Google Cloud Vision

API

Google Cloud API for image labels, OCR, faces, logos and SafeSearch

Price: Free tier, then pay per use
Access: Google Cloud credentials

Docs

About

Google Cloud image analysis API that returns labels, printed and handwritten text, faces, landmarks, logos, objects and SafeSearch ratings for explicit content. Each feature run on each image is billed as one unit; the first 1,000 units a month are free.

What you can do with it

Extract printed and handwritten text from photos, scans and PDF pages
Label images, find logos and landmarks, and find where an image appears online
Rate uploads for adult, violent and racy content with SafeSearch

Get started

Enable billing and the Cloud Vision API in a Google Cloud project
Sign in with the gcloud CLI to get an access token

Example

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "x-goog-user-project: $PROJECT_ID" \
  -H "Content-Type: application/json; charset=utf-8" \
  -d '{"requests": [{"image": {"source": {"imageUri": "gs://cloud-samples-data/vision/ocr/sign.jpg"}},
       "features": [{"type": "TEXT_DETECTION"}, {"type": "SAFE_SEARCH_DETECTION"}]}]}' \
  "https://vision.googleapis.com/v1/images:annotate"

Details

Hosting: Hosted service
Available in: Worldwide
Official SDKs: C#, Go, Java, JavaScript/TypeScript, PHP, Python, Ruby
MCP server: None
Works with: Google Cloud