v0.1.0-beta

OpenAPI 3.1.0

Live ChatGPT LLM Responses

Felo API Support

MIT

Сервер

https://openapi.felo.ai

Клиентские библиотеки

Shell Curl

DataForSEO

SEO, search-engine results, keyword research, backlinks and AI visibility data.

DataForSEO Операции

post/v1/beta/dataforseo/ai_optimization/chat_gpt/llm_responses/live

Live ChatGPT LLM Responses

Sends a user_prompt to a ChatGPT model and returns its reply, synchronously. model_name picks the model - see get_dataforseo_ai_chat_gpt_llm_responses_models, and an unlisted name is rejected outright. max_output_tokens, temperature and top_p behave as they do on the vendor's own API, and web_search or force_web_search let it browse. Returns model_name, input_tokens, output_tokens, reasoning_tokens, web_search, money_spent, datetime, items and fan_out_queries. Read money_spent on the response to see what a prompt actually cost. 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 a general LLM call routed through a data provider, not an SEO measurement. If you want to know what ChatGPT tells users about a brand, post_dataforseo_ai_chat_gpt_llm_scraper_live reproduces the consumer experience instead.

Тело

обязательно

application/json

Тип: array object[]
- model_name
  Тип: string
  обязательно
  
  name of the AI model required field model_nameconsists 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
- user_prompt
  Тип: string
  обязательно
  
  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
- force_web_search
  Тип: 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 Note #2: not supported in reasoning models
- max_output_tokens
  Тип: integer
  
  maximum number of tokens in the AI response optional field minimum value for reasoning models (e.g., reasoning is true in the Models endpoint): 1024; minimum value for non-reasoning models: 16; maximum value: 4096; default value: 2048 Note: if web_search is set to true or the reasoning model is specified in the request, the output token count may exceed the specified max_output_tokens limit
- message_chain
  Тип: array object[]
  
  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?"}]
  
  message
  Тип: string
  обязательно
  role
  Тип: string enum
  обязательно
  значения
  user
  ai
- system_message
  Тип: 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
- tag
  Тип: 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
- temperature
  Тип: number
  
  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 reasoning models
- top_p
  Тип: number
- web_search
  Тип: 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;
- web_search_city
  Тип: string
  
  city name of the location optional field Note: specify web_search_country_iso_code to use this parameter Note #2: not supported in o3-mini, o1-pro, o1 models
- web_search_country_iso_code
  Тип: 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

Ответы

200
Тип: object

Successful response
cost
Тип: number

total tasks cost, USD

status_code
Тип: 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
Тип: string

general informational message you can find the full list of general informational messages here

tasks
Тип: array string[]

array of tasks

tasks_count
Тип: integer

the number of tasks in the tasks array

tasks_error
Тип: integer

the number of tasks in the tasks array returned with an error

tasks.cost
Тип: number

cost of the task, USD includes the base task price plus the money_spent value

tasks.data
Тип: object

contains the same parameters that you specified in the POST request

tasks.id
Тип: string

task identifier unique task identifier in our system in the UUID format

tasks.path
Тип: array string[]

URL path

tasks.result
Тип: array string[]

array of results

tasks.result_count
Тип: integer

number of elements in the result array

tasks.result.datetime
Тип: 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

tasks.result.fan_out_queries
Тип: array string[]

array of fan-out queries contains related search queries derived from the main query to provide a more comprehensive response

tasks.result.input_tokens
Тип: integer

number of tokens in the input total count of tokens processed

tasks.result.items
Тип: array string[]

array of response items contains structured AI response data

tasks.result.items.message
Тип: object

element in the response

tasks.result.items.message.sections
Тип: array string[]

array of content sections contains different parts of the AI response

tasks.result.items.message.sections.annotations
Тип: array string[]

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

tasks.result.items.message.sections.annotations.title
Тип: string

the domain name or title of the quoted source

tasks.result.items.message.sections.annotations.url
Тип: string

URL of the quoted source

tasks.result.items.message.sections.text
Тип: string

AI-generated text content

tasks.result.items.message.sections.type
Тип: string

type of element='text'

tasks.result.items.message.type
Тип: string

type of the element = 'message'

tasks.result.items.reasoning
Тип: object

element in the response

tasks.result.items.reasoning.sections
Тип: array string[]

reasoning chain sections array of objects containing the reasoning chain sections generated by the LLM

tasks.result.items.reasoning.sections.text
Тип: string

text of the reasoning chain section text of the reasoning chain section summarizing the model's thought process

tasks.result.items.reasoning.sections.type
Тип: string

type of element='summary_text'

tasks.result.items.reasoning.type
Тип: string

type of the element = 'reasoning' Note: this element is supported only in reasoning models and is not guaranteed to be returned

tasks.result.model_name
Тип: string

name of the AI model used

tasks.result.money_spent
Тип: number

cost of AI tokens, USD the price charged by the third-party AI model provider for according to its Pricing

tasks.result.output_tokens
Тип: integer

number of tokens in the output total count of tokens generated in the AI response

tasks.result.reasoning_tokens
Тип: integer

number of reasoning tokens total count of tokens used to generate reasoning content

tasks.result.web_search
Тип: boolean

indicates if web search was used

tasks.status_code
Тип: 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

tasks.status_message
Тип: string

informational message of the task you can find the full list of general informational messages here

tasks.time
Тип: string

execution time, seconds

time
Тип: string

execution time, seconds

version
Тип: string

the current version of the API
application/json
400

Bad request
401

Unauthorized
402

The request cannot proceed because a billing requirement is not met.
403

The account is not permitted to perform this operation.
429

Rate limit exceeded
500

Internal server error
502

The service could not complete the request.
503

The API or billing service is temporarily unavailable.
504

The service timed out while processing the request.
default

The operation failed. Keep the response request ID when contacting Felo support.

post/v1/beta/dataforseo/ai_optimization/chat_gpt/llm_responses/live

curl https://openapi.felo.ai/v1/beta/dataforseo/ai_optimization/chat_gpt/llm_responses/live \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer YOUR_SECRET_TOKEN' \
  --data '[
  {
    "user_prompt": "",
    "model_name": "",
    "max_output_tokens": 1,
    "temperature": 1,
    "top_p": 1,
    "web_search": true,
    "force_web_search": true,
    "web_search_country_iso_code": "",
    "web_search_city": "",
    "system_message": "",
    "message_chain": [
      {
        "role": "user",
        "message": ""
      }
    ],
    "tag": ""
  }
]'

Показать схему

{
  "version": "string",
  "status_code": 1,
  "status_message": "string",
  "time": "string",
  "cost": 1,
  "tasks_count": 1,
  "tasks_error": 1,
  "tasks": [
    "string"
  ],
  "tasks.id": "string",
  "tasks.status_code": 1,
  "tasks.status_message": "string",
  "tasks.time": "string",
  "tasks.cost": 1,
  "tasks.result_count": 1,
  "tasks.path": [
    "string"
  ],
  "tasks.data": {},
  "tasks.result": [
    "string"
  ],
  "tasks.result.model_name": "string",
  "tasks.result.input_tokens": 1,
  "tasks.result.output_tokens": 1,
  "tasks.result.reasoning_tokens": 1,
  "tasks.result.web_search": true,
  "tasks.result.money_spent": 1,
  "tasks.result.datetime": "string",
  "tasks.result.items": [
    "string"
  ],
  "tasks.result.items.reasoning": {},
  "tasks.result.items.reasoning.type": "string",
  "tasks.result.items.reasoning.sections": [
    "string"
  ],
  "tasks.result.items.reasoning.sections.type": "string",
  "tasks.result.items.reasoning.sections.text": "string",
  "tasks.result.items.message": {},
  "tasks.result.items.message.type": "string",
  "tasks.result.items.message.sections": [
    "string"
  ],
  "tasks.result.items.message.sections.type": "string",
  "tasks.result.items.message.sections.text": "string",
  "tasks.result.items.message.sections.annotations": [
    "string"
  ],
  "tasks.result.items.message.sections.annotations.title": "string",
  "tasks.result.items.message.sections.annotations.url": "string",
  "tasks.result.fan_out_queries": [
    "string"
  ]
}

Successful response

Live ChatGPT LLM Responses

АутентификацияRequired

DataForSEO

Live ChatGPT LLM Responses