Prompt caching (OpenAI Responses API)

Prompt cache retention

If you don’t specify a retention policy, the default is in_memory.

24hの指定もできる

Best practices

Structure prompts with static or repeated content at the beginning and dynamic, user-specific content at the end.

Use the prompt_cache_key parameter consistently across requests that share common prefixes.

Monitor your cache performance metrics

Maintain a steady stream of requests