Provider status
Is your AI provider down right now?
6 of 6 providers answering. We ask every provider one small question every 10 minutes and record what comes back. This is that record, kept for 7 days, with a page for each provider.
As of 26 Oct 2026, 17:20 UTC · one real completion to each provider’s API every 10 minutes, on our own account
Free account · provider alerts on any plan · an email after 20 minutes without an answer, and again when it comes back
Free account · 24 hours, 7 days and 30 days · no card
Already have an account? Log in
- 6/6
- providers answered the last check
- 10 min
- between checks, the same call for every provider
- 7 d
- of record kept, with the checks we could not make listed separately
Last 7 days
Which AI providers are up? The last 7 days, hour by hour
Each bar is one hour of checks. A check that failed on our side is hatched and counts as neither uptime nor downtime, and an hour with no check at all stays empty, so a gap in the record shows as a gap.
OpenAI (GPT)Answering1.4 s
Anthropic (Claude)Answering1.1 s
Google (Gemini)Answering643 ms
DeepSeekAnswering1.0 s
Moonshot AI (Kimi)Answering1.2 s
Z.ai (GLM)Answering1.7 sBy provider
Which AI provider is down? The last 24 hours and 7 days
“Answered” counts only the checks we could make; the last column is the denominator. The median reply is our round trip, from a machine that is often running a benchmark sweep at the same time. Each name opens the provider’s own page.
| Provider | Last check | Answered, 24h | Answered, 7d | Median reply, 24h | Checks measured, 24h |
|---|---|---|---|---|---|
| OpenAI (GPT) | Answering6 minutes ago | 100% | 100% | 1.4 s | 142 of 142 |
| Anthropic (Claude) | Answering6 minutes ago | 100% | 100% | 1.1 s | 91 of 142 |
| Google (Gemini) | Answering6 minutes ago | 100% | 100% | 643 ms | 142 of 142 |
| DeepSeek | Answering6 minutes ago | 100% | 100% | 1.0 s | 142 of 142 |
| Moonshot AI (Kimi) | Answering6 minutes ago | 100% | 100% | 1.2 s | 142 of 142 |
| Z.ai (GLM) | Answering6 minutes ago | 100% | 100% | 1.7 s | 142 of 142 |
- Anthropic (Claude): 51 of the 142 checks in the last 24 hours failed on our side and count as neither uptime nor downtime.
The record
Which AI provider outages did we record in the last 7 days?
Outages we recorded
No provider failed to answer in the last 7 days.
Checks we could not make
These were issues on our side, not the providers’. We list them so that a problem of ours never shows up as somebody else’s downtime, and because a gap in the record is a fact about the record. Each line says how long it lasted and when it last happened: anything not marked ongoing is over, and stays listed only until it falls out of the 7-day window.
- Anthropic (Claude)lasted 8h 30man issue on our side · 1 episode · last seen 11 hours ago, since resolvedAn issue on our side. We are working to resolve it.
Slow periods
Two or more consecutive checks that took longer than 5 seconds. Measured from our machine, which is often running a benchmark sweep at the same time, so read these next to the median above rather than on their own.
- Moonshot AI (Kimi)lasted 8h 30m11 episodes in the last 7 days
Method
How is AI provider status measured here?
- The check
- One short completion on our own key, from one machine in Germany. It is the same call for every provider, so the numbers are comparable.
- What “answered” means
- The provider returned usable content. It does not mean the model was correct, fast or good; that is what the benchmarks are for.
- When a check fails
- We ask again fifteen seconds later and record the second answer, so one dropped connection is not published as ten minutes of outage. If the provider still cannot be reached, we test our own side before blaming theirs: whether our server stalled while the check was in flight, whether other providers failed to connect at the same moment, and whether two independent control endpoints answer. Any of those means the failure was ours: it is listed under checks we could not make and counts as neither uptime nor downtime.
- What we do not claim
- One probe, every 10 minutes, from one machine in Germany, on one account. A provider can be down for us and up for you, or the reverse. If your own traffic disagrees with this page, trust your own traffic.
- When a provider is down
- We stop benchmarking it rather than publishing a number we did not measure, and run the missed models as soon as it answers again. An outage leaves a gap in the charts, and that gap is deliberate.
- The same data by API
- GET
/api/v1/providersand GET/api/v1/analytics/provider-reliabilityreturn these figures with a free Data API key; both are on the API reference.
Figures generated 26 Oct 2026, 17:25 UTC; this page is rebuilt from the feed about once a minute.
FAQ
Questions about AI provider status
Answers computed from the feed as of 26 Oct 2026, 17:20 UTC.
Is OpenAI, Anthropic or Google down right now?
How do you check whether an AI provider is down?
One short completion on our own key, from one machine in Germany. Every 10 minutes we send the same short request to every provider's API on our own account and record whether usable content came back and how long it took; a provider that has not answered within 60 seconds is recorded as not answering. A failed check is tried again fifteen seconds later and only the second answer is recorded, so one dropped connection is never published as ten minutes of outage. "Slow" means the reply took longer than 5 seconds from our machine, so the median sits next to it. The record is kept for 7 days.
Why does a provider say "not measured"?
Because the check failed on our side, not the provider's: an issue with our own account, our own request or our own server (its event loop frozen while the check was in flight, several providers failing to connect at the same moment, or two independent control endpoints not answering either). We publish those checks as not measured rather than hiding them, and they count as neither uptime nor downtime, so a problem of ours never shows up as somebody else's downtime and the uptime figures only ever divide real observations.
Is this the same as the providers' official status pages?
No. An official status page is the provider's own report of its own services. This page is an independent measurement: one real completion to each API on our own account, every 10 minutes, with every check we could make counted and every check we could not make listed separately. The two can disagree; when they do, the one that matches your own traffic is the one to trust. The official pages we know of: status.openai.com, status.claude.com, aistudio.google.com/status, status.deepseek.com. The same figures are on the Data API as GET /api/v1/providers and GET /api/v1/analytics/provider-reliability, documented on the API reference.
Can I get an email when a provider goes down?
Yes, on any plan. A free account can turn on provider outage emails in account settings: when a provider you track or have connected keys for stops answering our checks for 20 minutes or more you get an email, and another when it answers again. The Smart Router handles the outage itself: it skips a provider that is not answering and routes the request to the next best model, on your own provider keys, with 1,000 routed requests a month free.
By provider