Reduce costs and latency with Amazon Bedrock Intelligent Prompt Routing and prompt caching (preview)

Amazon Bedrock has introduced two new preview capabilities to help reduce costs and latency for generative AI applications:

• Amazon Bedrock Intelligent Prompt Routing: Dynamically routes requests between different-sized models in the same family to optimize quality and cost
• Prompt Caching: Allows caching of frequently used context across multiple model invocations

Key features and benefits include:

• Can reduce costs by up to 30% with prompt routing
• Prompt caching can reduce costs by up to 90% and latency by up to 85%
• Currently supports English language prompts
• Available in preview in US East and US West regions
• Works with models like Anthropic Claude and Meta Llama

These capabilities make it easier to build cost-effective and high-performing generative AI applications by intelligently managing model selection and caching.