Home icon

Amazon Bedrock announces general availability of prompt caching

News



Amazon Bedrock has announced the general availability of prompt caching, a new feature designed to optimize generative AI interactions by reducing costs and latency.

  • Reduces costs by up to 90% and latency by up to 85%
  • Caches repetitive inputs to avoid reprocessing context
  • Available for multiple Anthropic Claude models, including Haiku, Sonnet, Nova Micro, Lite, and Pro
  • Part of Amazon Bedrock's broader capabilities for building secure and responsible generative AI applications
  • Helps organizations optimize generative AI usage while maintaining data governance

The feature enables more efficient AI interactions by minimizing computational resources needed for repeated prompts, offering significant performance and cost benefits.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Dec 4
2024
Amazon Bedrock announces preview of prompt caching
Apr 7
2025
Effectively use prompt caching on Amazon Bedrock
Jan 26
2026
Amazon Bedrock now supports 1-hour duration for prompt caching
Apr 23
2025
Prompt Optimization in Amazon Bedrock now generally available

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.