AI API outages on September 23, 2026
UTC day · measured every 5 minutes from 4 regions · method
On September 23, 2026 (UTC) our probes attributed 5 outage(s) to 2 provider(s): Gemini API (Google): 4; aleph-alpha API: 1. Providers’ own status pages opened 4 entries (OpenAI, TypeSafe, nebius).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Gemini API (Google), aleph-alpha API, OpenAI API, TypeSafe API, SambaNova API, nebius API · all AI APIs, last 72 hours
Was the Gemini API (Google) down on September 23, 2026?
Yes, measured. 4 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 06:14 UTC, at least 19 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 06:14–06:18 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), US (Central) | ≥4 min | 2 | provider outage | timeout |
| 12:00–12:15 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), Europe (Germany) | ≥15 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 13:00–13:15 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), South America (São Paulo) | ≥15 min | 2 | provider outage | timeout |
| 13:35–17:35 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥240 min | 51 | shared with 8 other provider(s) — not attributed | http 503; timeout |
| 17:55–17:55 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | timeout |
| 18:35–18:35 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | timeout |
Current Gemini API (Google) status
Was the aleph-alpha API down on September 23, 2026?
Yes, measured. 1 outage(s) attributed to aleph-alpha: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 19:30 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 19:30–19:30 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | [Errno 113] No route to host |
Current aleph-alpha API status
Was the OpenAI API down on September 23, 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:
- minor Elevated Error Rates for ChatGPT across Plus and Pro plans. · resolved Sep 23, 09:54 UTC
- minor Mobile users unable to see Work Mode and the Model Picker · resolved Sep 23, 23:49 UTC
Was the TypeSafe API down on September 23, 2026?
Not by our measurements. No failure of TypeSafe was seen from two or more regions at once. TypeSafe’s own status page opened 1 entry that day (self-reported, listed below).
Self-reported on TypeSafe’s status page, not verified by our probes:
- notice Elevated API latency and connection issues · resolved Sep 23, 20:56 UTC
Was the SambaNova API down on September 23, 2026?
Not attributably. 1 multi-region failure(s) of SambaNova coincided with failures of other providers, so the cause sat above SambaNova and is not blamed on it. SambaNova’s status page lists nothing that day.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 12:50–12:50 | host probes | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
Was the nebius API down on September 23, 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:
- major Network issues in eu-west2 · resolved Sep 23, 08:32 UTC
34 single-region failure(s) were also recorded that day (doubao 6, baichuan 5, iflytek 5, ernie 2, friendli 2, hunyuan 2, stepfun 2, google 2, sensenova 2, deepinfra 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.
Previous: Sep 22 · Last 72 hours · Next: Sep 24
Machine-readable: incidents.json · Licence: CC BY 4.0