I’m being incorrectly routed to GPT-5.2. I'm pro user and cyber verified
Resolved 💬 9 comments Opened Feb 16, 2026 by aurindo10 Closed May 14, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
I ran this command. RUST_LOG='codex_api::sse::responses=trace' codex exec --skip-git-repo-check -s read-only -m 'gpt-5.3-codex' 'hi' 2>&1 >/dev/null | rg -o --replace '$1' '"model":"([^"]+)"' | head -n1
9 Comments
Same here. It worked right after verification, but last night I was randomly downgraded to GPT‑5.2, not even GPT‑5.2‑Codex. Nothing changed on my end, same Pro subscription, same normal repos I've been using since verification two days ago, so whatever is triggering the downgrade seems broken. Worse, the downgrade is sticky: it's been 22 hours and I'm still routed to GPT‑5.2. At this point, the passport verification was pointless.
Duplicate https://github.com/openai/codex/issues/11561
Known issue, described there several times - also from verified users.
Same here. Still being routed 2 days after verification initially cleared it.
Thanks for reporting, and apologies for the inconvenience. We're aware of the issue and are actively working on a mitigation. I'll share updates as they become available.
I received an automated email from a support agent 3 days after emailing support. After going back and forth with the agent who assured me nothing is wrong on the OpenAI side and running the non-existent commands it specified (codex auth status, etc.) it says it has escalated me to a support specialist and I should expect a response "in the coming days."
The (presumably) human support agent who responded to my email says the following: "At this time, GPT-5.3-codex is not an officially available or publicly supported model endpoint."
Same issue here. Pro / Cyber verified
Same issue here. False positive cyber-risk rerouting (routed to GPT-5.2)
same problem here. this is bullshit paying 230 eur per month and you just block access.