Language & translation · AWS vs Google Cloud
Amazon Comprehend vs Gemini model tuning
Comprehend custom classification and entity recognition have no direct counterpart since AutoML Text shut down on Jun 15, 2025.
Google recommends prompting or tuning Gemini instead.
Side-by-side comparison
| Aspect | Amazon Web Services | Google Cloud |
|---|---|---|
| Service | Amazon Comprehend | Gemini model tuning |
| Lifecycle | Topic modeling, event detection, and prompt safety classification are no longer available to new customers (maintenance, Mar 31, 2026). Other features are unaffected. | Generally available |
| What it is | NLP. Entities, key phrases, sentiment and targeted sentiment, language detection, PII, syntax, toxicity, and custom classification/entity recognition. | Supervised fine-tuning and preference tuning for Gemini models, embedding tuning, and tuning of open models from Model Garden. |
| Pricing model | Training time, model storage per month, and real-time endpoint inference units per second (or async per-unit). | Tuning is billed by training tokens; inference by token. |
| Docs | Amazon Comprehend docs | Gemini model tuning docs |
| Pricing page | Amazon Comprehend pricing | Gemini model tuning pricing |
Key differences
- Gemini tuning replaces AutoML Text; you get a tuned generative model, not a dedicated classifier endpoint.
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 →
- GCP
- Tuning is billed by training tokens; inference by token. Gemini model tuning pricing →
And on Azure?
Direct match Azure's equivalent is Azure Language. AWS vs Azure comparison →
FAQ
What is the Google Cloud equivalent of Amazon Comprehend?
Comprehend custom classification and entity recognition have no direct counterpart since AutoML Text shut down on Jun 15, 2025. Google recommends prompting or tuning Gemini instead.
How does pricing compare between Amazon Comprehend and Gemini model tuning?
AWS: Training time, model storage per month, and real-time endpoint inference units per second (or async per-unit). Google Cloud: Tuning is billed by training tokens; inference by token. Check the official pricing pages for current rates.
What is the Azure equivalent?
Azure Language (direct match). Comprehend custom classification and custom entity recognition map to Azure Language custom text classification (legacy) and custom NER (core).