Process Ocr

Process a document using OCR (Optical Character Recognition).

This endpoint extracts text and structure from documents (PDFs, images) and returns the content in markdown format. It supports multiple document types and can extract images embedded within documents.

The extracted markdown preserves document structure including headings, tables, lists, and other formatting.

POST /ocr

cURL

cURL

curl -X POST https://api.opper.ai/v2/ocr \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${OPPER_API_KEY}" \
  -d '{
    "model": "mistral/mistral-ocr-latest",
    "document": {
      "type": "document_url",
      "document_url": "https://example.com/sample.pdf"
    }
  }'

200

{
  "id": "<string>",
  "pages": [
    {
      "index": 123,
      "markdown": "<string>",
      "dimensions": {
        "dpi": 123,
        "height": 123,
        "width": 123
      },
      "images": [
        {
          "id": "<string>",
          "top_left_x": 123,
          "top_left_y": 123,
          "bottom_right_x": 123,
          "bottom_right_y": 123,
          "image_base64": "<string>"
        }
      ],
      "elements": [
        {
          "type": "<string>",
          "label": "<string>",
          "text": "<string>",
          "bbox": {},
          "data": {}
        }
      ]
    }
  ],
  "model": "<string>",
  "usage_info": {
    "pages_processed": 123,
    "doc_size_bytes": 123,
    "processing_time_seconds": 123,
    "time_per_page_seconds": 123,
    "applied_settings": {}
  },
  "cost": {
    "generation": 123,
    "platform": 123,
    "total": 123
  }
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request model for OCR processing.

model · string · required

The OCR model to use

Example:

"mistral/mistral-ocr-latest"

document · OCRDocument · object · required

The document to process

Show child attributes

pages · integer[] | null

Specific page indices to process (0-based). If not specified, all pages are processed.

include_image_base64 · boolean · default: false

Whether to include base64-encoded images in the response

image_limit · integer | null

Maximum number of images to extract per page

Required range: x >= 1

image_min_size · integer | null

Minimum size (width or height in pixels) for images to be included

Required range: x >= 1

mistral_extra · MistralOCRExtra · object

Mistral-specific OCR parameters

Show child attributes

docling_extra · DoclingOCRExtra · object

Docling-specific OCR parameters (output_format, ocr_engine, force_ocr, table_mode)

Show child attributes

Response

200

application/json

Successful Response

Response model for OCR processing.

id · string · required

Unique identifier for this OCR request

pages · OCRPageResult · object[] · required

Processed page results

Show child attributes

model · string · required

The model used for OCR

usage_info · OCRUsageInfo · object · required

Usage information

Show child attributes

cost · OCRCost · object

Cost information for this OCR request

Show child attributes