<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Llm-Cost on David Zhang | AI Engineering, Careers &amp; Industry Deep-Dives</title>
    <link>https://ryrenz.com/tags/llm-cost/</link>
    <description>Recent content in Llm-Cost on David Zhang | AI Engineering, Careers &amp; Industry Deep-Dives</description>
    <generator>Hugo -- 0.155.3</generator>
    <language>en-US</language>
    <lastBuildDate>Sat, 25 Jul 2026 10:00:00 -0400</lastBuildDate>
    <atom:link href="https://ryrenz.com/tags/llm-cost/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Pi &gt; Claude Code and Codex? Same Model, Half the Bill</title>
      <link>https://ryrenz.com/ai/pi-vs-claude-code-codex/</link>
      <pubDate>Sat, 25 Jul 2026 10:00:00 -0400</pubDate>
      <guid>https://ryrenz.com/ai/pi-vs-claude-code-codex/</guid>
      <description>Databricks ran every major model paired with every major CLI coding tool against its own multi-million-line codebase. Of the 7 best cost-to-quality combos, 4 were Pi, and the single highest score, 90%, was also Pi. For the same work, Pi&amp;rsquo;s bill is often half of Claude Code&amp;rsquo;s. Here&amp;rsquo;s why the data holds up, why Pi is so cheap, and which one you should actually use.</description>
    </item>
  </channel>
</rss>
