Skip to main content
POST
Extract Structured Web Data

Request contract

  • Method and path: POST /apis/v1/context-dev/extract-structured-web-data
  • Availability: enabled
  • Request URL template: https://api.aisa.one/apis/v1/context-dev/extract-structured-web-data
  • Runtime facts: 3068b7678674e2539daed47d533143c7d5bf21072a81e6aac34d7bd71ed57eb3
Complete OpenAPI definition Effective request and pricing declaration (including authentication and referenced schemas):

Cost and request rules

Usage-based billing; Default request estimate: $0.0103 USD (not a fixed price). Declared unit rate: $0.000001 USD per provider_credit. Account-specific pricing and final settlement may differ. Published reference values are not an account-specific quote or a settled charge. For endpoints supporting X-AISA-Cost-Mode: quote, obtain a free quote for your exact request before execution; reconcile the settled cost with response metadata and Usage Logs. USD amounts use 1,000,000 integer micro-USD per dollar.
  • Default request reference estimate (USD): 0.0103
  • Declared unit rate (USD): 1e-06
  • Billing unit: provider_credit
  • Cost contract: response_units
  • Published reference multiplier: 1.0
  • Declared maximum count/units: 10000000
  • Settlement evidence source: response_body

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
url
string<uri>
required

Starting HTTP or HTTPS website URL to crawl.

Minimum string length: 1
Example:

"https://example.com"

output_schema
object
required

JSON Schema describing the object to extract. Add descriptions to non-obvious properties so the extractor can interpret them correctly.

Example:
tags
string[]

Usage-tracking tags. Provide at most 20 tags of 1-50 characters each.

Maximum array length: 20
Required string length: 1 - 50
max_depth
integer

Maximum link depth from the starting URL. Use 0 to analyze only the starting page; omit for no crawl-depth limit.

Required range: x >= 0
max_pages
integer
default:5

Maximum pages to analyze (1-50). Higher values increase the price.

Required range: 1 <= x <= 50
fact_check
boolean
default:false

Require every returned value to be grounded in page content. Unsupported fields are returned as null or empty instead of inferred.

instructions
string

Optional extraction guidance or field interpretation, up to 2000 characters.

Maximum string length: 2000
stop_after_ms
integer
default:80000

Soft crawl time budget in milliseconds (10000-110000).

Required range: 10000 <= x <= 110000
follow_subdomains
boolean
default:false

Follow links on subdomains of the starting domain.

Response

Tool result data

url
string
required
data
object
required
metadata
object
required
key_metadata
object
urls_analyzed
string[]