OpenAI GPT-5.6 Models Hit Amazon Bedrock with Smart Prompt Caching
OpenAI's GPT-5.6 Sol, Terra, and Luna models are now live on Amazon Bedrock with explicit prompt caching—letting you cherry-pick which parts of your prompts get cached for reuse. This means serious cost savings on inference while keeping your ML workloads running lean and mean.
source: [aws/machine-learning-blog]