I’m a ChatGPT
Prosubscriber, and I’d like an explanation for an anomaly in my Codex usage statistics.
My setup
• I use the service almost exclusively through the Codex CLI, rarely via the web UI.
• My local config.toml explicitly sets the model to GPT-5.5.
• I have never configured or manually selected GPT-5.4.
The problem
On 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.)
So despite GPT-5.5 being my configured model, most usage is attributed to GPT-5.4.
Questions
(1) With my config explicitly set to GPT-5.5, why is GPT-5.4 used for the vast majority of turns?
(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)?
(3) Is this a reporting/display issue in Analytics, or is the actual model called different from my config?
(4) How do I ensure requests always use my configured GPT-5.5?
Happy to share my exact config.toml model line and Codex CLI version if that helps with debugging. Thanks!
Welcome to the community!
There was a similar issue 2 days ago and the user was able to solve it.
I’d recommend you to check this topic and see if your issue matches this:
For the past three days 60-85% of my 5.5 xhigh requests have been serviced by 5.4. I’ve double and triple checked that I’m not setting the wrong model. [Screenshot 2026-06-19 at 9.25.42 pm] My usage is being drained at 5.5 xhigh rates. I’ve contact support but I just got an AI message back saying “we understand your concern please read the pricing page”. Has anyone else been experiencing this? You can check at: chatgptcom/codex/cloud/settings/analytics#usage If anyone has any information …