"Confidence" field missing in the paid version of the cloud vision API's JSON response for OCR

Question

The JSON response from the free version of Vision API (https://cloud.google.com/vision/docs/drag-and-drop) has the field named "Confidence" which shows the recognition confidence of the model on the word level and character level. While in the paid version this field is missing. The example JSON is as under.

Drag-and-Drop output JSON structure:

{
    "boundingBox": {
        "vertices": [
            {
                "x": 85,
                "y": 7
            },
            {
                "x": 92,
                "y": 7
            },
            {
                "x": 92,
                "y": 26
            },
            {
                "x": 85,
                "y": 26
            }
        ]
        },
    "text": "abc xyz",
    "confidence": 0.99
}

Paid version output structure:

{
    "description": "abc xyz", 
    "boundingPoly": {
        "vertices": [ 
            {"y": 437, "x": 2108}, 
            {"y": 437, "x": 2194}, 
            {"y": 453, "x": 2194}, 
            {"y": 453, "x": 2108}]
    }
}

Is this feature in the testing stage and not available to any paid user? I want to use the character level model confidence, how can I use?

Answer 1

For text_detection currently no character level confidence as it is using a different model comparing to document_text_detection.