Efficiently managing large customer-specific data for Workers AI API calls.

For Workers & Pages, what is the name of the domain?

nill

What is the issue or error you’re encountering

I am building a product that involves making API calls to a Workers AI model. Each API call requires a system prompt that is typically around 200,000 words long. Most of this data remains constant for a particular customer across multiple API calls, but it varies between different customers. Essentially, I need a solution to manage and retrieve this large, customer-specific data efficiently during API calls without wasting input tokens on it. To optimize this process, is there a way to store this data on Cloudflare (or any related service) so that it doesn’t need to be sent repeatedly for the same customer? I would appreciate any insights or suggestions on how to achieve this!