---
title: "Comment by Rishita Sharma on \"Do we have an AI token cost solution in sight?\" | Hashnode"
description: "Routing helps, but a lot of the waste I see is upstream of the model choice. Huge system prompts, full chat history sent every turn, no caching. Trimming that i"
url: "https://hashnode.com/posts/do-we-have-an-ai-token-cost-solution-in-sight/6ac719fd8ecfdac715111cef/comment/6ac870d40e25ff2e48cc8e36"
---

[Discussion](https://hashnode.com/posts/do-we-have-an-ai-token-cost-solution-in-sight/6ac719fd8ecfdac715111cef)

Comment [Do we have an AI token cost solution in sight?](https://hashnode.com/posts/do-we-have-an-ai-token-cost-solution-in-sight/6ac719fd8ecfdac715111cef)

[Rishita Sharma](https://hashnode.com/@narawaybuilder)

Sharing practical lessons from building Naraway and shipping useful products.

[Oct 9](https://hashnode.com/posts/do-we-have-an-ai-token-cost-solution-in-sight/6ac719fd8ecfdac715111cef/comment/6ac870d40e25ff2e48cc8e36)

Routing helps, but a lot of the waste I see is upstream of the model choice. Huge system prompts, full chat history sent every turn, no caching. Trimming that is boring but often cuts more than switching models. Has anyone here seen routing hold up once you count the extra eval work for each model?

[Raj Darshan Pachori](https://hashnode.com/@rajpachori)

Technology Leader. Exploring AI to Drive Productivity Improvement and AI enablement.

[Oct 10](https://hashnode.com/posts/do-we-have-an-ai-token-cost-solution-in-sight/6ac719fd8ecfdac715111cef/comment/6ac870d40e25ff2e48cc8e36#reply-6aca633d5ce7bb0d75880c15)

[Rishita Sharma](https://hashnode.com/@narawaybuilder "Rishita Sharma") Those are best practices. Some of that can be automated and some are guidelines for developers to be followed as part of their day to day work. Sorry, cannot get the eval question.