<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Model-Selection on Tokenise</title><link>https://tokenise.rosvetic.com/tags/model-selection/</link><description>Recent content in Model-Selection on Tokenise</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 08 Oct 2026 07:03:00 +0000</lastBuildDate><atom:link href="https://tokenise.rosvetic.com/tags/model-selection/index.xml" rel="self" type="application/rss+xml"/><item><title>GPT-6.1 Sol is in Codex. Test it against Astra on your own task before you switch</title><link>https://tokenise.rosvetic.com/posts/codex-gpt-6-1-sol-same-task-test/</link><pubDate>Thu, 08 Oct 2026 07:03:00 +0000</pubDate><guid>https://tokenise.rosvetic.com/posts/codex-gpt-6-1-sol-same-task-test/</guid><description>&lt;p&gt;OpenAI added GPT-6.1 Sol to Codex on September 29, and Codex CLI 0.161.0 (October 7) makes it the default model in the bundled catalog, according to the &lt;a href="https://learn.chatgpt.com/docs/changelog" target="_blank" rel="noopener noreferrer"&gt;Codex changelog&lt;/a&gt;&#10;. The pitch: near-Astra performance for complex work, at lower cost than Astra. That&amp;rsquo;s a claim about OpenAI&amp;rsquo;s tasks. Whether it holds on your codebase is a ten-minute experiment, and OpenAI&amp;rsquo;s own &lt;a href="https://developers.openai.com/api/docs/guides/model-selection" target="_blank" rel="noopener noreferrer"&gt;model selection guide&lt;/a&gt;&#10; tells you to run it: compare the models on the same task and keep the lightest setting that meets your quality bar.&lt;/p&gt;</description></item></channel></rss>