AI API outages on September 22, 2026

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

On September 22, 2026 (UTC) our probes attributed 8 outage(s) to 2 provider(s): Gemini API (Google): 7; SambaNova API: 1. Providers’ own status pages opened 4 entries (OpenAI, Anthropic, nebius).

This page is history. Is it down right now?

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

Was the Gemini API (Google) down on September 22, 2026?

Yes, measured. 7 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 11:35 UTC, at least 31 minutes observed in total. At least once Google’s own host answered with an HTTP 5xx.

UTCWhat failedRegionsDurationFailed probesVerdictError
11:35–11:38requests to gemini-flash-lite-latest2 of 4: Europe (Germany), South America (São Paulo)≥3 min2provider outagetimeout
12:55–12:58requests to gemini-flash-lite-latest2 of 4: Europe (Germany), South America (São Paulo)≥3 min2provider outagetimeout
13:35–13:35requests to gemini-flash-lite-latest2 of 4: South America (São Paulo), US (Central)<5 min2shared with 2 other provider(s) — not attributedtimeout
14:13–14:18requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥5 min4provider outagetimeout
14:33–14:38requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥5 min4provider outagehttp 503; timeout
14:53–14:58requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥5 min4shared with 1 other provider(s) — not attributedhttp 503; timeout
15:13–15:18requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥5 min4provider outagehttp 503
15:33–15:38requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥5 min4shared with 1 other provider(s) — not attributedhttp 503; timeout
15:53–16:18requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥25 min8shared with 1 other provider(s) — not attributedhttp 503; timeout
16:33–16:38requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥5 min4provider outagehttp 503; timeout
16:53–16:58requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥5 min4provider outagetimeout
17:13–17:38requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥25 min8shared with 1 other provider(s) — not attributedhttp 503; timeout
17:53–17:58requests to gemini-flash-lite-latest4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥5 min4shared with 1 other provider(s) — not attributedhttp 503; timeout
18:13–18:15requests to gemini-flash-lite-latest3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)≥2 min3shared with 1 other provider(s) — not attributedtimeout

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

Was the SambaNova API down on September 22, 2026?

Yes, measured. 1 outage(s) attributed to SambaNova: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 07:05 UTC, at least 3 minutes observed in total. SambaNova’s status page lists nothing that day.

UTCWhat failedRegionsDurationFailed probesVerdictError
07:05–07:08host probes2 of 4: Europe (Germany), South America (São Paulo)≥3 min2provider outagetimeout
07:50–07:50host probes2 of 4: South America (São Paulo), US (Central)<5 min2shared with 1 other provider(s) — not attributedtimeout

Is the SambaNova API down right now? Live status →

Was the OpenAI API down on September 22, 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 2 entries that day (self-reported, listed below).

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

Is the OpenAI API down right now? Live status →

Was the Claude API (Anthropic) down on September 22, 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:

Is the Claude API (Anthropic) down right now? Live status →

Was the nebius API down on September 22, 2026?

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

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

Is the nebius API down right now? Live status →

Was the hunyuan API down on September 22, 2026?

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

UTCWhat failedRegionsDurationFailed probesVerdictError
12:45–12:45host probes2 of 4: South America (São Paulo), US (Central)<5 min2shared with 2 other provider(s) — not attributedtimeout

Is the hunyuan API down right now? Live status →

Was the yi-01ai API down on September 22, 2026?

Not attributably. 1 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
06:10–06:45host probes2 of 4: Asia (Tokyo), Europe (Germany)≥35 min5shared with 1 other provider(s) — not attributedtimeout

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

54 single-region failure(s) were also recorded that day (yi-01ai 27, google 7, sambanova 2, doubao 2, iflytek 2, hunyuan 2, stepfun 2, featherless 2, openai 1, openrouter 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