AI API outages on October 2, 2026
UTC day · measured every 5 minutes from 4 regions · method
On October 2, 2026 (UTC) our probes attributed 3 outage(s) to 3 provider(s): SambaNova API: 1; doubao API: 1; sensenova API: 1. Providers’ own status pages opened 3 entries (OpenAI, nebius).
This page is history. Is it down right now?
Live status, updated every 30 minutes: SambaNova API, doubao API, sensenova API, OpenAI API, Gemini API (Google), xAI API · all AI APIs, last 72 hours
Was the SambaNova API down on October 2, 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 19:52 UTC, at least 30 minutes observed in total. SambaNova’s status page lists nothing that day.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:23–06:28 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥185 min | 33 | shared with 39 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
| 06:43–08:43 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥120 min | 21 | shared with 37 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
| 19:52–20:22 | host probes | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | ≥30 min | 17 | provider outage | timeout |
Is the SambaNova API down right now? Live status →
Was the doubao API down on October 2, 2026?
Yes, measured. 1 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 21:18 UTC, at least 11 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:23–03:46 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥23 min | 6 | shared with 25 other provider(s) — not attributed | [Errno -5] No address associated with hostname; timeout |
| 04:13–05:08 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥55 min | 9 | shared with 24 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
| 21:18–21:30 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥11 min | 2 | provider outage | timeout |
Is the doubao API down right now? Live status →
Was the sensenova API down on October 2, 2026?
Yes, measured. 1 outage(s) attributed to sensenova: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 22:30 UTC, at least 2 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:51–04:02 | host probes | 2 of 4: Europe (Germany), US (Central) | ≥10 min | 2 | shared with 21 other provider(s) — not attributed | [Errno -2] Name or service not known; timeout |
| 22:30–22:32 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥2 min | 4 | provider outage | timeout |
Is the sensenova API down right now? Live status →
Was the OpenAI API down on October 2, 2026?
Not by our measurements. No failure of OpenAI was seen from two or more regions at once; 5 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:
- minor Issues with data analysis and file creation in ChatGPT · resolved Oct 2, 16:51 UTC
Is the OpenAI API down right now? Live status →
Was the Gemini API (Google) down on October 2, 2026?
Not attributably. 2 multi-region failure(s) of Google coincided with failures of other providers, so the cause sat above Google and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 04:57–05:17 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), US (Central) | ≥20 min | 3 | shared with 14 other provider(s) — not attributed | timeout |
| 17:38–17:51 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), US (Central) | ≥13 min | 2 | shared with 11 other provider(s) — not attributed | http 503; timeout |
Is the Gemini API (Google) down right now? Live status →
Was the xAI API down on October 2, 2026?
Not attributably. 2 multi-region failure(s) of xAI coincided with failures of other providers, so the cause sat above xAI and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:51–04:03 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥12 min | 2 | shared with 25 other provider(s) — not attributed | [Errno 101] Network is unreachable |
| 07:56–08:03 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥7 min | 2 | shared with 18 other provider(s) — not attributed | [Errno 101] Network is unreachable |
Is the xAI API down right now? Live status →
Was the nebius API down on October 2, 2026?
Not by our measurements. No failure of nebius was seen from two or more regions at once; 14 single-region failure(s) are not called an outage. nebius’s own status page opened 2 entries that day (self-reported, listed below).
Self-reported on nebius’s status page, not verified by our probes:
- major Compute VM creation and Object storage are partial unavailable · resolved Oct 2, 02:07 UTC
- minor Issues with preempted Managed Kubernetes nodes in all regions · resolved — UTC
Is the nebius API down right now? Live status →
Was the aleph-alpha API down on October 2, 2026?
Not attributably. 1 multi-region failure(s) of aleph-alpha coincided with failures of other providers, so the cause sat above aleph-alpha and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:46–04:28 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥42 min | 12 | shared with 29 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
Is the aleph-alpha API down right now? Live status →
Was the baichuan API down on October 2, 2026?
Not attributably. 1 multi-region failure(s) of baichuan coincided with failures of other providers, so the cause sat above baichuan and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 15:55–16:30 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥35 min | 6 | shared with 9 other provider(s) — not attributed | [Errno 101] Network is unreachable; timeout |
Is the baichuan API down right now? Live status →
Was the deepinfra API down on October 2, 2026?
Not attributably. 2 multi-region failure(s) of deepinfra coincided with failures of other providers, so the cause sat above deepinfra and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:46–04:08 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥22 min | 6 | shared with 28 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
| 07:23–08:38 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥75 min | 11 | shared with 31 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
Is the deepinfra API down right now? Live status →
Was the friendli API down on October 2, 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.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:23–03:56 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥33 min | 5 | shared with 30 other provider(s) — not attributed | [Errno -5] No address associated with hostname; timeout |
Is the friendli API down right now? Live status →
Was the glm API down on October 2, 2026?
Not attributably. 1 multi-region failure(s) of glm coincided with failures of other providers, so the cause sat above glm and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:56–03:58 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥2 min | 2 | shared with 18 other provider(s) — not attributed | [Errno 101] Network is unreachable; timeout |
Is the glm API down right now? Live status →
Was the minimax API down on October 2, 2026?
Not attributably. 3 multi-region failure(s) of minimax coincided with failures of other providers, so the cause sat above minimax and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:23–03:58 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥35 min | 7 | shared with 30 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
| 04:18–04:21 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥3 min | 2 | shared with 10 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
| 07:13–08:53 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥100 min | 12 | shared with 34 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
Is the minimax API down right now? Live status →
Was the nscale API down on October 2, 2026?
Not attributably. 2 multi-region failure(s) of nscale coincided with failures of other providers, so the cause sat above nscale and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:23–03:56 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥33 min | 8 | shared with 30 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
| 07:33–08:03 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥30 min | 6 | shared with 23 other provider(s) — not attributed | [Errno -5] No address associated with hostname |
Is the nscale API down right now? Live status →
Was the stepfun API down on October 2, 2026?
Not attributably. 1 multi-region failure(s) of stepfun coincided with failures of other providers, so the cause sat above stepfun and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:48–03:56 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥8 min | 2 | shared with 26 other provider(s) — not attributed | [Errno -3] Temporary failure in name resolution; [Errno 101] |
Is the stepfun API down right now? Live status →
Was the targon API down on October 2, 2026?
Not attributably. 1 multi-region failure(s) of targon coincided with failures of other providers, so the cause sat above targon and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:58–04:21 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥23 min | 3 | shared with 21 other provider(s) — not attributed | [Errno -5] No address associated with hostname; timeout |
Is the targon API down right now? Live status →
Was the yi-01ai API down on October 2, 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.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 07:50–08:13 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥24 min | 5 | shared with 23 other provider(s) — not attributed | timeout |
Is the yi-01ai API down right now? Live status →
330 single-region failure(s) were also recorded that day (yi-01ai 18, cerebras 16, targon 15, nebius 14, qwen 13, upstage 12, hunyuan 11, xai 11, google 10, siliconflow 10). 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.
Machine-readable: incidents.json · Licence: CC BY 4.0