# How to Cache LLM Prompts and Responses in Pega to Reduce Token Costs?

**URL:** <https://forums.pega.com/t/how-to-cache-llm-prompts-and-responses-in-pega-to-reduce-token-costs/11177>\
**Category:** AI\
**Created:** [March 17, 2026, 5:06am UTC](https://forums.pega.com/t/how-to-cache-llm-prompts-and-responses-in-pega-to-reduce-token-costs/11177 "2026-03-17T05:06:07Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![RameshSangili](https://yyz2.discourse-cdn.com/pega/user_avatar/forums.pega.com/rameshsangili/32/22508_2.png) [@RameshSangili](https://forums.pega.com/u/RameshSangili)\
**Post date:** [March 19, 2026, 12:36am UTC](https://forums.pega.com/t/how-to-cache-llm-prompts-and-responses-in-pega-to-reduce-token-costs/11177/6 "2026-03-19T00:36:23Z")

</div>

_ **Use Data Transforms for token efficiency for Agents and Coach:** _ Apply Data Transforms to supply only essential information from the Data Page. This reduces the amount of data the Large Language Model (LLM) processes, improving token efficiency and response speed. Sample token usage when conversing with a Coach:

Please follow this link for more details: [Trim the Payload: Use Data Transforms to Minimize Token Consumption](https://forums.pega.com/t/trim-the-payload-use-data-transforms-to-minimize-token-consumption/10464)

---

_[View the full topic](https://forums.pega.com/t/how-to-cache-llm-prompts-and-responses-in-pega-to-reduce-token-costs/11177)._