{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreievxtsfib73eh3wohxp2au2ipokm6mjwcwvvn77q7gexaw5nlq3du",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3me7opnipa4a2"
  },
  "path": "/t/issue-with-reasoning-tokens-being-used-when-using-the-gpt-5-1-chat-latest-model/1366752#post_6",
  "publishedAt": "2026-02-06T18:12:08.000Z",
  "site": "https://community.openai.com",
  "textContent": "The “chat” models are your copy of what runs on ChatGPT - running with that configuration. They don’t accept a reasoning effort parameter; logically you’d get the same internal reasoning (and pre-judgement) done on ChatGPT.\n\nThe actual reasoning tokens are obfuscated, <127 and you get billed 0.",
  "title": "Issue with reasoning tokens being used when using the \"gpt-5.1-chat-latest\" model"
}