Is OpenAI API down?

OpenAI

No — OpenAI API is working normally

Our sources see nothing wrong. If it still fails for you, the cause is most likely on your side — the tips further down cover the usual suspects.

Working since · Checked at

What our sources say

Official status page
Working
Our test requests, last hour
Not running for this service
Traffic through OpenRouter
0 of 4 models failing, 100% of requests succeeded in 30 min
Reports from visitors, last hour
0

Parts of the service

Official status page ↗Open OpenAI API ↗

Last 24 hours

16:41 UTC — Working17:11 UTC — Working17:41 UTC — Working18:11 UTC — Working18:41 UTC — Working19:11 UTC — Working19:41 UTC — Working20:11 UTC — Working20:41 UTC — Working21:11 UTC — Working21:41 UTC — Working22:11 UTC — Working22:41 UTC — Working23:11 UTC — Working23:41 UTC — Working00:11 UTC — Working00:41 UTC — Working01:11 UTC — Working01:41 UTC — Working02:11 UTC — Working02:41 UTC — Working03:11 UTC — Working03:41 UTC — Working04:11 UTC — Working04:41 UTC — Working05:11 UTC — Working05:41 UTC — Working06:11 UTC — Working06:41 UTC — Working07:11 UTC — Working07:41 UTC — Working08:11 UTC — Working08:41 UTC — Working09:11 UTC — Working09:41 UTC — Working10:11 UTC — Working10:41 UTC — Working11:11 UTC — Working11:41 UTC — Working12:11 UTC — Working12:41 UTC — Working13:11 UTC — Working13:41 UTC — Working14:11 UTC — Working14:41 UTC — Working15:11 UTC — Working15:41 UTC — Working16:11 UTC — Working

24 h agonow

Last 30 days

28 Sept — No data29 Sept — No data30 Sept — No data1 Oct — No data2 Oct — No data3 Oct — No data4 Oct — No data5 Oct — No data6 Oct — Slow or glitchy7 Oct — Slow or glitchy8 Oct — Working9 Oct — Partly down10 Oct — Slow or glitchy11 Oct — Slow or glitchy12 Oct — Slow or glitchy13 Oct — Slow or glitchy14 Oct — Partly down15 Oct — Partly down16 Oct — Working17 Oct — Working18 Oct — Slow or glitchy19 Oct — Working20 Oct — Slow or glitchy21 Oct — Slow or glitchy22 Oct — Slow or glitchy23 Oct — Working24 Oct — Working25 Oct — Working26 Oct — Slow or glitchy27 Oct — Working

30 days agoyesterday

8 of 22 days with data had no problems.

Recent incidents

  1. Slow or glitchy

    6.1 Sol Degraded Model Performance

    Resolved after 1 hr 18 mins

  2. Elevated error rates for most hosted Code Reviews and Security Reviews on private GitHub repositories

    Resolved after 29 mins

  3. Slow or glitchy

    Elevated error rates for Ads POST requests

    Resolved after 11 mins

  4. Help Center Chat Support Degraded

    Resolved after 33 mins

  5. Delays in customer support responses

    Resolved after 2 hrs 17 mins

  6. Slow or glitchy

    New Ad Accounts failing to provision admins

    Resolved after 4 hrs 31 mins

  7. Slow or glitchy

    Degraded Performance of Dots on Enterprise

    Resolved after 2 hrs 4 mins

  8. Partly down

    Authentication errors for some users

About this service

We watch the components developers depend on: Chat Completions, Responses, Embeddings, Batch, Realtime, Files and more. A 429 with insufficient_quota is a billing issue on your account, not an outage; a burst of 500s and 503s across several models is.

Other model APIs right now

OpenAI API: common questions

Is the OpenAI API down, or is it my code?

Look at the HTTP status. 401 and 403 mean a key or permission problem, 400 and 422 a malformed request, 429 a rate or spending limit. Only 500, 502, 503, 504 and timeouts point at OpenAI. If this page is green while you get them, send a minimal request with curl to rule out your client library or proxy.

How should my app handle OpenAI API outages?

Retry 429 and 5xx responses with exponential backoff and a little random jitter, cap the number of attempts, and set a timeout so stuck streams don't pile up. For anything users see, keep a fallback model from another vendor configured and switch to it automatically after a few failures in a row — the list above shows which ones are healthy right now.

Why do my requests fail when others say it works?

Limits apply per organisation and per model, so your account can be throttled while everyone else is fine. Newly released and very large models are also the first to be rate-limited at busy hours. Check the usage page of your account, try a smaller model and make sure you call the right base URL and region.

Responses are slow but they arrive. Does that count as an outage?

Watch the time to the first token rather than the total time. On our own test requests we flag a slowdown when the first token takes more than 3 seconds and three times longer than the day's median. Long prompts and long outputs are slow by nature and are not treated as a problem.

How do you know whether OpenAI API is down?

For OpenAI API we combine OpenAI's official status page, read every minute, the share of successful requests to OpenAI's models on OpenRouter and reports from people who press the button on this page. The most serious signal that is still fresh sets the verdict, and stale sources are ignored rather than trusted. The page refreshes by itself; the exact thresholds are on our “How we check” page.

How we check →