Status 503 issue persistent
What version of Codex CLI is running?
codex-cli 0.118.0
What subscription do you have?
Plus
Which model were you using?
gpt-5-4 high
What platform is your computer?
Darwin 25.2.0 arm64 arm
What terminal emulator and version are you using (if applicable)?
Warp
What issue are you seeing?
`codex -m gpt-5.4 -c model_reasoning_effort=high --yolo
╭────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.118.0) │
│ │
│ model: gpt-5.4 high /model to change │
│ directory: REDACTED │
╰────────────────────────────────────────────╯
Tip: New Try the Codex App with 2x rate limits until April 2nd. Run 'codex app' or visit
https://chatgpt.com/codex?app-landing-page=true
⚠ MCP client for firecrawl-search failed to start: MCP startup failed: handshaking with MCP server
failed: connection closed: initialize response
⚠ MCP startup incomplete (failed: firecrawl-search)
› hello
• Reconnecting... 5/5 (1m 13s • esc to interrupt)
└ Unexpected status 503 Service Unavailable: upstream connect error or disconnect/reset before headers. retried and the latest reset reason: remote connection failure,
transport failure reason: delayed connect error: Connection refused, url: wss://chatgpt.com/backend-api/codex/responses, cf-ray: 9e8dd3cdaeb07e42-SYD`
What steps can reproduce the bug?
i just launched codex with codex -m gpt-5.4 -c model_reasoning_effort=high --yolo
What is the expected behavior?
to be able to use codex normally
Additional information
No
12 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
Please use
/feedbackto upload logs, then post the thread ID here.50x errors are often diagnosed as misconfiguration where Codex is configured to point to the wrong URL or point to an LLM proxy that generates an error.
Thread ID: 019d6afd-5351-7fc0-9af2-2d0e06b63684
Its a server side issue, but no outage or degradation is reflected in status.openai.com?
ive tried changing to other models to no avail.
Running codex doesnt seem to work at all now it wont launch or extremely delayed response.
After some diagnosis
Proxy variables: None set
OpenAI environment variables: None set
Codex config files: None found
Also getting 503 errors
Yes, this looks like a server issue. The team is investigating.
Also getting 503 in Sydney
Could be an Australian thing maybe cause I'm Based in Adelaide.
Just started getting this in Singapore. Somewhat intermittent, I can restart codex and sometimes it works for a couple minutes before failing again.
!Image
So it gone from 503 to getting model at capacity errors now
Codex seems to have degraded performance at this point but has recovered from the 503 errors for me
same problem agent dont work normal very long time to wait