Build real-time recommendations into your applications

Reduce Amazon Personalize costs with these tips

Amazon Personalize cost saving tips

Optimize your Amazon Personalize costs with these tips

Delete Unused Models

Regularly review and delete your models and campaigns that are no longer needed. You are charged per model so this can lower costs.

Optimize Dataset Size

Use smaller dataset sizes and model types where possible to optimize costs. The guidance to do this is found in the AWS documentation

Auto-scaling

Use automatic scaling features to optimize resource provisioning for your workload, scaling up during peak usage and down when not needed.

Discover your infrastructure maturity

Curious about the state of your digital infrastructure? Our Infrastructure Maturity Assessment provides immediate results, offering you a clear understanding of your setup’s strengths and areas for improvement.

The Infrastructure Maturity Assessment is a quick and free tool designed to evaluate the quality and readiness of your digital infrastructure. In just a few minutes, you’ll receive personalized insights to help you enhance scalability, efficiency, and performance.

Ready to see how your digital infrastructure stacks up?

It only takes 10-15 minutes, and your results are available instantly!

Service information & pricing

About Amazon Personalize

About Amazon Personalize

Amazon Personalize is a machine learning system that improves customer experiences and boosts revenue through data unification, loyalty promotion, and optimization of personalization engines. It provides real-time suggestions, aids digital transformation, and works well with existing platforms. Further, it enhances customer targeting, manages rule-based promotions, and uses data efficiently. It consequently leads to increased customer purchases and long-term engagement.

Learn more

Amazon Personalize pricing

Amazon Personalize operates on a pay-as-you-go scheme. Charging $0.05/GB for data storage and processing and $0.24 per training hour. Real-time recommendations cost $0.0556/1,000 for the initial 72 million requests, decreasing with increased usage. Batch recommendations cost $0.067/1,000 for the first 20 million and similarly decrease. Additional costs for specific features like including Item metadata in requests apply.

Learn more