HomeIncidents
Data API

AI API outages on September 28, 2026

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

On September 28, 2026 (UTC) our probes attributed 2 outage(s) to 1 provider(s): Gemini API (Google): 2. Providers’ own status pages opened 1 entry (TypeSafe).

This page is history. Is it down right now?

Live status, updated every 30 minutes: Gemini API (Google), TypeSafe API, baichuan API, friendli API, iflytek API, stepfun API · all AI APIs, last 72 hours

Was the Gemini API (Google) down on September 28, 2026?

Yes, measured. 2 outage(s) attributed to Google: requests to gemini-flash-lite-latest failed from up to 3 of 4 regions at once while no other provider was failing, first at 02:25 UTC, at least 20 minutes observed in total.

UTCWhat failedRegionsDurationFailed probesVerdictError
02:25–02:45requests to gemini-flash-lite-latest3 of 4: Asia (Tokyo), Europe (Germany), US (Central)≥20 min3provider outagetimeout
05:05–05:05requests to gemini-flash-lite-latest2 of 4: South America (São Paulo), US (Central)<5 min2shared with 1 other provider(s) — not attributedtimeout
06:05–06:05requests to gemini-flash-lite-latest2 of 4: South America (São Paulo), US (Central)<5 min2provider outagetimeout
06:45–07:05requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥20 min5shared with 2 other provider(s) — not attributedtimeout
08:55–09:05requests to gemini-flash-lite-latest2 of 4: Asia (Tokyo), Europe (Germany)≥9 min2shared with 1 other provider(s) — not attributedtimeout
11:45–18:25requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥400 min80shared with 18 other provider(s) — not attributedhttp 503; timeout
19:05–21:45requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥160 min31shared with 3 other provider(s) — not attributedhttp 503; timeout
22:35–22:45requests to gemini-flash-lite-latest2 of 4: Europe (Germany), South America (São Paulo)≥9 min2shared with 1 other provider(s) — not attributedtimeout

Current Gemini API (Google) status

Was the TypeSafe API down on September 28, 2026?

Not attributably. 5 multi-region failure(s) of TypeSafe coincided with failures of other providers, so the cause sat above TypeSafe and is not blamed on it. TypeSafe’s own status page opened 1 entry that day (self-reported, listed below).

UTCWhat failedRegionsDurationFailed probesVerdictError
13:21–13:50host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥29 min9shared with 2 other provider(s) — not attributedhttp 503; timeout
13:35–13:35requests to jev-1.13.02 of 4: Europe (Germany), US (Central)<5 min2shared with 2 other provider(s) — not attributedhttp 503
14:55–14:55requests to jev-1.13.02 of 4: Asia (Tokyo), US (Central)<5 min2shared with 1 other provider(s) — not attributedtimeout
15:01–15:25host probes3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo)≥24 min5shared with 3 other provider(s) — not attributedtimeout
16:00–16:06host probes2 of 4: Europe (Germany), South America (São Paulo)≥6 min2shared with 2 other provider(s) — not attributedtimeout

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

Current TypeSafe API status

Was the baichuan API down on September 28, 2026?

Not attributably. 4 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
00:50–01:00host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥10 min2shared with 1 other provider(s) — not attributedtimeout
07:30–07:45host probes2 of 4: Asia (Tokyo), US (Central)≥15 min2shared with 1 other provider(s) — not attributed[Errno 101] Network is unreachable; timeout
09:10–09:25host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥15 min2shared with 1 other provider(s) — not attributed[Errno 101] Network is unreachable; timeout
14:00–14:05host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥5 min2shared with 5 other provider(s) — not attributedtimeout

Current baichuan API status

Was the friendli API down on September 28, 2026?

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

UTCWhat failedRegionsDurationFailed probesVerdictError
12:55–13:00host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥5 min3shared with 5 other provider(s) — not attributedtimeout

Current friendli API status

Was the iflytek API down on September 28, 2026?

Not attributably. 2 multi-region failure(s) of iflytek coincided with failures of other providers, so the cause sat above iflytek and is not blamed on it.

UTCWhat failedRegionsDurationFailed probesVerdictError
10:10–10:15host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥5 min2shared with 1 other provider(s) — not attributed[Errno 104] Connection reset by peer; timeout
14:05–14:25host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥20 min3shared with 11 other provider(s) — not attributedtimeout

Current iflytek API status

Was the stepfun API down on September 28, 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
14:05–14:20host probes2 of 4: South America (São Paulo), US (Central)≥15 min2shared with 10 other provider(s) — not attributedtimeout

Current stepfun API status

83 single-region failure(s) were also recorded that day (iflytek 23, baichuan 20, google 7, deepinfra 5, stepfun 3, sensenova 3, aleph-alpha 3, doubao 2, fireworks 2, minimax 2). 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