ChatGPT answer to a prompt, live
From DataForSEO, through Joshu Data Bodega.
Part of AI Visibility / AEO chatgpt answer.
- Price
- $0.032 per call
No calls measured in the last 30 days.
Prices include the router's 10% markup and are paid from the usage wallet. Checked on November 11, 2026.
Inputs
tagstring, optionalem user-defined task identifier /em br optional field br em the character limit is 255 /em br you can use this parameter to identify the task and match it with the result br you will find the specified code tag /code value in the code data /code object of the response
top_pnumber, optionalem diversity of the AI response /em br optional field br controls diversity of the response by limiting token selection; br minimum value: code 0 /code br maximum value: code 1 /code br default value: code 0.92 /code p strong Note: /strong code top_p /code cannot be used together with
model_namestring, optionalem 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-
web_searchboolean, optionalem enable web search /em br optional field br when enabled, the AI model can access and cite current web information; br default value: code false /code ; br strong Note: /strong refer to the a href="https://docs.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/models/" Models endpoint
temperaturenumber, optionalem randomness of the AI response /em br optional field br higher values make output more diverse; br lower values make output more focused; br minimum value: code 0 /code br maximum value: code 2 /code br default value: code 0.94 /code br strong Note: /strong not supported in reasoning mo
user_promptstring, optionalem 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
message_chainarray, optionalconversation history optional field array of message objects representing previous conversation turns; each object must contain: role string with either user or ai role; message string with message content (max 500 characters); you can specify maximum of 10 message objects in the array; Note: for Pe
system_messagestring, optionalem instructions for the AI behaviour /em br optional field br defines the AI's role, tone, or specific behavior br you can specify strong up to 500 characters /strong in the code system_message /code field
web_search_citystring, optionalem city name of the location /em br optional field br strong Note: /strong not supported in code o3-mini /code , code o1-pro /code , code o1 /code models
force_web_searchboolean, optionalem force AI agent to use web search /em br optional field br to enable this parameter, code web_search /code must also be enabled; br when enabled, the AI model is forced to access and cite current web information; br default value: code false /code ; br strong Note: /strong even if the param
max_output_tokensinteger, optionalem maximum number of tokens in the AI response /em br optional field br minimum value for reasoning models (e.g., code reasoning /code is code true /code in the a href="/v3/ai_optimization/chat_gpt/llm_responses/models/" target="_blank" Models endpoint /a ): code 1024 /code ; br minimum valu
web_search_country_iso_codestring, optionalem ISO country code of the location /em br optional field br to enable this parameter, code web_search /code must also be enabled; br when enabled, the AI model will search the web from the country you specify; br strong Note: /strong not supported in code o3-mini /code , code o1-pro /code ,
Call it
curl https://hello.joshu.me/api/router/call \
-H "Authorization: Bearer $JOSHU_ROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{
"endpoint": "dataforseo.x.ai-optimization-chat-gpt-llm-responses-live",
"params": {}
}'