<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
  <channel>
    <title>Gptcc - 标签 - William</title>
    <link>https://williamlfang.github.io/tags/gptcc/</link>
    <description>Gptcc - 标签 | William</description>
    <generator>Hugo -- gohugo.io</generator><language>zh-CN</language><lastBuildDate>Fri, 13 Nov 2026 17:44:31 &#43;0800</lastBuildDate><atom:link href="https://williamlfang.github.io/tags/gptcc/" rel="self" type="application/rss+xml" /><item>
  <title>ChatGPT models in Claude Code: gptcc setup and troubleshooting</title>
  <link>https://williamlfang.github.io/2026-11-13-gptcc-chatgpt-models-in-claude-code/</link>
  <pubDate>Fri, 13 Nov 2026 17:44:31 &#43;0800</pubDate>
  <author>william</author>
  <guid>https://williamlfang.github.io/2026-11-13-gptcc-chatgpt-models-in-claude-code/</guid>
  <description><![CDATA[<div class="featured-image"><img loading="eager" src="https://williamlfang.github.io/2026-11-13-gptcc-chatgpt-models-in-claude-code/featured-image.png" alt="ChatGPT models in Claude Code: gptcc setup and troubleshooting" title="ChatGPT models in Claude Code: gptcc setup and troubleshooting" referrerpolicy="no-referrer"/></div><p>I wanted Claude Code&rsquo;s terminal interface and tools to run ChatGPT models. Installing <code>gptcc</code> was only the first step. I could select Sol in <code>/model</code> and still get an account-hold error before the request reached GPT.</p>
<p>The working setup uses a local authenticated gateway, ChatGPT OAuth, and Claude Code&rsquo;s custom model picker. It lists eight GPT models, makes <strong>Default resolve to GPT-6.1 Sol with medium effort</strong>, and displays Codex&rsquo;s five-hour and weekly usage beside the model. A real Claude Code session completed a file-read tool call in two turns.</p>]]></description>
</item>
</channel>
</rss>
