{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicbp4ot6yvv6lgl4dj46sgzojawe2k3segtwayf3x4wlbli2eqxty",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mjzjpwm3he62"
  },
  "path": "/t/custom-gpt-content-failed-to-load-when-switching-models/1379264#post_4",
  "publishedAt": "2026-04-21T17:10:00.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@BradWyatt"
  ],
  "textContent": "@BradWyatt, yeah I get why it looks like a model support issue, especially with what you’re seeing in the UI and console.\n\nThe confusing part is it’s not really about “older vs newer models” being required. What’s actually happening is:\n\n  * Actions aren’t supported in Pro mode right now\n  * When you add Actions, your GPT is limited to Instant + Thinking models\n  * So the model list changes, and during that switch/reload the Action runtime gets rebuilt\n\n\n\nIf the Action spec or auth config has any issues, that rebuild step can fail, which is why the UI feels like it’s breaking when switching models.\n\nSo it’s kind of two things overlapping:\n\n  1. model availability changes when Actions are enabled\n  2. your Action setup likely has something fragile that crashes during reinit\n\n\n\nThat’s also why it works fine with Actions off.\n\nIf you want to double check, quick test:\n\n  * replace your Action with a tiny one-endpoint spec (no auth)\n  * switch models again\n\n\n\nIf that works cleanly, then it confirms it’s the spec/auth causing the break, not the model restriction itself.\n\nThis one’s definitely not obvious from the UI, you’re not alone in hitting it.\n\n-Mark G.",
  "title": "Custom GPT: “Content failed to load” when switching models"
}