Vision APIs

Pre-trained perception models.

Production-ready computer vision APIs. Object detection, OCR, face analysis, image segmentation, and visual search. No ML expertise needed.

COMPUTER VISION AI PIPELINE1. RAW IMAGE INPUTBUS 98%PERSON 95%2. VISION AI ENGINE📦OBJECT DETECTION🔤OPTICAL CHARACTER REC🙂FACE & LANDMARKS🛡️EXPLICIT CONTENT MODresponse.json{"responses": [{"labelAnnotations": [{"desc": "Bus","score": 0.98},{"desc": "Person","score": 0.95}],"textAnnotations": [{"text": "STOP"}],"safeSearch": {"adult": "UNLIKELY"}}]Edge TPU OptimizedLatency < 50ms

10+

Models

< 100 ms

Latency

99.5%

Accuracy

Image/Video

Input

See everything.

Object detection, OCR, visual search.

Object detection

Detect and classify 1000+ object types with bounding boxes.

OCR

Extract text from images and documents. 60+ languages.

Face analysis

Age, emotion, and landmark detection. No face recognition.

Image segmentation

Pixel-level segmentation for scene understanding.

Visual search

Find similar images in your catalog using visual embeddings.

Custom models

Fine-tune models on your data with AutoML.

Getting started

Launch your first instance in three steps. CLI, console, or API — your choice.

Terminal
curl https://api.ur.com/v1/vision/detect \
  -H "Authorization: Bearer $KEY" \
  -F "[email protected]"

Vision patterns.

Product search and document processing.

Visual product search

Search products by photo in e-commerce catalogs.

View tutorial

Suggested configuration

Visual search · Embeddings · 99.5%

Estimate your costs

Create detailed configurations to see exactly how much your architecture will cost. Pay for what you use, down to the second.

Configuration 1

Estimated: $44.20/mo

Computer Vision

Usage Volume

K

Infrastructure

GB

Options

Premium SLA (99.99%)+25% for guaranteed availability
Config 1 cost$44.20

Cost details

$44.20

Pre-trained models. Custom training available.

Configuration 1
$44.20
2× standard Replica(s)$29.20
Request Processing$10.00
Storage$5.00

Works seamlessly with

LLM API
S3
Functions
IAM
Logging
Analytics

Frequently asked questions

See everything.

Object detection, OCR, visual search. 99.5% accuracy.