Skip to main content
Completed Parse and Extract submissions return document fields at the top level, without a wrapper object. Retrieval of either a Parse or Extract job places the completed document inside result alongside the job’s status and error.
  • Read markdown for Markdown output or elements for individual document elements.
  • Read extracted_data[i].data for extracted fields.
  • Inspect warnings when present, including for completed_with_warnings.
  • Read source.file_id, source.filename, source.mimetype, and source.expires_at when source is present. source can be null when the associated input is unknown.
  • An absent field_metadata property supplies no citation metadata. It does not imply a confidence score.
For completed_with_warnings, see how to inspect warnings. See the captured Parse response, Extract response, and job lifecycle.