Introducing explicit prompt caching for OpenAI GPT-5.6 models on Amazon Bedrock
TL;DR
OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock, along with explicit prompt caching that gives you precise control over which parts of your prompt are cached and reused. Learn how to get started, set up explicit caching, and migrate existing GPT workloads to reduce inference cost.
Nauti's Take
The first practical test should use long, stable system prompts with realistic repetition rates. Measure the actual cache hit rate, cost per request, and failures caused by stale context before migrating production workloads.
For dynamic prompts or sensitive data, cache controls will determine whether the savings justify the added complexity.
Sources
26.6.26