Is Claude API down?

Anthropic

No — Claude 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 Claude API ↗

Last 24 hours

16:42 UTC — Working17:12 UTC — Working17:42 UTC — Working18:12 UTC — Working18:42 UTC — Working19:12 UTC — Working19:42 UTC — Working20:12 UTC — Working20:42 UTC — Working21:12 UTC — Working21:42 UTC — Working22:12 UTC — Working22:42 UTC — Working23:12 UTC — Working23:42 UTC — Working00:12 UTC — Working00:42 UTC — Working01:12 UTC — Working01:42 UTC — Working02:12 UTC — Working02:42 UTC — Working03:12 UTC — Working03:42 UTC — Working04:12 UTC — Working04:42 UTC — Working05:12 UTC — Working05:42 UTC — Working06:12 UTC — Working06:42 UTC — Working07:12 UTC — Working07:42 UTC — Working08:12 UTC — Working08:42 UTC — Working09:12 UTC — Working09:42 UTC — Working10:12 UTC — Working10:42 UTC — Working11:12 UTC — Working11:42 UTC — Working12:12 UTC — Working12:42 UTC — Working13:12 UTC — Working13:42 UTC — Working14:12 UTC — Working14:42 UTC — Working15:12 UTC — Working15:42 UTC — Working16:12 UTC — Working

24 h agonow

Last 30 days

28 Sept — Partly down29 Sept — Working30 Sept — Slow or glitchy1 Oct — Slow or glitchy2 Oct — Working3 Oct — Working4 Oct — Partly down5 Oct — Partly down6 Oct — Partly down7 Oct — Partly down8 Oct — Partly down9 Oct — Partly down10 Oct — Partly down11 Oct — Partly down12 Oct — Partly down13 Oct — Partly down14 Oct — Working15 Oct — Working16 Oct — Working17 Oct — Working18 Oct — Working19 Oct — Working20 Oct — Working21 Oct — Slow or glitchy22 Oct — Working23 Oct — Down24 Oct — Partly down25 Oct — Working26 Oct — Partly down27 Oct — Working

30 days agoyesterday

13 of 30 days with data had no problems.

Recent incidents

  1. Partly down

    Elevated errors for Claude Sonnet 5.5

    Resolved after 41 mins

  2. Partly down

    Elevated errors for Claude Sonnet 5.5

    Resolved after 42 mins

  3. Partly down

    Elevated errors for Claude Fable 5.1

    Resolved after 32 mins

  4. Partly down

    Elevated errors for Claude Sonnet 5.5 and other models

    Resolved after 1 hr 39 mins

  5. Partly down

    Elevated errors for Claude Fable 5 and Claude Fable 5.1

    Resolved after 37 mins

  6. Partly down

    Elevated errors for Claude Opus 5.5

    Resolved after 6 mins

  7. Down

    Elevated errors for Claude Fable 5.1, Sonnet 5.5, and Haiku 5.5

    Resolved after 34 mins

  8. Slow or glitchy

    Degraded performance for Claude Fable 5

    Resolved after 40 mins

About this service

Covers api.anthropic.com and the developer Console. HTTP 529 overloaded_error means Anthropic is shedding load: it is temporary and worth retrying with backoff. 401 and 403 point at your key or workspace, not at Anthropic.

Other model APIs right now

Claude API: common questions

Is the Claude 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 Anthropic. 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 Claude 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 Claude API is down?

For Claude API we combine Anthropic's official status page, read every minute, the share of successful requests to Anthropic'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 →