AI API outages on September 4, 2026

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

On September 4, 2026 (UTC) our probes attributed 3 outage(s) to 1 provider(s): Gemini API (Google): 3.

This page is history. Is it down right now?

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

Was the Gemini API (Google) down on September 4, 2026?

Yes, measured. 3 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 01:35 UTC, at least 14 minutes observed in total.

UTCWhat failedRegionsDurationFailed probesVerdictError
01:35–01:50requests to gemini-flash-lite-latest2 of 4: Europe (Germany), US (Central)≥14 min2provider outagetimeout
08:35–08:55requests to gemini-flash-lite-latest3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥19 min3shared with 1 other provider(s) — not attributedtimeout
09:35–09:50requests to gemini-flash-lite-latest2 of 4: Europe (Germany), US (Central)≥14 min2shared with 1 other provider(s) — not attributedtimeout
10:10–10:10requests to gemini-flash-lite-latest2 of 4: Asia (Tokyo), US (Central)<5 min2provider outagetimeout
10:55–10:55requests to gemini-flash-lite-latest2 of 4: Europe (Germany), South America (São Paulo)<5 min2shared with 1 other provider(s) — not attributedtimeout
11:15–11:15requests to gemini-flash-lite-latest2 of 4: Europe (Germany), South America (São Paulo)<5 min2shared with 2 other provider(s) — not attributedtimeout
11:35–18:55requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥439 min87shared with 4 other provider(s) — not attributedhttp 503; timeout
19:30–19:30requests to gemini-flash-lite-latest2 of 4: Asia (Tokyo), US (Central)<5 min2provider outagetimeout

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

Was the friendli API down on September 4, 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
08:05–08:06host probes2 of 4: Asia (Tokyo), Europe (Germany)<5 min2shared with 1 other provider(s) — not attributedtimeout

Is the friendli API down right now? Live status →

Was the iflytek API down on September 4, 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
12:05–12:25host probes2 of 4: Asia (Tokyo), Europe (Germany)≥20 min4shared with 2 other provider(s) — not attributedtimeout
13:46–14:05host probes2 of 4: Asia (Tokyo), Europe (Germany)≥19 min3shared with 3 other provider(s) — not attributedtimeout

Is the iflytek API down right now? Live status →

64 single-region failure(s) were also recorded that day (yi-01ai 27, iflytek 12, google 10, doubao 10, hunyuan 2, baichuan 1, stepfun 1, friendli 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