Vision

0.5 credits

Analyze images using Google Cloud Vision. Supports labels, OCR, logos, landmarks, objects, and more.

POST/api/v1/tools/google/vision

Parameters

imageUrlstringrequired

URL of the image to analyze. Must be publicly accessible. Use direct image URLs, not pages containing images.

featuresstring[]required

At least one required. Options: labels, ocr, logos, landmarks, objects, faces, web, safe_search, image_properties, crop_hints. Only requested features appear in the response.

Response Schema

dataobject

Vision analysis results (fields depend on requested features)

labelsobject[]

Detected labels

textobject

OCR result

logosobject[]

Detected logos

landmarksobject[]

Detected landmarks

objectsobject[]

Detected objects with bounding boxes

safeSearchobject

Safe search annotations

webobject

Web detection (similar images, entities)

metaobject

Request metadata

toolstring

Tool name (vision)

creditsUsednumber

Credits consumed (0.5)

requestIdstring

Unique request ID

Request

curl -X POST https://scraper.run/api/v1/tools/google/vision \
  -H "Authorization: Bearer sc_live_..." \
  -H "Content-Type: application/json" \
  -d '{"imageUrl": "https://example.com/photo.jpg", "features": ["labels", "ocr"]}'

Response Example

{
  "data": {
    "labels": [
      {
        "name": "Coffee",
        "score": 0.97
      },
      {
        "name": "Cup",
        "score": 0.95
      },
      {
        "name": "Drink",
        "score": 0.92
      }
    ],
    "text": {
      "full": "Starbucks Reserve",
      "annotations": [
        "..."
      ]
    }
  },
  "meta": {
    "tool": "google-vision",
    "creditsUsed": 0.5,
    "requestId": "req_abc123"
  }
}