---
title: "Comment by Kartik N V J K on \"Do we have an AI token cost solution in sight?\" | Hashnode"
description: "The routing argument lands, but the comment about measuring cost-per-successful-outcome instead of cost-per-million-tokens is the part I would build on. A cheap"
url: "https://hashnode.com/posts/do-we-have-an-ai-token-cost-solution-in-sight/6ac719fd8ecfdac715111cef/comment/6ac7de603d4d8361506041b7"
---

[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)

[Kartik N V J K](https://hashnode.com/@kartik-nvj)

AI Developer | Making AI reliable, trustworthy & accessible to everyone | Active community contributor

[Oct 8](https://hashnode.com/posts/do-we-have-an-ai-token-cost-solution-in-sight/6ac719fd8ecfdac715111cef/comment/6ac7de603d4d8361506041b7)

The routing argument lands, but the comment about measuring cost-per-successful-outcome instead of cost-per-million-tokens is the part I would build on. A cheaper model that fails and triggers a retry or an escalation is not actually cheaper, so routing needs a success signal in the loop, not just a price table. When you route to the cheapest capable model, what defines 'capable' at decision time, a prior eval score or a live confidence check?

[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/6ac7de603d4d8361506041b7#reply-6aca673ca122ee952a2bb5c9)

@kartik-nvj Thats a valid point. Successful-outcome is something which would build the credibility and not just the cost. Havings said that there's a merit in routing the low complexity tasks to the cheaper models if one is able to get the confidence in prior evaluation. And capability has to be understood through both prior eval score and refinement of model deployed to live.