{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidltgrwgbarngzojuujxoa72sizlrhi2srvwyqcgdlhytefot4bm4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mklhnbztxny2"
  },
  "path": "/t/high-token-consumption-with-codex-and-5-5/1379994#post_1",
  "publishedAt": "2026-04-28T20:42:43.000Z",
  "site": "https://community.openai.com",
  "textContent": "Did any one notice way higher than expected token consumption report in api usage with gpt 5.5 today (Apr 28).\n\nMy dashboard suggests that when using codex I used 95 Million tokens input, 25 Million cached input to produce 600K output tokens!!??\n\nI did not use codex for such intense work, and the output token count to input ratio should on its own suggest there is some kind of problem with this.",
  "title": "High token consumption with codex and 5.5"
}