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

Setting ‘LLM Responses ChatGPT’ Tasks

サーバー:https://openapi.felo.ai
クライアントライブラリ

DataForSEO

​

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

Setting ‘LLM Responses ChatGPT’ Tasks

​

Queues a ChatGPT prompt instead of waiting for the reply, returning a task id. Adds system_message and message_chain over the live endpoint, so a multi-turn conversation can be sent in one task. Wrapped in DataForSEO's envelope: data in tasks[0].result, outcome in tasks[0].status_code - a rejected request still returns HTTP 200. ⚠️ Not every model supports queuing - check task_post_supported in get_dataforseo_ai_chat_gpt_llm_responses_models. Retrieve with get_dataforseo_ai_chat_gpt_llm_responses_fetch.

リクエストボディ
必須
application/json
  • 型: array object[]
    • model_name
      型: string
      必須

      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
      型: string
      必須

      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

    • max_output_tokens
      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

    • message_chain
      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
        型: string
        必須
      • role
        型: string 列挙値
        必須
        値
        • user
        • ai
    • pingback_url
      型: string

      notification URL of a completed task optional field when a task is completed we will notify you by GET request sent to the URL you have specified you can use the ‘$id’ string as a $id variable and ‘$tag’ as urlencoded $tag variable. We will set the necessary values before sending the request example: http://your-server.com/pingscript?id=$id http://your-server.com/pingscript?id=$id&tag=$tag Note: special character in pingback_url will be urlencoded; i.a., the # character will be encoded into %23learn more on our Help Center

    • postback_url
      型: string

      URL for sending task results optional field once the task is completed, we will send a POST request with its results compressed in the gzip format to the postback_url you specified you can use the ‘$id’ string as a $id variable and ‘$tag’ as urlencoded $tag variable. We will set the necessary values before sending the request. example: http://your-server.com/postbackscript?id=$id http://your-server.com/postbackscript?id=$id&tag=$tag Note: special character in postback_url will be urlencoded; i.a., the # character will be encoded into %23learn more on our Help Center

    • system_message
      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
      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 array of the response

    • temperature
      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
      型: number
レスポンス
  • 200
    型: object

    Successful response

    • cost
      型: number

      total tasks cost, USD

    • status_code
      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
      型: string

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

    • tasks
      型: array string[]

      array of tasks

    • tasks_count
      型: integer

      the number of tasks in the tasksarray

    • tasks_error
      型: integer

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

    • tasks.cost
      型: number

      cost of the task, USD

    • tasks.data
      型: object

      contains the same parameters that you specified in the POST request

    • tasks.id
      型: string

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

    • tasks.path
      型: array string[]

      URL path

    • tasks.result
      型: array string[]

      array of results in this case, the value will be null

    • tasks.result_count
      型: integer

      number of elements in the result array

    • tasks.status_code
      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 response codes here

    • tasks.status_message
      型: string

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

    • tasks.time
      型: string

      execution time, seconds

    • time
      型: string

      execution time, seconds

    • version
      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/task_post
curl https://openapi.felo.ai/v1/beta/dataforseo/ai_optimization/chat_gpt/llm_responses/task_post \
  --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,
    "system_message": "",
    "message_chain": [
      {
        "role": "user",
        "message": ""
      }
    ],
    "postback_url": "",
    "pingback_url": "",
    "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"
  ]
}
Setting ‘LLM Responses ChatGPT’ Tasks