<?xml version="1.0" encoding="UTF-8" ?>
<?xml-stylesheet type="text/xsl" href="https://community.appian.com/cfs-file/__key/system/syndication/rss.xsl" media="screen"?><rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:wfw="http://wellformedweb.org/CommentAPI/"><channel><title>Token Use</title><link>https://community.appian.com/discussions/f/rules/38602/token-use</link><description>Hi Appian Community, 
 Quick question: Is there any way for Appian Gen-AI to tell us how many tokens are used for a particular task, from input to output? 
 I believe there isn’t, but just in case, I wanted to ask. The purpose of this is to analyze token</description><dc:language>en-US</dc:language><generator>Telligent Community 12</generator><item><title>RE: Token Use</title><link>https://community.appian.com/thread/145765?ContentTypeID=1</link><pubDate>Fri, 28 Feb 2025 06:29:21 GMT</pubDate><guid isPermaLink="false">d3a83456-d57b-489c-a84c-4e8267bb592a:143c54f0-b24a-41ac-8da5-6bf7308d860a</guid><dc:creator>Abdul Rahim</dc:creator><description>&lt;p&gt;&lt;span&gt;Alright, thank you for the reply.&amp;nbsp;&lt;/span&gt;&lt;/p&gt;&lt;div style="clear:both;"&gt;&lt;/div&gt;</description></item><item><title>RE: Token Use</title><link>https://community.appian.com/thread/145764?ContentTypeID=1</link><pubDate>Fri, 28 Feb 2025 06:29:07 GMT</pubDate><guid isPermaLink="false">d3a83456-d57b-489c-a84c-4e8267bb592a:b81eb4a3-0bda-4d54-bd13-c2bcd21e544d</guid><dc:creator>Abdul Rahim</dc:creator><description>&lt;p&gt;I see, thank you for the reply.&lt;/p&gt;&lt;div style="clear:both;"&gt;&lt;/div&gt;</description></item><item><title>RE: Token Use</title><link>https://community.appian.com/thread/145753?ContentTypeID=1</link><pubDate>Fri, 28 Feb 2025 04:14:10 GMT</pubDate><guid isPermaLink="false">d3a83456-d57b-489c-a84c-4e8267bb592a:32154193-70df-4da1-ae78-1496ee7731a4</guid><dc:creator>Konduru Chaitanya</dc:creator><description>&lt;p&gt;Simple answer to your question is NO, there is no proven method to monitor or analyze the token consumption data.&lt;/p&gt;&lt;div style="clear:both;"&gt;&lt;/div&gt;</description></item><item><title>RE: Token Use</title><link>https://community.appian.com/thread/145752?ContentTypeID=1</link><pubDate>Fri, 28 Feb 2025 02:45:15 GMT</pubDate><guid isPermaLink="false">d3a83456-d57b-489c-a84c-4e8267bb592a:8af4f1d1-71f8-430d-aaa9-0b6c66df1b5a</guid><dc:creator>Karumuru Abhishek</dc:creator><description>&lt;p&gt;Hi&amp;nbsp;&lt;a href="/members/abdulrahimb9853"&gt;Abdul Rahim&lt;/a&gt;&amp;nbsp;AFAIK there is no way&amp;nbsp; to count how many tokens used. A model breaks down data into meaningful parts&amp;nbsp; tokens before it begins processing that data. Language processing models break down paragraphs of text into their smallest units, but these units aren&amp;#39;t always equivalent to words. Instead, a token could be part of a word. Therefore, the number of tokens won&amp;#39;t always equal the number of words in the text analyzed.&lt;/p&gt;&lt;div style="clear:both;"&gt;&lt;/div&gt;</description></item></channel></rss>