AI API outages on September 21, 2026

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

On September 21, 2026 (UTC) our probes attributed 5 outage(s) to 2 provider(s): Gemini API (Google): 3; featherless API: 2. Providers’ own status pages opened 2 entries (baseten).

This page is history. Is it down right now?

Live status, updated every 30 minutes: Gemini API (Google), featherless API, baseten API, iflytek API, minimax API, yi-01ai API · all AI APIs, last 72 hours

Was the Gemini API (Google) down on September 21, 2026?

Yes, measured. 3 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 01:15 UTC, at least 6 minutes observed in total. At least once Google’s own host answered with an HTTP 5xx.

UTCWhat failedRegionsDurationFailed probesVerdictError
01:15–01:18requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥3 min4provider outagehttp 503; timeout
14:15–14:18requests to gemini-flash-lite-latest2 of 4: Europe (Germany), South America (São Paulo)≥3 min2shared with 3 other provider(s) — not attributedtimeout
14:35–14:35requests to gemini-flash-lite-latest3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)<5 min3shared with 1 other provider(s) — not attributedtimeout
14:55–14:58requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥3 min4provider outagetimeout
15:15–15:18requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥3 min4shared with 1 other provider(s) — not attributedtimeout
19:15–19:15requests to gemini-flash-lite-latest2 of 4: South America (São Paulo), US (Central)<5 min2provider outagetimeout

Is the Gemini API (Google) down right now? Live status →

Was the featherless API down on September 21, 2026?

Yes, measured. 2 outage(s) attributed to featherless: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 01:53 UTC, at least 4 minutes observed in total.

UTCWhat failedRegionsDurationFailed probesVerdictError
01:53–01:55host probes2 of 4: Europe (Germany), US (Central)≥2 min2provider outagetimeout
03:20–03:20host probes2 of 4: Asia (Tokyo), US (Central)<5 min2shared with 1 other provider(s) — not attributedtimeout
03:40–04:10host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥30 min7shared with 2 other provider(s) — not attributedtimeout
04:50–04:55host probes2 of 4: Asia (Tokyo), US (Central)≥5 min2shared with 1 other provider(s) — not attributedtimeout
05:23–06:00host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥37 min8shared with 1 other provider(s) — not attributedtimeout
09:00–09:15host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥15 min4shared with 1 other provider(s) — not attributedtimeout
10:03–10:05host probes2 of 4: Asia (Tokyo), Europe (Germany)≥2 min2provider outagetimeout
10:25–10:38host probes2 of 4: Europe (Germany), US (Central)≥13 min2shared with 1 other provider(s) — not attributedtimeout
12:05–12:20host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥15 min2shared with 1 other provider(s) — not attributedtimeout
14:13–14:25host probes2 of 4: Europe (Germany), US (Central)≥12 min2shared with 3 other provider(s) — not attributedtimeout
16:25–16:45host probes3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)≥20 min3shared with 2 other provider(s) — not attributedtimeout
18:05–19:55host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥110 min28shared with 3 other provider(s) — not attributedtimeout

Is the featherless API down right now? Live status →

Was the baseten API down on September 21, 2026?

Not by our measurements. No failure of baseten was seen from two or more regions at once. baseten’s own status page opened 2 entries that day (self-reported, listed below).

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

Is the baseten API down right now? Live status →

Was the iflytek API down on September 21, 2026?

Not attributably. 1 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
14:03–14:05host probes2 of 4: Europe (Germany), South America (São Paulo)≥2 min2shared with 3 other provider(s) — not attributedtimeout

Is the iflytek API down right now? Live status →

Was the minimax API down on September 21, 2026?

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

UTCWhat failedRegionsDurationFailed probesVerdictError
13:10–13:15host probes2 of 4: South America (São Paulo), US (Central)≥5 min3shared with 1 other provider(s) — not attributedtimeout

Is the minimax API down right now? Live status →

Was the yi-01ai API down on September 21, 2026?

Not attributably. 2 multi-region failure(s) of yi-01ai coincided with failures of other providers, so the cause sat above yi-01ai and is not blamed on it.

UTCWhat failedRegionsDurationFailed probesVerdictError
05:00–05:25host probes2 of 4: Asia (Tokyo), US (Central)≥25 min4shared with 2 other provider(s) — not attributedtimeout
14:05–14:25host probes2 of 4: Asia (Tokyo), US (Central)≥20 min3shared with 5 other provider(s) — not attributedtimeout

Is the yi-01ai API down right now? Live status →

63 single-region failure(s) were also recorded that day (yi-01ai 24, featherless 8, google 5, nebius 4, hunyuan 4, qwen 3, sambanova 3, aleph-alpha 2, minimax 2, openrouter 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