Felo API PlatformFelo API Platform
v0.1.0-beta
OpenAPI 3.1.0

Live ChatGPT LLM Responses

Felo API Support
MIT
服务器:https://openapi.felo.ai
客户端库
Shell Curl

DataForSEO

​

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

DataForSEO 操作

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.

请求体
必填
application/json
  • 类型: array object[]
    • model_name
      类型: string
      必填

      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
      类型: string
      必填

      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
      类型: 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
      类型: 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
      类型: 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
        类型: string
        必填
      • role
        类型: string 枚举
        必填
        值
        • user
        • ai
    • system_message
      类型: 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
      类型: 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
      类型: 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
      类型: number
    • web_search
      类型: 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
      类型: 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
      类型: 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

响应
  • 200
    类型: object

    Successful response

    • cost
      类型: number

      total tasks cost, USD

    • status_code
      类型: 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
      类型: string

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

    • tasks
      类型: array string[]

      array of tasks

    • tasks_count
      类型: integer

      the number of tasks in the tasks array

    • tasks_error
      类型: integer

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

    • tasks.cost
      类型: number

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

    • tasks.data
      类型: object

      contains the same parameters that you specified in the POST request

    • tasks.id
      类型: string

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

    • tasks.path
      类型: array string[]

      URL path

    • tasks.result
      类型: array string[]

      array of results

    • tasks.result_count
      类型: integer

      number of elements in the result array

    • tasks.result.datetime
      类型: 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
      类型: 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
      类型: integer

      number of tokens in the input total count of tokens processed

    • tasks.result.items
      类型: array string[]

      array of response items contains structured AI response data

    • tasks.result.items.message
      类型: object

      element in the response

    • tasks.result.items.message.sections
      类型: array string[]

      array of content sections contains different parts of the AI response

    • tasks.result.items.message.sections.annotations
      类型: 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
      类型: string

      the domain name or title of the quoted source

    • tasks.result.items.message.sections.annotations.url
      类型: string

      URL of the quoted source

    • tasks.result.items.message.sections.text
      类型: string

      AI-generated text content

    • tasks.result.items.message.sections.type
      类型: string

      type of element='text'

    • tasks.result.items.message.type
      类型: string

      type of the element = 'message'

    • tasks.result.items.reasoning
      类型: object

      element in the response

    • tasks.result.items.reasoning.sections
      类型: array string[]

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

    • tasks.result.items.reasoning.sections.text
      类型: 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
      类型: string

      type of element='summary_text'

    • tasks.result.items.reasoning.type
      类型: 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
      类型: string

      name of the AI model used

    • tasks.result.money_spent
      类型: 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
      类型: integer

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

    • tasks.result.reasoning_tokens
      类型: integer

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

    • 类型: boolean

      indicates if web search was used

    • tasks.status_code
      类型: 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
      类型: string

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

    • tasks.time
      类型: string

      execution time, seconds

    • time
      类型: string

      execution time, seconds

    • version
      类型: 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.

Request Example for 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": ""
  }
]'

{
  "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