{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihc45oyyl7xtptq7eqmqrrpxtackwrqmpcxpfcfywkthtain4s3wi",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mk4p43bertk2"
  },
  "path": "/t/deprecation-of-fine-tuned-models-but-still-cant-access-newer-ones/1379550#post_5",
  "publishedAt": "2026-04-22T23:19:31.000Z",
  "site": "https://community.openai.com",
  "textContent": "Well, this is very uncool. We’re using nano specifically because the response times are much better. gpt-5-nano absolutely will not do our classification correctly without fine tuning.\n\nWe all know that gpt-5 fine tuning exists and a bunch of people have access to it already (people have published papers!). Why can’t the rest of us start fine tuning on gpt-5 (nanon/mini/regular)?",
  "title": "Deprecation of fine tuned models, but still can't access newer ones?"
}