OCR

Extract text and structure from a document or image as markdown using an OCR model.

post/v1/ocr

Request

modelstring required

ID of the OCR model to use.

idstring

include_image_base64boolean

Whether to return extracted images as base64 in the response.

image_limitinteger

image_min_sizeinteger

bbox_annotation_formatobject

document_annotation_formatobject

{
  "model": "mistral-ocr-latest",
  "document": {
    "document_url": "https://arxiv.org/pdf/2201.04234"
  }
}

OCR response.

modelstring

document_annotationstring nullable

Oct 31, 20262902b7e0a589 Revision changes
- breaking
  removed subschema #1 subschema #2 from the request property anyOf list
- info
  added subschema #1 subschema #2 to the request property anyOf list
Sep 6, 20263ab255a22d1b Revision changes
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- breaking
  the response property / became nullable for the status
- info
  added the non-success response with the status
- info
  added the non-success response with the status
- info
  added the non-success response with the status
- info
  added the non-success response with the status