Vision & documents · AWS vs Google Cloud
Amazon Rekognition vs Cloud Vision API / Gemini models on Agent Platform
Amazon Rekognition Image maps to the Cloud Vision API (labels, objects, text, faces, landmarks, logos, SafeSearch), with Gemini for open-ended image understanding.
Side-by-side comparison
| Aspect | Amazon Web Services | Google Cloud |
|---|---|---|
| Service | Amazon Rekognition | Cloud Vision API Gemini models on Agent Platform |
| Lifecycle | Streaming Events and Batch Image Content Moderation are in maintenance (Mar 31, 2026). Person Pathing was fully shut down Oct 31, 2025. | Generally available Generally available |
| What it is | Prebuilt image and video analysis. Labels, text, moderation, face detection, comparison and search, celebrity recognition, and Face Liveness. | Pretrained image analysis (labels, objects, OCR, faces without identity, landmarks, logos, SafeSearch). Google's first-party models (Gemini, Gemma, Veo, Lyria, embeddings) served per token or per output unit through the Agent Platform API. |
| Pricing model | Per image processed, tiered by monthly volume, plus per face-metadata stored. | Cloud Vision is billed per 1,000 units (one feature on one image), with a monthly free tier. Gemini is billed per token. |
| Docs | Amazon Rekognition docs | Cloud Vision API docs Gemini models on Agent Platform docs |
| Pricing page | Amazon Rekognition pricing | Cloud Vision API pricing Gemini models on Agent Platform pricing |
Key differences
- Cloud Vision detects faces and facial attributes but does not identify individuals.
- Gemini can answer free-form questions about images, which neither pretrained API does.
Pricing summary
Pricing models only. No prices are quoted because they change by region and over time.
- AWS
- Per image processed, tiered by monthly volume, plus per face-metadata stored. Amazon Rekognition pricing →
- GCP
- Cloud Vision is billed per 1,000 units (one feature on one image), with a monthly free tier. Gemini is billed per token. Cloud Vision API pricing → Gemini models on Agent Platform pricing →
And on Azure?
Partial match Azure's equivalent is Azure Vision – Image Analysis, Microsoft Foundry Models (incl. Azure OpenAI), Azure Content Understanding. AWS vs Azure comparison →
FAQ
What is the Google Cloud equivalent of Amazon Rekognition?
Amazon Rekognition Image maps to the Cloud Vision API (labels, objects, text, faces, landmarks, logos, SafeSearch), with Gemini for open-ended image understanding.
How does pricing compare between Amazon Rekognition and Cloud Vision API and Gemini models on Agent Platform?
AWS: Per image processed, tiered by monthly volume, plus per face-metadata stored. Google Cloud: Cloud Vision is billed per 1,000 units (one feature on one image), with a monthly free tier. Gemini is billed per token. Check the official pricing pages for current rates.
What is the Azure equivalent?
Azure Vision – Image Analysis, Microsoft Foundry Models (incl. Azure OpenAI) and Azure Content Understanding (partial match). Amazon Rekognition's image features map partly to Azure Vision Image Analysis, but that API is deprecated and retires on September 25, 2028.