Google OCR

When calling the API described on this page, the ID of a specific model is not provided. The request is made solely by specifying the correct method URL and valid parameters.

Model Overview

This API provides a feature to extract characters from images.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

Extract text from images using OCR.

post

Performs optical character recognition (OCR) to extract text from images, enabling text-based analysis, data extraction, and automation workflows from visual data.

Authorizations

access-token

AuthorizationstringRequired

Bearer key

Body

application/json

modelundefined · enumOptionalPossible values:

documentany ofRequired

The document file to be processed by the OCR model.

string · uriOptional

or

stringOptional

mimeTypestring · enumOptional

The MIME type of the document.

Possible values:

pagesany ofOptional

Specific pages you wants to process

or

or

or

Responses

201

Successfully processed document with OCR

application/json

post

/v1/ocr

HTTPcURLJavaScriptPython

POST /v1/ocr HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 130

{
  "model": "google/gc-document-ai",
  "document": "https://example.com",
  "mimeType": "application/pdf",
  "pages": {
    "type": "start",
    "start": 1
  }
}

201

Successfully processed document with OCR

{
  "pages": [
    {
      "index": 1,
      "markdown": "text",
      "images": [
        {
          "id": "text",
          "top_left_x": 1,
          "top_left_y": 1,
          "bottom_right_x": 1,
          "bottom_right_y": 1,
          "image_base64": "https://example.com"
        }
      ],
      "dimensions": {
        "dpi": 1,
        "height": 1,
        "width": 1
      }
    }
  ],
  "model": "mistral-ocr-latest",
  "usage_info": {
    "pages_processed": 1,
    "doc_size_bytes": 1
  }
}