{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreihgvpayp3pwjf5o4q6cxopmxnygcy3c2tbxnlcsmeuwejcihekrv4",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mkgl4c5jgys2"
},
"path": "/t/custom-gpt-content-failed-to-load-when-switching-models/1379264#post_11",
"publishedAt": "2026-04-26T20:59:44.000Z",
"site": "https://community.openai.com",
"textContent": "I can confirm that it looks like OpenAI fixed it.\n\nHowever, I want to note that when I set the model to use Instant, it does not make API calls. The Thinking model does work for API calls though.\n\no3: Works\n5.2 Instant: Does not work\n5.2 Thinking: Works\nLatest model Instant: Does not work\nLatest model Thinking: Works\n\nCan someone else in this thread please confirm that they’re seeing this behavior as well?",
"title": "Custom GPT: “Content failed to load” when switching models"
}