Live Gemini LLM Responses
Live Gemini LLM Responses endpoint allows you to retrieve structured responses from a specific Gemini AI model, based on the input parameters.
Documentation Index
Fetch the complete documentation index at: https://aisa.one/docs/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
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
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 gemini-1.5-pro is specified, the gemini-1.5-pro-002 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/gemini/llm_responses/models
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 1024
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: 1.3
diversity of the AI response optional field controls diversity of the response by limiting token selection minimum value: 0 maximum value: 1 default value: 0.9
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
instructions for the AI behavior optional field defines the AI's role, tone, or specific behavior you can specify up to 500 characters in the system_message field
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?"}]
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 1024 Note #2: for Gemini Pro models, the use_reasoning will automatically be set to true
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
Response
Successful response
the current version of the API
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
general informational message you can find the full list of general informational messages here
execution time, seconds
total tasks cost, USD
the number of tasks in the tasks array
the number of tasks in the tasks array returned with an error
array of tasks
task identifier unique task identifier in our system in the UUID format
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
informational message of the task you can find the full list of general informational messages here
execution time, seconds
cost of the task, USD includes the base task price plus the money_spent value
number of elements in the result array
URL path
contains the same parameters that you specified in the POST request
array of results
name of the AI model used
number of tokens in the input total count of tokens processed
number of tokens in the output total count of tokens generated in the AI response
number of reasoning tokens total count of tokens used to generate reasoning content
indicates if web search was used
cost of AI tokens, USD the price charged by the third-party AI model provider for according to its Pricing
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
array of response items contains structured AI response data
element in the response
type of the element = 'reasoning' Note: this element is supported only in reasoning models and is not guaranteed to be returned
reasoning chain sections array of objects containing the reasoning chain sections generated by the LLM
type of element='summary_text'
text of the reasoning chain section text of the reasoning chain section summarizing the model's thought process
element in the response
type of the element = 'message'
array of content sections contains different parts of the AI response
type of element='text'
AI-generated text content
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
the domain name or title of the quoted source
redirect URL to the quoted source contains a Vertex AI redirect that leads to the original source
array of fan-out queries contains related search queries derived from the main query to provide a more comprehensive response