Amazon Bedrock introduces Priority and Flex inference service tiers

Amazon Bedrock Introduces New Inference Service Tiers

Amazon Bedrock introduces two new inference service tiers to optimize costs and performance for different AI workloads. The new Flex tier offers cost-effective pricing for non-time-critical applications, while the Priority tier provides premium performance for mission-critical applications.

New Service Tiers

• Flex Tier: Cost-effective for non-time-critical applications like model evaluations and content summarization.
• Priority Tier: Premium performance for mission-critical applications with up to 25% better latency compared to the standard tier.

What to do

• Evaluate your AI workloads to determine the most suitable service tier.
• Migrate non-critical applications to the Flex tier to reduce costs.
• Prioritize critical applications to the Priority tier for optimal performance.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.