{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreia6udwozr6i2cibtaqxmd7urgczyjs6fpsaj2h5hpfg7nth5gxqgi",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3miizp4pgfsa2"
  },
  "path": "/t/gpt-5-4-ignores-reasoning-effort-none-when-max-completion-tokens-is-used/1378362#post_3",
  "publishedAt": "2026-04-02T09:45:57.000Z",
  "site": "https://community.openai.com",
  "textContent": "Foxalabs:\n\n> `max_output_tokens`\n\nHi, no, it doesn’t work. `max_output_tokens` returns “BadRequestError 400 Unknown parameter: ‘max_output_tokens’.”\n\nIf you meant the old `max_tokens` parameter, it seems to be no longer supported with this model, as it returns:\n\nBadRequestError 400 Unsupported parameter: ‘max_tokens’ is not supported with this model. Use ‘max_completion_tokens’ instead.",
  "title": "Gpt-5.4 ignores reasoning_effort=\"none\" when max_completion_tokens is used"
}