{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigi2lzi4ym4enhrlaq4cd4sxgat72kudiz77auoh5sawfum3xhgla",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3motyaeyibvu2"
  },
  "path": "/t/codex-analytics-shows-gpt-5-4-for-most-turns-but-my-cli-is-configured-to-gpt-5-5-why/1384303#post_1",
  "publishedAt": "2026-06-22T02:24:19.000Z",
  "site": "https://community.openai.com",
  "textContent": "\nI’m a ChatGPT **Pro** subscriber, and I’d like an explanation for an anomaly in my Codex usage statistics.\n\n**My setup**\n• I use the service almost exclusively through the **Codex CLI** , rarely via the web UI.\n• My local `config.toml` explicitly sets the model to **GPT-5.5**.\n• I have **never** configured or manually selected **GPT-5.4**.\n\n**The problem**\nOn the analytics page (Settings → Analytics, `chatgpt.com/codex/cloud/settings/analytics`), under **Usage → Turns → By model** for the last 1 month (total **8,558 turns**), the **light-blue area (gpt-5.4) accounts for the overwhelming majority** of my turns, while **gpt-5.5 is only a thin band** on top. The legend lists: gpt-5.4, gpt-5.5, gpt-5.4-mini, gpt-5.3-codex-spark. (Screenshot below.)\n\nSo despite GPT-5.5 being my configured model, **most usage is attributed to GPT-5.4**.\n\n**Questions**\n(1) With my config explicitly set to GPT-5.5, why is GPT-5.4 used for the vast majority of turns?\n(2) Are requests being automatically routed / fell back to GPT-5.4? If so, what triggers it (capacity limits, task type, Pro-plan quota policy)?\n(3) Is this a reporting/display issue in Analytics, or is the actual model called different from my config?\n(4) How do I ensure requests always use my configured GPT-5.5?\n\nHappy to share my exact `config.toml` model line and Codex CLI version if that helps with debugging. Thanks!",
  "title": "Codex Analytics shows GPT-5.4 for most turns, but my CLI is configured to GPT-5.5 — why?"
}