_absoluteintegerOptionalabsolute rank in SERP absolute position among all the elements in SERP
markdownstringOptionalcontent of the element in markdown format content of the result formatted in the markdown markup language
itemsstring[]Optionalitems present in the element
typestringOptionaltype of element = 'chat_gpt_local_businesses_element'
titlestringOptionaltitle of the local business
descriptionstringOptionaldescription of the local business
addressstringOptionaladdress of the local business
phonestringOptionalphone of the local business
reviews_countintegerOptionaltotal number of reviews submitted for the local business
urlstringOptionalwebsite URL of the local business
domainstringOptionaldomain name of the local business
ratingobjectOptionalrating of the corresponding local business popularity rate based on reviews and displayed in SERP
rating_typestringOptionaltype of rating here you can find the following elements: Max5, Percents, CustomMax
valuenumberOptionalthe average rating based on all reviews
votes_countintegerOptionalthe number of votes
rating_maxintegerOptionalthe maximum value for a rating_type
chat_gpt_productsobjectOptionalelement in the response
typestringOptionaltype of element='chat_gpt_products'
rank_groupintegerOptionalgroup rank in SERP position within a group of elements with identical type values positions of elements with different type values are omitted from rank_group
rank_absoluteintegerOptionalabsolute rank in SERP absolute position among all the elements in SERP
itemsstring[]Optionalitems present in the element
typestringOptionaltype of element = 'chat_gpt_products_element'
product_idstringOptionalproduct id
merchantsstringOptionalmerchant(s) offering the product
id_to_token_mapstringOptionalproduct identifier token Base64-encoded token containing Google Shopping product IDs associated with the product
titlestringOptionaltitle of the product
ratingobjectOptionalrating of the product popularity rate based on reviews and displayed in SERP
rating_typestringOptionaltype of rating here you can find the following elements: Max5, Percents, CustomMax
valuenumberOptionalthe average rating based on all reviews
votes_countintegerOptionalthe number of votes
rating_maxintegerOptionalthe maximum value for a rating_type
pricenumberOptionalproduct price
currencystringOptionalcurrency of the listed price ISO code of the currency applied to the price
tagstringOptionaltag text
urlstringOptionalresult URL
domainstringOptionalresult domain in SERP
imagesstring[]Optionalimage URLs of the element contains URLs leading to the images on the original resource or DataForSEO storage (in case the original source is not available)
product_idsstring[]OptionalGoogle Shopping product identifiers array of Google Shopping product IDs associated with the product
typestringOptionaltype of element = 'chat_gpt_google_shopping_product'
eistringOptionalevent identifier internal event identifier used by Google
product_idstringOptionalproduct identifier can be used as a data_docid in Google Shopping API endpoints
catalog_idstringOptionalGoogle Shopping catalog identifier of the product can be used as a product_id in Google Shopping API endpoints
gpcidstringOptionalGoogle product cluster identifier can be used as a gid in Google Shopping API endpoints
headline_offer_docidstringOptionaldocument identifier of the main offer in the headline can be used as a data_docid in Google Shopping API endpoints
image_docidstringOptionalidentifier for the displayed product’s image
rdsstringOptionalresource descriptor string internal Google resource descriptor string that identifies the product within Google's Shopping index
querystringOptionalsearch query search query used by ChatGPT to retrieve the product from Google Shopping
midstringOptionalmerchant identifier identifier of the seller or merchant account in Google Shopping
pvtstringOptionalproduct view type internal Google parameter that specifies the product view type used when rendering the product item
uulestringOptionalencoded location parameter indicates the location for a search
glstringOptionalcountry code indicates the location for which search results are displayed
hlstringOptionalhost language code indicates the language in which search results are displayed