Skip to main content
POST
web.extract-site

Authorizations

Authorization
string
header
required

API key: sk_live_…

Headers

Idempotency-Key
string

Optional. A retry with the same key returns the stored result.

Maximum string length: 255
Pramaan-Max-Price-Micro
string

Optional. The most this request may be priced at, in micro-USD (a whole number above 0). It replaces the capability's own price ceiling for this request, lower or higher. Sources that could cost more are left out; when none is left the answer is 400 with the lowest limit that would work.

Pattern: ^[1-9]\d{0,14}$

Body

application/json
urls
string[]
required

One to ten URLs, without duplicates.

Required array length: 1 - 10 elements

Public exact URL or an explicitly enabled site path ending in /*.

Required string length: 1 - 2048
schema
object

JSON object schema for the extracted fields; only local references.

prompt
string

What to extract; send a schema, a prompt or both.

Required string length: 1 - 2000
allowExpansion
boolean
default:false

Explicitly allow wildcard, search or subdomain discovery; it uses the larger fixed ceiling.

Use web search to discover additional sources; requires allowExpansion.

ignoreSitemap
boolean
default:false

Skip sitemap discovery during expansion.

includeSubdomains
boolean
default:false

Expand to subdomains; requires allowExpansion.

showSources
boolean
default:false

Include factual source links when returned.

onlyMainContent
boolean
default:true

Read main document content.

includeTags
string[]

Keep only these page parts.

Maximum array length: 20

CSS selector to keep.

Required string length: 1 - 2048
excludeTags
string[]

Drop these page parts.

Maximum array length: 20

CSS selector to omit.

Required string length: 1 - 2048
maxPages
integer
default:100

PDF page cap per source; default 100, maximum 1,000.

Required range: 1 <= x <= 1000
pdfMode
enum<string>
default:auto

PDF text extraction or optical character recognition, which reads scanned pages.

Available options:
auto,
fast,
ocr

Response

Job started; poll GET /v1/jobs/{id}

job_id
string
required
status
enum<string>
required
Available options:
running
held_micro
integer
required

The credit set aside for the job (its estimate), micro-USD; 0 when it takes none. Not a price: what the job is charged reads on GET /v1/jobs/{id} once it is settled.