Language & translation
Amazon Comprehend vs Azure Language
Comprehend custom classification and custom entity recognition map to Azure Language custom text classification (legacy) and custom NER (core).
Side-by-side comparison
| Aspect | Amazon Web Services | Microsoft Azure |
|---|---|---|
| Service | Amazon Comprehend | Azure Language |
| Lifecycle | Topic modeling, event detection, and prompt safety classification are no longer available to new customers (maintenance, Mar 31, 2026). Other features are unaffected. | "Core" (recommended): PII, language detection, NER, custom NER, and Text Analytics for health. "Legacy" (supported for existing implementations): sentiment and opinion mining, key phrases, entity linking, summarization, custom text classification, question answering, CLU, and orchestration. |
| What it is | NLP. Entities, key phrases, sentiment and targeted sentiment, language detection, PII, syntax, toxicity, and custom classification/entity recognition. | Text NLP APIs, also exposed as tools via the Azure Language MCP server. |
| Pricing model | Training time, model storage per month, and real-time endpoint inference units per second (or async per-unit). | Training hours, model hosting, and per-text-record inference. |
| Docs | Amazon Comprehend docs | Azure Language docs |
| Pricing page | Amazon Comprehend pricing | Azure Language pricing |
| Exams | AIF-C01 MLA-C01 Retiring | AI-103 |
Key differences
- Comprehend custom models accept plain text, and also PDF, Word, and images (for custom classification and entity recognition).
- On Azure, custom NER is a "core" capability, while custom text classification is "legacy". For new classification work, Microsoft leans toward Foundry models.
Pricing summary
Pricing models only. No prices are quoted because they change by region and over time.
- AWS
- Training time, model storage per month, and real-time endpoint inference units per second (or async per-unit). Amazon Comprehend pricing →
- Azure
- Training hours, model hosting, and per-text-record inference. Azure Language 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. |
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 Comprehend?
Comprehend custom classification and custom entity recognition map to Azure Language custom text classification (legacy) and custom NER (core).
How does pricing compare between Amazon Comprehend and Azure Language?
AWS: Training time, model storage per month, and real-time endpoint inference units per second (or async per-unit). Azure: Training hours, model hosting, and per-text-record inference. 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).