And if you have multiple prompts you just do a separate caching for each one?
I think this hinges on the system prompt going after the user prompt, for some router-related non-obvious reason, meaning at each model change the input is always new and thus uncacheable.
Also going by the last Claude system prompt that leaked these things can be like 20.000 tokens long.

Overall more interesting than I expected. On the Leverage Research cult: