Vision & documents
Amazon Rekognition Custom Labels vs Azure Custom Vision / Azure ML automated ML (AutoML)
Rekognition Custom Labels maps to Azure Custom Vision, but Custom Vision is retiring (supported until September 25, 2028).
Microsoft recommends Azure ML AutoML for images, Foundry models, or Content Understanding for new work.
Side-by-side comparison
| Aspect | Amazon Web Services | Microsoft Azure |
|---|---|---|
| Service | Amazon Rekognition Custom Labels | Azure Custom Vision Deprecated Azure ML automated ML (AutoML) |
| Lifecycle | Generally available | Retirement announced. Full support for existing customers until Sep 25, 2028. Microsoft recommends Azure ML AutoML (images), Foundry models, or Content Understanding. Generally available |
| What it is | Train custom image classification and object detection models from labeled images. | Train custom image classifiers and object detectors. AutoML for classification, regression, forecasting, computer vision, and NLP, from code (SDK/CLI v2) or a no-code studio UI. |
| Pricing model | Billed per training hour and per inference hour while the model is running. | Custom Vision is billed per training hour and per transaction until retirement. AutoML is billed for compute plus endpoint hosting. |
| Docs | Amazon Rekognition Custom Labels docs | Azure Custom Vision docs Azure ML automated ML (AutoML) docs |
| Pricing page | Amazon Rekognition Custom Labels pricing | Azure Custom Vision pricing Azure ML automated ML (AutoML) pricing |
| Exams | AIF-C01 MLA-C01 Retiring | AI-103 AI-300 |
Key differences
- Custom Labels runs as a managed model you start and stop (billed per inference hour).
- Azure ML AutoML for images gives you full control (classification, detection, segmentation) but requires you to deploy and manage an endpoint.
Pricing summary
Pricing models only. No prices are quoted because they change by region and over time.
- AWS
- Billed per training hour and per inference hour while the model is running. Amazon Rekognition Custom Labels pricing →
- Azure
- Custom Vision is billed per training hour and per transaction until retirement. AutoML is billed for compute plus endpoint hosting. Azure Custom Vision pricing → Azure ML automated ML (AutoML) pricing →
Certification exam mapping
| Exam | Provider | Level | Status |
|---|---|---|---|
| AWS Certified AI Practitioner AIF-C01 | AWS | Foundational | current Italian and German versions retire after Oct 15, 2026 (per AWS cert page). |
| AWS Certified Machine Learning Engineer – Associate MLA-C01 | AWS | Associate | retiring Being updated to MLA-C02 (beta registration opened Sep 1, 2026). Last day for MLA-C01 in English was Sep 28, 2026; Korean, Japanese, and Simplified Chinese remain until MLA-C02 GA. |
| Microsoft Certified – Azure AI Apps and Agents Developer Associate AI-103 | Azure | Associate | current Generative AI and agentic solutions with Microsoft Foundry using Python. Successor in scope to the retired AI-102. |
| Microsoft Certified – Machine Learning Operations Engineer Associate AI-300 | Azure | Associate | current MLOps and GenAIOps infrastructure on Azure (IaC with Bicep/CLI, GitHub Actions). Closest successor in scope to the retired DP-100. |
Relevance is based on each exam's published scope, not a line-by-line objective match. Check the official study guide.
FAQ
What is the Azure equivalent of Amazon Rekognition Custom Labels?
Rekognition Custom Labels maps to Azure Custom Vision, but Custom Vision is retiring (supported until September 25, 2028). Microsoft recommends Azure ML AutoML for images, Foundry models, or Content Understanding for new work.
How does pricing compare between Amazon Rekognition Custom Labels and Azure Custom Vision and Azure ML automated ML (AutoML)?
AWS: Billed per training hour and per inference hour while the model is running. Azure: Custom Vision is billed per training hour and per transaction until retirement. AutoML is billed for compute plus endpoint hosting. Check the official pricing pages for current rates.
Which certification exams cover this topic?
AWS Certified AI Practitioner (AIF-C01); AWS Certified Machine Learning Engineer – Associate (MLA-C01) [retiring]; Microsoft Certified – Azure AI Apps and Agents Developer Associate (AI-103); Microsoft Certified – Machine Learning Operations Engineer Associate (AI-300).