LLM & Text Generation18 min reading time
Introducing explicit prompt caching for OpenAI GPT-5.6 models on Amazon Bedrock
AWS Blog
Read full post
OpenAI's GPT-5.6 models—Sol, Terra, and Luna—are now available on Amazon Bedrock, featuring explicit prompt caching that reduces costs by reusing parts of prompts for 30 minutes. This caching is especially beneficial for agentic workflows with repeated instructions and documents.
