Optional prompt to guide the model in extracting structured output from the entire document. A document_annotation_format must be provided.
extract_footerboolean
Whether to extract the footer of the document.
extract_headerboolean
Whether to extract the header of the document.
image_limitinteger nullable
Max images to extract
image_min_sizeinteger nullable
Minimum height and width of image to extract
include_image_base64boolean nullable
Include image URLs in response
modelstring nullable
The model to use for the OCR.
pagesinteger[] nullable
Specific pages to process. Accepts a list of integers or a string of comma-separated numbers and ranges (e.g. '0,1,2' or '0-5' or '0,2-4'). Page numbers start from 0.
table_format'markdown' | 'html' nullable
Format for table extraction: 'markdown' (default) or 'html'.