数据 API / DataForSEO / AI Optimization
Live Claude LLM Responses
Sends a user_prompt to a Claude model and returns its reply, synchronously. model_name must come from get_dataforseo_ai_claude_llm_responses_models - names look like claude-sonnet-5, and a plausible-looking guess is rejected. 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.
参数
没有路径、查询或请求头参数。
请求体
user_promptstring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
model_namestring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 claude-opus-4-0 is specified, the claude-opus-4-20250514 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/claude/llm_responses/models
max_output_tokensinteger可选maximum number of tokens in the AI response optional field minimum value: 1; 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 Note #2: if use_reasoning is set to true, the minimum value for max_output_tokens is 1025
temperaturenumber可选randomness of the AI response optional field higher values make output more diverse; lower values make output more focused; minimum value: 0 maximum value: 1 default value: 0.7Note: temperature cannot be used together with top_p in the same request
top_pnumber可选diversity of the AI response optional field controls diversity of the response by limiting token selection; minimum value: 0 maximum value: 1 default value: nullNote: top_p cannot be used together with temperature in the same request
web_searchboolean可选enable web search for current information optional field when enabled, the AI model can access and cite current web information; Note: refer to the Models endpoint for a list of models that support web_search; default value: false; The cost of the parameter can be calculated on the Pricing page
force_web_searchboolean可选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
web_search_country_iso_codestring可选ISO country code of the location optional field possible values: 'AR','AT','AU','BE','BR','CA','CH','CL','CN','DE','DK','ES','FI','FR','GB','HK','ID','IN','IT','JP','KR','MX','MY','NL','NO','NZ','PH','PL','PT','RU','SA','SE','TR','TW','US','ZA'
web_search_citystring可选city name of the location optional field Note: specify web_search_country_iso_code to use this parameter
system_messagestring可选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
message_chainobject[]可选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?"}]
rolestring必填允许值: user · ai
messagestring必填use_reasoningboolean可选enable reasoning for the AI model optional field when enabled, the model will perform reasoning before generating a response refer to the Models endpoint for a list of models that support reasoning default value: false Note: if set to true, the minimum value for max_output_tokens is 1025 Note #2: if set to true, force_web_search must be set to false Note #3: if set to true, the temperature and top_p cannot be used
tagstring可选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
请求示例
curl -X POST "https://openapi.felo.ai/v1/beta/dataforseo/ai_optimization/claude/llm_responses/live" \
-H "Authorization: Bearer $FELO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"user_prompt": "<string>",
"model_name": "<string>",
"max_output_tokens": 0,
"temperature": 0,
"top_p": 0,
"web_search": false,
"force_web_search": false,
"web_search_country_iso_code": "<string>"
}'响应
响应字段
versionstring可选the current version of the API
status_codeinteger可选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_messagestring可选general informational message you can find the full list of general informational messages here
timestring可选execution time, seconds
costnumber可选total tasks cost, USD
tasks_countinteger可选the number of tasks in the tasks array
tasks_errorinteger可选the number of tasks in the tasks array returned with an error
tasksstring[]可选array of tasks
idstring可选task identifier unique task identifier in our system in the UUID format
status_codeinteger可选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
status_messagestring可选informational message of the task you can find the full list of general informational messages here
timestring可选execution time, seconds
costnumber可选cost of the task, USD includes the base task price plus the money_spent value
result_countinteger可选number of elements in the result array
pathstring[]可选URL path
dataobject可选contains the same parameters that you specified in the POST request
resultstring[]可选array of results
model_namestring可选name of the AI model used
input_tokensinteger可选number of tokens in the input total count of tokens processed
output_tokensinteger可选number of tokens in the output total count of tokens generated in the AI response
reasoning_tokensinteger可选number of reasoning tokens total count of tokens used to generate reasoning content
web_searchboolean可选indicates if web search was used
money_spentnumber可选cost of AI tokens, USD the price charged by the third-party AI model provider for according to its Pricing
datetimestring可选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
itemsstring[]可选array of response items contains structured AI response data
reasoningobject可选element in the response
typestring可选type of the element = 'reasoning' Note: this element is supported only in reasoning models and is not guaranteed to be returned
sectionsstring[]可选reasoning chain sections array of objects containing the reasoning chain sections generated by the LLM
typestring可选type of element='summary_text'
textstring可选text of the reasoning chain section text of the reasoning chain section summarizing the model's thought process
messageobject可选element in the response
typestring可选type of the element = 'message'
sectionsstring[]可选array of content sections contains different parts of the AI response
typestring可选type of element='text'
textstring可选AI-generated text content
annotationsstring[]可选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
titlestring可选the domain name or title of the quoted source
urlstring可选URL of the quoted source
fan_out_queriesstring[]可选array of fan-out queries contains related search queries derived from the main query to provide a more comprehensive response