Cloud Vision pricing
The Vision API provides a set of features for analyzing images. Across these scenarios, we enable you to pay only for what you use with no upfront commitments. The API supports the following features:
Feature type | |
---|---|
CROP_HINTS |
Determine suggested vertices for a crop region on an image. |
DOCUMENT_TEXT_DETECTION |
Perform OCR on dense text images, such as documents (PDF/TIFF), and images with
handwriting.
TEXT_DETECTION can be used for sparse text images.
Takes precedence when both DOCUMENT_TEXT_DETECTION and
TEXT_DETECTION are present.
|
FACE_DETECTION |
Detect faces within the image. |
IMAGE_PROPERTIES |
Compute a set of image properties, such as the image's dominant colors. |
LABEL_DETECTION |
Add labels based on image content. |
LANDMARK_DETECTION |
Detect geographic landmarks within the image. |
LOGO_DETECTION |
Detect company logos within the image. |
OBJECT_LOCALIZATION |
Detect and extract multiple objects in an image. |
SAFE_SEARCH_DETECTION |
Run SafeSearch to detect potentially unsafe or undesirable content. |
TEXT_DETECTION |
Perform Optical Character Recognition (OCR) on text within the image.
Text detection is optimized for areas of sparse text within a larger image.
If the image is a document (PDF/TIFF), has dense text, or contains handwriting,
use DOCUMENT_TEXT_DETECTION instead.
|
WEB_DETECTION |
Detect topical entities such as news, events, or celebrities within the image, and find similar images on the web using the power of Google Image Search. |
Prices
Charges are incurred per image. For files with multiple pages, such as PDF files, each page is treated as an individual image.
Each feature applied to an image is a billable unit. For example, if you apply Face Detection and Label Detection to the same image, you are billed for one unit of Label Detection and one unit for Face Detection.
The table below shows the price for each feature per 1000 units. Pricing is tiered - the first 1000 units used each month are free, units 1001 to 5,000,000 are priced as marked, etc.
The final 1000-unit block is prorated out of 1000 units.
Feature | Price per 1000 units | |||
---|---|---|---|---|
First 1000 units/month | Units 1001 - 5,000,000 / month | Units 5,000,001 and higher / month | ||
Label Detection | Free | $1.50 | $1.00 | |
Text Detection | Free | $1.50 | $0.60 | |
Document Text Detection | Free | $1.50 | $0.60 | |
Safe Search (explicit content) Detection | Free | Free with Label Detection, or $1.50 | Free with Label Detection, or $0.60 | |
Facial Detection | Free | $1.50 | $0.60 | |
Facial Detection - Celebrity Recognition | Free | $1.50 | $0.60 | |
Landmark Detection | Free | $1.50 | $0.60 | |
Logo Detection | Free | $1.50 | $0.60 | |
Image Properties | Free | $1.50 | $0.60 | |
Crop Hints | Free | Free with Image Properties, or $1.50 | Free with Image Properties, or $0.60 | |
Web Detection | Free | $3.50 | Contact Google for more information | |
Object Localization | Free | $2.25 | $1.50 |
If you pay in a currency other than USD, the prices listed in your currency on Cloud Platform SKUs apply.
Example
If your application made the following requests in a particular month:
- 700 images with label detection
- 5300 images with landmark detection
Your cost would be:
- $0 for 700 label detection requests.
- $0 for the first 1000 landmark detection requests.
- $6.45 for the remaining 4300 landmark detection requests. Pricing is calculated in 1000-request blocks with the final request block prorated out of 1000. For example, exactly 4000 requests is priced at (4 * $1.50) . Any number of requests between 4001 and 5000 (including the 4300 requests in this example) moves the total into the next (5th) block of 1000 and is priced at (300/1000 * 1.50), adding another $0.45 to the existing cost and bringing the total cost to $6.45.
Total cost is $6.45.
Google Cloud Platform costs
You may be charged for other Google Cloud resources used in your project, such as Compute Engine instances, Cloud Storage, etc. For full information, consult our Google Cloud Platform Pricing Calculator to determine those separate costs based on current rates.
What's next
- Read the Cloud Vision documentation.
- Get started with Cloud Vision.
- Try the Pricing calculator.
- Learn about Cloud Vision solutions and use cases.