HomeIncidents
Data API

AI API outages on October 6, 2026

UTC day · measured every 5 minutes from 4 regions · method

On October 6, 2026 (UTC) our probes attributed 2 outage(s) to 1 provider(s): Gemini API (Google): 2. Providers’ own status pages opened 7 entries (OpenAI, Anthropic, baseten).

This page is history. Is it down right now?

Live status, updated every 30 minutes: Gemini API (Google), OpenAI API, Claude API (Anthropic), baseten API, baichuan API, doubao API · all AI APIs, last 72 hours

Was the Gemini API (Google) down on October 6, 2026?

Yes, measured. 2 outage(s) attributed to Google: requests to gemini-flash-lite-latest failed from up to 4 of 4 regions at once while no other provider was failing, first at 02:17 UTC, at least 12 minutes observed in total. At least once Google’s own host answered with an HTTP 5xx.

UTCWhat failedRegionsDurationFailed probesVerdictError
02:17–02:30requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥12 min4provider outagetimeout
11:30–11:30requests to gemini-flash-lite-latest2 of 4: Asia (Tokyo), South America (São Paulo)<5 min2shared with 1 other provider(s) — not attributedtimeout
23:30–23:30requests to gemini-flash-lite-latest3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)<5 min3provider outagehttp 503; timeout

Current Gemini API (Google) status

Was the OpenAI API down on October 6, 2026?

Not by our measurements. No failure of OpenAI was seen from two or more regions at once; 1 single-region failure(s) are not called an outage. OpenAI’s own status page opened 5 entries that day (self-reported, listed below).

Self-reported on OpenAI’s status page, not verified by our probes:

  • minor Elevated errors in API Platform login and administration APIs. · resolved Oct 6, 01:35 UTC
  • minor Elevated errors affecting multiple products including ChatGPT (conversations), Image gener · resolved Oct 6, 03:17 UTC
  • minor Elevated error rates in ChatGPT Go conversations · resolved Oct 6, 14:40 UTC
  • minor Errors processing large PDFs in the Responses API · resolved Oct 6, 17:50 UTC
  • minor Computer Use Is Experiencing Issues · resolved Oct 6, 20:00 UTC

Current OpenAI API status

Was the Claude API (Anthropic) down on October 6, 2026?

Not by our measurements. No failure of Anthropic was seen from two or more regions at once. Anthropic’s own status page opened 1 entry that day (self-reported, listed below).

Self-reported on Anthropic’s status page, not verified by our probes:

Current Claude API (Anthropic) status

Was the baseten API down on October 6, 2026?

Not by our measurements. No failure of baseten was seen from two or more regions at once. baseten’s own status page opened 1 entry that day (self-reported, listed below).

Self-reported on baseten’s status page, not verified by our probes:

Current baseten API status

Was the baichuan API down on October 6, 2026?

Not attributably. 1 multi-region failure(s) of baichuan coincided with failures of other providers, so the cause sat above baichuan and is not blamed on it.

UTCWhat failedRegionsDurationFailed probesVerdictError
13:25–13:25host probes2 of 4: South America (São Paulo), US (Central)<5 min2shared with 2 other provider(s) — not attributed[Errno 101] Network is unreachable; timeout

Current baichuan API status

Was the doubao API down on October 6, 2026?

Not attributably. 1 multi-region failure(s) of doubao coincided with failures of other providers, so the cause sat above doubao and is not blamed on it.

UTCWhat failedRegionsDurationFailed probesVerdictError
09:10–09:10host probes2 of 4: South America (São Paulo), US (Central)<5 min2shared with 1 other provider(s) — not attributedtimeout

Current doubao API status

Was the writer API down on October 6, 2026?

Not attributably. 1 multi-region failure(s) of writer coincided with failures of other providers, so the cause sat above writer and is not blamed on it.

UTCWhat failedRegionsDurationFailed probesVerdictError
15:10–15:10host probes2 of 4: South America (São Paulo), US (Central)<5 min2shared with 1 other provider(s) — not attributedtimeout

Current writer API status

26 single-region failure(s) were also recorded that day (google 7, featherless 6, doubao 4, baichuan 2, nebius 1, nscale 1, iflytek 1, friendli 1, openai 1, meta-llama 1). A failure seen from one region cannot be separated from a problem on that network path, so none of them is called an outage.

How is an outage told apart from a network problem?

Each provider is probed every five minutes from 4 independent regions. A failure is attributed to the provider only when it is seen from two or more regions at once and no other provider fails in the same minutes; a failure shared with other providers has a cause above all of them and is not blamed on anyone. Durations are lower bounds: we see the first and last failed probe, not the real start and end. Status-page entries are the provider’s own words, shown next to the measurement, not instead of it.

· Last 72 hours ·

Machine-readable: incidents.json · Licence: CC BY 4.0