AI API outages on September 24, 2026
UTC day · measured every 5 minutes from 4 regions · method
On September 24, 2026 (UTC) our probes attributed 15 outage(s) to 3 provider(s): Gemini API (Google): 12; doubao API: 2; SambaNova API: 1. Providers’ own status pages opened 4 entries (OpenAI, TypeSafe, baseten).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Gemini API (Google), doubao API, SambaNova API, OpenAI API, TypeSafe API, baseten API · all AI APIs, last 72 hours
Was the Gemini API (Google) down on September 24, 2026?
Yes, measured. 12 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 05:15 UTC, at least 4 minutes observed in total. At least once Google’s own host answered with an HTTP 5xx.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 05:15–05:15 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | http 503; timeout |
| 05:55–05:55 | requests to gemini-flash-lite-latest | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 12:00–12:00 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), US (Central) | <5 min | 2 | provider outage | timeout |
| 13:00–13:00 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 2 other provider(s) — not attributed | http 503 |
| 13:20–13:20 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | timeout |
| 13:40–13:40 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | timeout |
| 14:00–14:00 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 1 other provider(s) — not attributed | http 503; timeout |
| 14:20–14:20 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 1 other provider(s) — not attributed | http 503; timeout |
| 14:40–14:40 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | http 503; timeout |
| 15:00–15:00 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 1 other provider(s) — not attributed | http 503; timeout |
| 15:20–15:20 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | http 503; timeout |
| 15:40–15:40 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 1 other provider(s) — not attributed | http 503 |
| 16:00–16:00 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 2 other provider(s) — not attributed | http 503; timeout |
| 16:20–16:20 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | http 503; timeout |
| 16:40–16:40 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | timeout |
| 17:00–17:00 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | <5 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
| 17:40–17:40 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | http 503; timeout |
| 18:00–18:00 | requests to gemini-flash-lite-latest | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | timeout |
| 18:40–18:40 | requests to gemini-flash-lite-latest | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | provider outage | timeout |
| 19:00–19:00 | 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 doubao API down on September 24, 2026?
Yes, measured. 2 outage(s) attributed to doubao: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 06:25 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 06:25–06:25 | host probes | 2 of 4: Europe (Germany), US (Central) | <5 min | 2 | provider outage | timeout |
| 13:05–13:10 | host probes | 2 of 4: Europe (Germany), US (Central) | ≥5 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
| 20:20–20:20 | host probes | 2 of 4: Europe (Germany), US (Central) | <5 min | 2 | provider outage | timeout |
Was the SambaNova API down on September 24, 2026?
Yes, measured. 1 outage(s) attributed to SambaNova: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 23:25 UTC, at least 15 minutes observed in total. SambaNova’s status page lists nothing that day.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 15:45–15:45 | host probes | 2 of 4: Europe (Germany), South America (São Paulo) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 23:25–23:40 | host probes | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | ≥15 min | 4 | provider outage | timeout |
Was the OpenAI API down on September 24, 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 1 entry that day (self-reported, listed below).
Self-reported on OpenAI’s status page, not verified by our probes:
- notice Elevated Error Rates on GPT-6 Astra Pro · resolved Sep 24, 19:46 UTC
Was the TypeSafe API down on September 24, 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 · resolved Sep 24, 07:18 UTC
Was the baseten API down on September 24, 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:
- major Elevated inference 500s for a subset of models deployed in 1 US-East cluster · resolved Sep 24, 08:06 UTC
- minor Intermittent 5xx for a subset of models in 1 US Central cluster · resolved Sep 24, 19:57 UTC
Was the Tencent Hunyuan API down on September 24, 2026?
Not attributably. 1 multi-region failure(s) of Tencent Hunyuan coincided with failures of other providers, so the cause sat above Tencent Hunyuan and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 09:45–10:00 | host probes | 2 of 4: Europe (Germany), South America (São Paulo) | ≥15 min | 5 | shared with 1 other provider(s) — not attributed | timeout |
Current Tencent Hunyuan API status
Was the iflytek API down on September 24, 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.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 16:05–16:05 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), US (Central) | <5 min | 3 | shared with 3 other provider(s) — not attributed | [Errno 104] Connection reset by peer; timeout |
24 single-region failure(s) were also recorded that day (google 5, baichuan 5, iflytek 3, stepfun 3, doubao 2, openai 1, sensenova 1, hunyuan 1, kimi 1, sambanova 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 23 · Last 72 hours · Next: Sep 25
Machine-readable: incidents.json · Licence: CC BY 4.0