OpenAI DataForSEO AI Optimization Chat GPT LLM Responses Live
Usage-based pricing
ae_dataforseo_ai_optimization_chat_gpt_llm_responses_live
Generate a response from a ChatGPT model through DataForSEO. Provide the task parameters in the request_body array according to this interface schema.
Usage-based pricing
Pricing
The charge per call is (max(1200 × actual billed usage (USD), 0)) AE credits. All applicable conditions are combined to calculate the total.
Charges depend on the number of tasks submitted, the selected model, actual input and output usage (including reasoning), and optional features such as web search. Settlement uses the actual billed usage for the call. The output token limit is not the actual output usage.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
request_body | array | Yes | No parameter description. | — |
request_body[].tag | string | null | No | No parameter description. | — |
request_body[].top_p | number | null | No | No parameter description. | — |
request_body[].model_name | string | No | <em>name of the AI model</em><br><strong>required field</strong><br><code>model_name</code >consists of the actual model name and version name;<br>if the basic model name is specified, its latest version will be set by default;<br>for example, if <code>gpt-4.1</code> is specified, the <code>gpt-4.1-2025-04-14</code> will be set as <code>model_name</code> automatically;<br>you can receive the list of available LLM models by making a separate request to the <code>https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/models</code> | — |
request_body[].web_search | boolean | null | No | No parameter description. | — |
request_body[].temperature | number | null | No | No parameter description. | — |
request_body[].user_prompt | string | No | <em>prompt for the AI model</em><br><strong>required field</strong><br>the question or task you want to send to the AI model;<br>you can specify <strong>up to 500 characters</strong> in the <code>user_prompt</code> field | — |
request_body[].message_chain | array | null | No | No parameter description. | — |
request_body[].message_chain[].role | string | null | No | No parameter description. | — |
request_body[].message_chain[].message | string | null | No | No parameter description. | — |
request_body[].system_message | string | null | No | No parameter description. | — |
request_body[].web_search_city | string | null | No | No parameter description. | — |
request_body[].force_web_search | boolean | null | No | No parameter description. | — |
request_body[].max_output_tokens | integer | null | No | No parameter description. | — |
request_body[].web_search_country_iso_code | string | null | No | No parameter description. | — |
Invocation example
Copy the request and explore its response example.
POST
/agent-api/v1/tool/executeX-Api-KeyRequest coderequest.sh
curl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_dataforseo_ai_optimization_chat_gpt_llm_responses_live' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": [
{
"max_output_tokens": 200,
"model_name": "gpt-4o-mini",
"system_message": "You are a concise assistant. Answer in exactly one short Chinese sentence.",
"tag": "workbuddy-verify-gpt",
"user_prompt": "用一句中文回答:ChatGPT Plus 消费者订阅能否用来给 OpenAI API 平台鉴权?API 是否与订阅分开计费?"
}
]
}
}'Response exampleresponse.json
{
"status_code": 20000,
"status_message": "Ok.",
"tasks": [
{
"data": {
"api": "ai_optimization",
"function": "llm_responses",
"max_output_tokens": 200,
"model_name": "gpt-4o-mini",
"se": "chat_gpt",
"system_message": "You are a concise assistant. Answer in exactly one short Chinese sentence."
},
"id": "11161236-2802-0612-0000-c855768aaf53",
"path": [
"v3"
],
"result": [
{
"datetime": "2026-11-16 12:36:04 +00:00",
"fan_out_queries": null,
"items": [
{}
],
"model_name": "gpt-4o-mini-2024-07-18",
"search_results": null,
"web_search": false
}
],
"result_count": 1,
"status_code": 20000
}
],
"tasks_count": 1,
"tasks_error": 0,
"time": "1.5468 sec."
}This example shows part of the response. Copied content is valid JSON.





