HomeIncidents
Data API

AI API outages on October 1, 2026

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

On October 1, 2026 (UTC) our probes attributed 7 outage(s) to 3 provider(s): doubao API: 3; Gemini API (Google): 2; SambaNova API: 2. Providers’ own status pages opened 2 entries (Anthropic, OpenAI).

This page is history. Is it down right now?

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

Was the doubao API down on October 1, 2026?

Yes, measured. 3 outage(s) attributed to doubao: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 03:40 UTC, at least 16 minutes observed in total.

UTCWhat failedRegionsDurationFailed probesVerdictError
03:40–03:40host probes2 of 4: Asia (Tokyo), South America (São Paulo)<5 min2provider outagetimeout
04:40–04:55host probes2 of 4: South America (São Paulo), US (Central)≥15 min3provider outagetimeout
15:51–15:52host probes2 of 4: Europe (Germany), US (Central)<5 min2provider outagetimeout

Current doubao API status

Was the Gemini API (Google) down on October 1, 2026?

Yes, measured. 2 outage(s) attributed to Google: requests to gemini-flash-lite-latest failed from up to 2 of 4 regions at once while no other provider was failing, first at 11:25 UTC, at least 24 minutes observed in total.

UTCWhat failedRegionsDurationFailed probesVerdictError
11:25–11:37requests to gemini-flash-lite-latest2 of 4: Europe (Germany), South America (São Paulo)≥12 min2provider outagetimeout
14:05–14:17requests to gemini-flash-lite-latest2 of 4: Europe (Germany), South America (São Paulo)≥12 min2provider outagetimeout
18:06–18:37requests to gemini-flash-lite-latest2 of 4: Europe (Germany), US (Central)≥30 min4shared with 3 other provider(s) — not attributedhttp 503; timeout

Current Gemini API (Google) status

Was the SambaNova API down on October 1, 2026?

Yes, measured. 2 outage(s) attributed to SambaNova: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 21:35 UTC, at least 14 minutes observed in total. SambaNova’s status page lists nothing that day.

UTCWhat failedRegionsDurationFailed probesVerdictError
21:35–21:37host probes2 of 4: Europe (Germany), South America (São Paulo)≥2 min2provider outagetimeout
22:05–22:16host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥12 min4provider outagetimeout

Current SambaNova API status

Was the Claude API (Anthropic) down on October 1, 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 OpenAI API down on October 1, 2026?

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

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

  • major Issues with login, signup, and ads · resolved Oct 1, 19:39 UTC

Current OpenAI API status

Was the stepfun API down on October 1, 2026?

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

UTCWhat failedRegionsDurationFailed probesVerdictError
17:38–17:40host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥2 min2shared with 1 other provider(s) — not attributedtimeout

Current stepfun API status

27 single-region failure(s) were also recorded that day (google 12, iflytek 4, deepinfra 2, aleph-alpha 2, baichuan 2, stepfun 2, writer 1, sensenova 1, fireworks 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