Cloud Vision API
Cloud Vision API
Google Cloud Vision API provides object detection, OCR, face attributes, landmark recognition, and safe-content moderation.
Strong multilingual OCR (Chinese, Japanese, Korean included)
No face identification — detection only
Enable Cloud Vision API, generate an API key. POST to https://vision.googleapis.com/v1/images:annotate with the image (base64 or GCS URL) and a features array (LABEL_DETECTION, TEXT_DETECTION, etc.).
Uptime · 30-day window
About this API
Cloud Vision is Google's image analysis service spanning object recognition, OCR, face attributes, landmark recognition, logo detection, content moderation, and Web Search (reverse image search). One request can combine multiple features — you can get labels, text, and faces in one round trip instead of calling each separately.
The biggest difference from AWS Rekognition is policy: Google does not offer 1:N face identification (detectFaces returns attributes only), sidestepping face-recognition compliance risk. OCR is one of its strongest areas — TEXT_DETECTION handles sparse text, DOCUMENT_TEXT_DETECTION handles dense documents (scanned contracts), and the latter performs well on Asian languages including Chinese, Japanese, and Korean.
Product Search is a smaller but powerful feature — upload a set of product images to build a product set, then send a photo at query time to get visually similar products back. Great for ecommerce "photo to similar item" use cases. AutoML Vision lets you upload small amounts of labeled data to train custom classifiers, deployable to cloud or edge.
What you can build
- 1Moderate user-uploaded images on UGC platforms
- 2OCR documents and handwriting
- 3Auto-tag product photos for search
- 4Recognize landmarks for travel recommendations
Strengths & limitations
Strengths
- Strong multilingual OCR (Chinese, Japanese, Korean included)
- Face detection returns attributes only — no identity matching, lower compliance risk
- Product Search lets you index product images for reverse search
- AutoML Vision trains custom models with small datasets
Limitations
- No face identification — detection only
- Specialized fields (e.g. medical imaging) need AutoML fine-tuning to reach quality bar
- Per-image pricing — large-scale analysis is expensive
Example request
curl https://google.com/<endpoint> \
-H "Authorization: Bearer $API_KEY"
# Some providers use X-Api-Key instead — verify in the docs.Getting started
Enable Cloud Vision API, generate an API key. POST to https://vision.googleapis.com/v1/images:annotate with the image (base64 or GCS URL) and a features array (LABEL_DETECTION, TEXT_DETECTION, etc.).
FAQ
How big is the free tier?+
1,000 calls per feature per month free. Combining multiple features in one request counts as multiple calls.
Can it OCR Chinese?+
Yes — DOCUMENT_TEXT_DETECTION handles printed Chinese well; handwriting is more limited.
Rekognition vs Vision?+
Pick Rekognition for AWS-native stacks. Pick Vision for stronger OCR or non-AWS environments. Note: face identification requires Rekognition (Vision does not match identities).
Technical details
- Auth type
- api_key
- Pricing
- paid
- Protocols
- REST
- SDKs
- python, javascript, java, go, ruby, csharp
- Response time
- 47 ms
- Last health check
- 5/12/2026, 7:37:37 AM
Endpoints
Parsed from the OpenAPI spec. Showing 8 of 8 non-deprecated endpoints.
/v1p1beta1/{parent}/files:annotateprojects/v1p1beta1/{parent}/files:asyncBatchAnnotateprojects/v1p1beta1/{parent}/images:annotateprojects/v1p1beta1/{parent}/images:asyncBatchAnnotateprojects/v1p1beta1/files:annotatefiles/v1p1beta1/files:asyncBatchAnnotatefiles/v1p1beta1/images:annotateimages/v1p1beta1/images:asyncBatchAnnotateimagesMore from Google
Google Workspace Admin SDK API programmatically manages Workspace organizations — users, groups, devices, domains, audit logs, organizational units.
Retrieve AdMob accounts, apps, ad units, ad sources, and generate mediation or network reports.
Work with AdSense Host accounts, ad clients, ad units, reports, and ad code generation from one API surface.
Programmatically manage Apigee organizations, API proxy deployments, attributes, certificates, and hybrid operations.
Google BigQuery API is the REST interface to GCP's flagship data warehouse — execute SQL queries, manage datasets/tables, stream inserts, and use built-in ML.
Control Binary Authorization attestors and policy checks for container images deployed to GKE and Anthos.
Fetch Business Profile location metrics, daily time series, and monthly search keyword impressions.
Google Calendar API lets apps create, read, and update calendar events programmatically — the go-to integration for scheduling apps.