extract

Extract structured data synchronously

Changed on Aug 18, 2026

Admit a single extract job from file bytes, file_id, or a tenant-owned succeeded parse_job_id, then run schema-constrained OpenRouter extraction via llm_model. A parse_job_id source reuses the canonical ParsedDocument (from dual artifacts or legacy result_json) without OCR or another page charge; historical raw-only parses return 422 canonical_result_unavailable. Wait up to the sync wait limit and return ExtractionTerminalResult when ready. Terminal failed within the wait window returns 422; terminal indeterminate returns 504. Returns 202 with a durable job reference and Location if the wait expires.

post/extract

Request

Base URL: https://api.openparser.dev
URL: https://api.openparser.dev/extract
Auth: HTTP bearer

Headers

Idempotency-Keystring required

Client-supplied idempotency key. Required on every parse or extract POST. Must be unique per distinct request body for a given tenant and operation.

Response

Terminal extraction result

outputunknown required

llm_modelstring required

OpenRouter model slug from the compatible OCR extraction catalog (GET /models/llm). Unknown or deprecated values return 422 unsupported_llm_model. Any currently compatible model may be used for extract and field grounding.

parse_job_idstring

Prefixed public id for an OCR job (opj_…).

Changes

Aug 18, 2026750d37b8455d Revision changes
- info
  added the optional property /// to the response with the status
- info
  added the optional property /// to the response with the status
- info
  added the optional property /// to the response with the status
- info
  added the optional property /// to the response with the status
- info
  added the optional property to the response with the status
Aug 4, 20264561194517a8 Revision changes
- breaking
  added 'propertyNames' constraint to the request property /
- breaking
  the ////// response's property type changed from integer to number for status
- breaking
  the ////// response's property type changed from integer to number for status
- breaking
  the ////// response's property type changed from integer to number for status
- breaking
  the ////// response's property type changed from integer to number for status
- breaking
  the ///// response's property type changed from number to object for status
- breaking
  removed the required property ///// from the response with the status
- breaking
  removed the required property / from the response with the status
- breaking
  removed the required property / from the response with the status
- breaking
  removed the required property / from the response with the status
- breaking
  removed the required property / from the response with the status
- breaking
  removed the required property / from the response with the status
- warning
  removed the request property //
- warning
  removed the request property //
- warning
  removed the request property //
- warning
  removed the optional property ///// from the response with the status
- warning
  removed the optional property ///// from the response with the status
- warning
  removed the optional property ///// from the response with the status
- warning
  added the new element enum value to the ///// response property for the response status
- warning
  added the new link enum value to the ///// response property for the response status
- warning
  added the new other enum value to the ///// response property for the response status
- warning
  added the new query_answer enum value to the ///// response property for the response status
- warning
  added the new section enum value to the ///// response property for the response status
- warning
  added the new selection_mark enum value to the ///// response property for the response status
- warning
  added the new stamp enum value to the ///// response property for the response status
- warning
  added the new table_cell enum value to the ///// response property for the response status
- warning
  added the new text_span enum value to the ///// response property for the response status
- info
  added the optional property ////// to the response with the status
- info
  added the optional property ////// to the response with the status
- info
  added the optional property ///// to the response with the status
- info
  added the optional property ///// to the response with the status
- info
  removed the block enum value from the ///// response property for the response status
- info
  removed the checkbox enum value from the ///// response property for the response status
- info
  removed the header_footer enum value from the ///// response property for the response status
- info
  removed the heading enum value from the ///// response property for the response status
- info
  removed the region enum value from the ///// response property for the response status
- info
  added the required property ////// to the response with the status
- info
  added the required property ////// to the response with the status
- info
  added the required property ////// to the response with the status
- info
  added the required property ///// to the response with the status
- info
  added the required property / to the response with the status
- info
  added the required property / to the response with the status
- info
  added the required property / to the response with the status
- info
  added the required property / to the response with the status
- info
  added the required property / to the response with the status
- info
  added the required property / to the response with the status
- info
  added the required property / to the response with the status

Operation history