Web

Extract structured data

Extracts structured data across one or more URLs, guided by a prompt and optional JSON schema. Asynchronous — returns a queued job; poll GET /v1/jobs/{id} for the data. Charges credits on completion.

post/web/extract

Request

  • Base URL: https://api.crevio.co/v1
  • URL: https://api.crevio.co/v1/web/extract
  • Auth: API key in header Authorization

Headers

Idempotency-Keystring

Makes this write safe to retry: a repeat with the same key replays the first response instead of creating a second resource. Scoped to the account, remembered for 24 hours; reusing a key with a different payload is an error.

Request body

urlsstring[] required

URLs to extract from.

promptstring required

What to extract.

schemaobject

Optional JSON schema for the output shape.

Response

Job queued

idstring required
objectstring required
typestring required
status'queued' | 'processing' | 'completed' | 'failed' | 'cancelled' required
modelstring required
progressinteger required
inputobject required
resultobject nullable required
errorstring nullable required
error_codestring nullable required
credits_usedinteger nullable required
provider_request_idstring nullable required
created_atstring date-time required
started_atstring date-time nullable required
completed_atstring date-time nullable required

Changes

No recorded changes to this operation across all 2 revisions of this API.