> ## 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.
# Live Claude LLM Responses
> Sends a user_prompt to a Claude model and returns its reply, synchronously.
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`. π° Billed per call at a flat rate, whatever the reply length. Wrapped in DataForSEO's envelope: data in `tasks[0].result`, outcome in `tasks[0].status_code` - a rejected request still returns HTTP 200.
## Example
```bash REST theme={null}
curl -X POST "https://api.aisa.one/apis/v1/dataforseo/ai_optimization/claude/llm_responses/live" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '[{"user_prompt": "...", "model_name": "...", "max_output_tokens": "..."}]'
```
```jsonc MCP theme={null}
// Copy this whole block into Claude Code, Codex, Cursor or any coding agent.
// It carries everything needed to connect, authorize and run this example β
// no key to paste, one click of Allow in the browser.
{
"operation_id": "post_dataforseo_ai_claude_llm_responses_live",
"arguments": {},
"max_price_usd": 0.05
}
// ββ for the agent βββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
// Register the AIsa MCP server, then call its `use` tool with the JSON above.
// name aisa
// endpoint https://mcp.aisa.one/mcp
// transport streamable-http
// auth OAuth. The server publishes RFC 9728 metadata, so open a
// browser and the user clicks Allow once β nothing to paste.
// If AISA_API_KEY is set, send it as a bearer header instead.
// Use your own MCP mechanism, not a hand-edited config file:
// Codex codex mcp add aisa --url https://mcp.aisa.one/mcp
// Claude Code claude mcp add --transport http -s user aisa https://mcp.aisa.one/mcp
// Cursor / VS Code a "url" entry for https://mcp.aisa.one/mcp in the MCP config
// The server lists five tools over https://mcp.aisa.one/servers worth of APIs:
// search, get_details, use, batch_use, list_categories. search and
// get_details are free; use is billed per call and max_price_usd refuses
// anything above the cap before spending. This operation's full contract β
// every argument, the response shape, the price and the pitfalls β is at
// https://aisa.one/docs/api-reference/dataforseo/post_dataforseo-ai-optimization-claude-llm-responses-live.md
// Then run the call and show me the result.
```
**First time?** Point any MCP client at `https://mcp.aisa.one/mcp` β Claude
Code, Codex, Cursor, VS Code and the rest. Authorization is OAuth: the client
opens a browser, you click Allow once, and there is no key to paste. The
commands per client, and what each call costs, are on
[aisa.one/mcp](https://aisa.one/mcp#connect).
[Set this endpoint up in your agent β](https://aisa.one/mcp?from=/api-reference/dataforseo/post_dataforseo-ai-optimization-claude-llm-responses-live)
## OpenAPI
````yaml openapi/dataforseo.json POST /dataforseo/ai_optimization/claude/llm_responses/live
openapi: 3.0.3
info:
title: DataForSEO API
version: 1.0.0
description: DataForSEO API endpoints exposed through the AIsa unified gateway.
servers:
- url: https://api.aisa.one/apis/v1
security:
- BearerAuth: []
paths:
/dataforseo/ai_optimization/claude/llm_responses/live:
post:
summary: Live Claude LLM Responses
description: >-
Live Claude LLM Responses endpoint allows you to retrieve structured
responses from a specific Claude model, based on the input parameters.
operationId: post_dataforseo_ai_claude_llm_responses_live
requestBody:
required: true
content:
application/json:
schema:
type: array
items:
type: object
properties:
user_prompt:
type: string
description: >-
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_name:
type: string
description: >-
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_tokens:
type: integer
description: >-
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
temperature:
type: number
description: >-
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_p:
type: number
description: >-
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_search:
type: boolean
description: >-
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
force_web_search:
type: boolean
description: >-
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_code:
type: string
description: >-
ISO country code of the location used for searching the
web 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_city:
type: string
description: >-
city name of the location used for searching the web
optional field
system_message:
type: string
description: >-
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_chain:
type: array
items:
type: object
properties:
role:
type: string
enum:
- user
- ai
description: role of the user from whom the message originates
message:
type: string
description: message text
required:
- role
- message
description: >-
conversation 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 Perplexity models, messages must
strictly alternate between user and AI roles (user β ai);
example: "message_chain":
[{"role":"user","message":"Hello, whatβs
up?"},{"role":"ai","message":"Hello! Iβm doing well, thank
you. How can I assist you today?"}]
use_reasoning:
type: boolean
description: >-
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
tag:
type: string
description: >-
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
required:
- user_prompt
- model_name
responses:
'200':
description: Successful operation
content:
application/json:
schema:
type: object
properties:
version:
type: string
description: the current version of the API
status_code:
type: integer
description: >-
general status code you can find the full list of the
response codes here
status_message:
type: string
description: >-
general informational message you can find the full list
of general informational messages here
time:
type: string
description: total execution time, seconds
cost:
type: number
description: total tasks cost, USD
tasks_count:
type: integer
description: the number of tasks in the tasks array
tasks_error:
type: integer
description: >-
the number of tasks in the tasks array returned with an
error
tasks:
type: array
items:
type: string
description: array of tasks
tasks.id:
type: string
description: >-
task identifier unique task identifier in our system in
the UUID format
tasks.status_code:
type: integer
description: >-
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
tasks.status_message:
type: string
description: >-
informational message of the task you can find the full
list of general informational messages here
tasks.time:
type: string
description: execution time, seconds
tasks.cost:
type: number
description: total tasks cost, USD
tasks.result_count:
type: integer
description: number of elements in the result array
tasks.path:
type: array
items:
type: string
description: URL path
tasks.data:
type: object
description: >-
contains the same parameters that you specified in the
POST request
tasks.result:
type: array
items:
type: string
description: array of results
tasks.result.model_name:
type: string
description: name of the AI model used
tasks.result.input_tokens:
type: integer
description: >-
number of tokens in the input total count of tokens
processed
tasks.result.output_tokens:
type: integer
description: >-
number of tokens in the output total count of tokens
generated in the AI response
tasks.result.reasoning_tokens:
type: integer
description: >-
number of reasoning tokens total count of tokens used to
generate reasoning content
tasks.result.web_search:
type: boolean
description: indicates if web search was used
tasks.result.money_spent:
type: number
description: >-
cost of AI tokens, USD the price charged by the
third-party AI model provider for according to its Pricing
tasks.result.datetime:
type: string
description: >-
date and time when the result was received in the UTC
format: βyyyy-mm-dd hh-mm-ss +00:00β example: 2019-11-15
12:57:46 +00:00
tasks.result.items:
type: array
items:
type: string
description: >-
array of response items contains structured AI response
data
tasks.result.items.reasoning:
type: object
description: element in the response
tasks.result.items.reasoning.type:
type: string
description: >-
type of the element = 'reasoning' Note: this element is
supported only in reasoning models and is not guaranteed
to be returned
tasks.result.items.reasoning.sections:
type: array
items:
type: string
description: >-
reasoning chain sections array of objects containing the
reasoning chain sections generated by the LLM
tasks.result.items.reasoning.sections.type:
type: string
description: type of element='summary_text'
tasks.result.items.reasoning.sections.text:
type: string
description: >-
text of the reasoning chain section text of the reasoning
chain section summarizing the model's thought process
tasks.result.items.message:
type: object
description: element in the response
tasks.result.items.message.type:
type: string
description: type of the element = 'message'
tasks.result.items.message.sections:
type: array
items:
type: string
description: >-
array of content sections contains different parts of the
AI response
tasks.result.items.message.sections.type:
type: string
description: type of element='text'
tasks.result.items.message.sections.text:
type: string
description: AI-generated text content
tasks.result.items.message.sections.annotations:
type: array
items:
type: string
description: >-
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
tasks.result.items.message.sections.annotations.title:
type: string
description: the domain name or title of the quoted source
tasks.result.items.message.sections.annotations.url:
type: string
description: URL of the quoted source
tasks.result.fan_out_queries:
type: array
items:
type: string
description: >-
array of fan-out queries contains related search queries
derived from the main query to provide a more
comprehensive response
'400':
description: Bad request
'401':
description: Unauthorized
'429':
description: Rate limit exceeded
'500':
description: Internal server error
components:
securitySchemes:
BearerAuth:
type: http
scheme: bearer
````
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.