OpenAI announced explicit cache breakpoints with the new GPT 5.6 models - https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-breakpoints

Not sure if this is supported in LiteLLM? Based on [LiteLLM's docs](https://docs.litellm.ai/docs/completion/input?utm_source=chatgpt.com#:~:text=This%20ONLY%20DROPS%20UNSUPPORTED%20OPENAI%20PARAMS.) I assume that this would be supported, but it would be good to have confirmation from the LiteLLM team.

Thanks for building a great tool!