Google Cloud → AWS and Azure
AWS and Azure equivalents of Gemini model tuning
The closest AWS equivalents of Google Cloud Gemini model tuning are Amazon Bedrock model customization and Amazon Comprehend; on Azure, Foundry fine-tuning and Azure Language.
About Gemini model tuning
| Provider | Google Cloud |
|---|---|
| Status | Generally available |
| What it is | Supervised fine-tuning and preference tuning for Gemini models, embedding tuning, and tuning of open models from Model Garden. |
| Documentation | docs.cloud.google.com |
| Pricing | Official pricing page |
Mappings (2)
| Capability | AWS | Match (GCP vs AWS) | Azure |
|---|---|---|---|
| Foundation model fine-tuning & distillation | Amazon Bedrock model customization | Direct match | Foundry fine-tuning |
| Custom text classification & entity recognition | Amazon Comprehend | Partial match | Azure Language |
Foundation model fine-tuning & distillation Direct match
Bedrock model customization maps to Gemini tuning on Agent Platform: supervised fine-tuning and preference tuning for Gemini, plus tuning of open models from Model Garden.
- Tuning targets Gemini and selected open models; which methods a model supports varies by model.
- Google recommends trying prompt design and grounding first and documents when each tuning method fits.
- Tuned Gemini models are served by the platform without you provisioning endpoints for them.
Custom text classification & entity recognition Partial match
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.
- Gemini tuning replaces AutoML Text; you get a tuned generative model, not a dedicated classifier endpoint.