Authorizations
Body
- Option 1
- Option 2
PDF or image to upload (required if no fileUrl). Allowed: .pdf, .jpg, .jpeg, .png
Required schema definition describing the fields to extract.
Publicly accessible URL of the file to process (required if no file).
Fast path that extracts directly from pages without full pipeline post-processing.
Optional additional context or instructions to guide the extraction process. Useful for providing domain-specific guidance or clarifications about the document.
If true, includes image metadata in each page of the response.
Response
Successful schema extraction
Model's structured output matching the provided schema. Will return as a stringified object.
fast, slow Present in slow mode.
Confidence score (0-100) indicating extraction reliability, present in slow mode.
Image metadata entries for this extraction (present if imageMetadataDetect=true).