OCR
Document to run OCR on
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.
Include image URLs in response
Max images to extract
Minimum height and width of image to extract
Specify the format that the model must output. By default it will use { "type": "text" }. Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is in JSON. When using JSON mode you MUST also instruct the model to produce JSON yourself with a system or a user message. Setting to { "type": "json_schema" } enables JSON schema mode, which guarantees the message the model generates is in JSON and follows the schema you provide.
Optional prompt to guide the model in extracting structured output from the entire document. A document_annotation_format must be provided.
Extract the page header into the response's header field and remove it from the markdown content
Extract the page footer into the response's footer field and remove it from the markdown content
Return paragraph-level bounding boxes for all content blocks in the response
Granularity for confidence scores: 'page' (aggregate only), 'word' (per-word scores). Defaults to None (no confidence scores) to keep response payload small.
{ "bbox_annotation_format": { "type": "text" }, "document_annotation_format": { "type": "text" } }
Successful Response
List of OCR info for pages.
The model used to generate the OCR.
Formatted response in the request_format if provided in json str