<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Node.js on The road</title><link>https://kane.mx/tags/node.js/</link><description>Recent content in Node.js on The road</description><generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Sun, 13 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kane.mx/tags/node.js/index.xml" rel="self" type="application/rss+xml"/><item><title>Switch Bedrock Models in Codex and the ChatGPT App</title><link>https://kane.mx/posts/2026/bedrock-model-router-ios-chatgpt/</link><pubDate>Sun, 13 Sep 2026 00:00:00 +0000</pubDate><guid>https://kane.mx/posts/2026/bedrock-model-router-ios-chatgpt/</guid><description>
&lt;p>When Codex uses Bedrock's OpenAI-compatible API, switching models can break requests: the selected model changes, but the provider still points to the same AWS Region. The failure appears both when using Codex directly and when operating it through the ChatGPT app. In both cases, Codex makes the model API request. A model picker alone cannot move that request to the region where the new model is available.&lt;/p>
&lt;p>The mobile workflow adds a separate compatibility issue. When I used ChatGPT iOS over SSH to operate Codex on a remote host, the model requests generated on that host still included &lt;code>reasoning.summary&lt;/code>, which the Bedrock endpoint in use rejected.&lt;/p>
&lt;p>&lt;a href="https://kane.mx/posts/2026/bedrock-model-router-ios-chatgpt/">Read More&lt;/a>&lt;/p></description></item></channel></rss>