feat(openai): promptCacheRetention settings

Open teeverc opened this issue 1 month ago • 0 comments

https://platform.openai.com/docs/guides/prompt-caching#extended-prompt-cache-retention

Wanted a way to add the 24h extended prompt caching when using OpenAI through API key.

Not sure if should warn the user if they are using a model that doesn't support it. But it is a power user feature so they hopefully know what they are doing.

On the docs it supports only the following models: gpt-5.1 gpt-5.1-codex gpt-5.1-codex-mini gpt-5.1-chat-latest gpt-5 gpt-5-codex gpt-4.1

But these are already outdated (ex: gpt-5.1-codex-max), so I have left any warnings to be up to the user.

Verified via mitmproxy:

Dec 06 '25 00:12 teeverc