Computer Vision Client
Computer Vision Client
Bing Computer Vision API analyzes images — OCR, object detection, face detection, scene captioning, content moderation.
Read API's OCR quality is industry-leading for both English and Chinese
Face identify (identification) service was restricted for new customers in 2022 due to policy
Create a Computer Vision resource in Azure for endpoint + key. POST /vision/v3.2/read/analyze to submit an OCR job; GET to fetch results.
Uptime · 30-day window
About this API
Computer Vision is Azure Cognitive Services' vision intelligence API, bundling multiple capabilities: Read API (OCR — strong on both handwritten and printed text), Analyze Image (scene captioning, tag generation, brand detection), Detect Objects (bounding boxes), Generate Thumbnail (smart crop), Content Moderation (NSFW, violence detection). Each capability is independent — no model training needed. Compared to Google Cloud Vision and AWS Rekognition, Microsoft has traditional strengths in OCR (especially Chinese handwriting) and scene captioning. Note: Face Identify (identifying specific people in photos) has been restricted to limited domains for new customers since 2022.
What you can build
- 1Bulk OCR text from images/PDFs
- 2Auto-moderate UGC image uploads
- 3Auto-tag e-commerce product images
- 4Generate alt-text descriptions for visually impaired users
Strengths & limitations
Strengths
- Read API's OCR quality is industry-leading for both English and Chinese
- Multiple capabilities (detection, captioning, moderation) in one API
- Batch async jobs supported
Limitations
- Face identify (identification) service was restricted for new customers in 2022 due to policy
- Not suitable for diagnostic medical imaging
Example request
curl https://microsoft.com/<endpoint>Getting started
Create a Computer Vision resource in Azure for endpoint + key. POST /vision/v3.2/read/analyze to submit an OCR job; GET to fetch results.
FAQ
Does OCR support Chinese?+
Yes. Read API v3.2+ has high-quality recognition for Simplified/Traditional Chinese including handwriting.
Can it identify specific people?+
Face API detect/group is available; identify (matching to known people) has been restricted to approved use cases since 2022.
What's the max input size?+
Read API: 500MB / 2000 pages (PDF) per file. Sync analysis: 4MB max.
Technical details
- Auth type
- unknown
- Pricing
- unknown
- Protocols
- REST
- SDKs
- python, javascript, csharp, java, go
- Response time
- 307 ms
- Last health check
- 5/12/2026, 7:37:52 AM
More from Microsoft
Bing Autosuggest API returns search suggestions from a partial query — for search-box type-ahead completion.
Bing Custom Image Search restricts image search to a custom set of domains — the image counterpart of Bing Custom Search.
Bing Custom Search lets you define a custom domain subset and run Bing search against it — for vertical or enterprise search.
Custom Vision Prediction API runs inference using your trained Custom Vision model — upload an image, get classification labels and confidence scores.
Custom Vision Training API programmatically trains image-classification / object-detection models — create projects, upload labeled images, trigger training, publish iterations.
Bing Entity Search recognizes queries as named entities (people, places, organizations) and returns structured card info (description, image, related links).
Bing Image Search runs image search over Bing's web-wide image index — by keyword, similar image, aspect ratio, or size filter.
Bing Local Business Search finds local businesses (restaurants, hotels, hospitals) by geographic query — returns business info, address, ratings.