gpt-6THREAD
OpenAI shares prompt caching tuning tips for GPT-6
OpenAI offers three practical tips: set explicit cache breakpoints, adjust reasoning effort and tools while keeping cached context, and prewarm shared context.
OpenAI Developers
@OpenAIDevsArchived 2026.09.23Originally posted 2026.09.23
THREAD
Tune caching for your application: – Choose which prompt prefixes to reuse with explicit cache breakpoints. – Adjust reasoning effort and tool availability while preserving cached context. – Prewarm shared context so responses start sooner. https://openai.com/index/better-prompt-caching-for-gpt-6/
We’ve improved prompt caching in the API for GPT-6, helping agents run faster and cost less. Higher cache-hit rates by default mean more input tokens benefit from cached-input discounts of up to 90%.
OpenAI Developers @OpenAIDevsOriginally posted 2026.09.23
x.com/openaidevs/status/2102506712590918001Archived 2026.09.23 10:30