AI API outages on October 9, 2026
UTC day · measured every 5 minutes from 4 regions · method
On October 9, 2026 (UTC) our probes attributed 3 outage(s) to 3 provider(s): Gemini API (Google): 1; doubao API: 1; yi-01ai API: 1. Providers’ own status pages opened 4 entries (OpenAI, baseten).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Gemini API (Google), doubao API, yi-01ai API, OpenAI API, baseten API · all AI APIs, last 72 hours
Was the Gemini API (Google) down on October 9, 2026?
Yes, measured. 1 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 07:01 UTC, at least 9 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 |
|---|---|---|---|---|---|---|
| 05:30–05:30 | 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 | http 503 |
| 07:01–07:10 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), South America (São Paulo) | ≥9 min | 2 | provider outage | http 503; timeout |
| 11:30–11:30 | 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 | http 503; timeout |
Is the Gemini API (Google) down right now? Live status →
Was the doubao API down on October 9, 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 14:35 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 00:40–00:40 | host probes | 2 of 4: Asia (Tokyo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 14:35–14:36 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | <5 min | 2 | provider outage | timeout |
Is the doubao API down right now? Live status →
Was the yi-01ai API down on October 9, 2026?
Yes, measured. 1 outage(s) attributed to yi-01ai: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 10:10 UTC, at least 65 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 10:10–11:15 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥65 min | 7 | provider outage | timeout |
Is the yi-01ai API down right now? Live status →
Was the OpenAI API down on October 9, 2026?
Not by our measurements. No failure of OpenAI was seen from two or more regions at once. OpenAI’s own status page opened 3 entries that day (self-reported, listed below).
Self-reported on OpenAI’s status page, not verified by our probes:
- minor Delayed Costs data in the Compliance API · resolved — UTC
- major Some ChatGPT content may be unavailable on Android · resolved Oct 10, 00:26 UTC
- major Workspace admins may be unable to manage plugins · resolved Oct 9, 23:26 UTC
Is the OpenAI API down right now? Live status →
Was the baseten API down on October 9, 2026?
Not by our measurements. No failure of baseten was seen from two or more regions at once. baseten’s own status page opened 1 entry that day (self-reported, listed below).
Self-reported on baseten’s status page, not verified by our probes:
- minor Elevated errors on new model builds. Existing models are not affected · resolved Oct 9, 22:06 UTC
Is the baseten API down right now? Live status →
40 single-region failure(s) were also recorded that day (yi-01ai 15, iflytek 7, baichuan 7, doubao 4, featherless 2, writer 1, cerebras 1, google 1, sensenova 1, ernie 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.
Machine-readable: incidents.json · Licence: CC BY 4.0