AI API outages on October 20, 2026
UTC day · measured every 5 minutes from 4 regions · method
On October 20, 2026 (UTC) our probes attributed 7 outage(s) to 2 provider(s): Gemini API (Google): 6; writer API: 1. Providers’ own status pages opened 2 entries (baseten).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Gemini API (Google), writer API, baseten API, doubao API, yi-01ai API · all AI APIs, last 72 hours
Was the Gemini API (Google) down on October 20, 2026?
Yes, measured. 6 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 16:00 UTC, at least 4 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 14:00–14:01 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), US (Central) | <5 min | 2 | shared with 3 other provider(s) — not attributed | timeout |
| 14:20–14:21 | 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 | timeout |
| 14:40–14:41 | 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 | timeout |
| 15:00–15:01 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 3 other provider(s) — not attributed | timeout |
| 15:20–15:21 | 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 | timeout |
| 15:40–15:41 | 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 | timeout |
| 16:00–16:01 | 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 |
| 16:20–16:21 | 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 |
| 16:40–16:41 | 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 | timeout |
| 17:00–17:01 | 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 |
| 17:20–17:20 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
| 17:40–17:41 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥1 min | 4 | shared with 2 other provider(s) — not attributed | http 503; timeout |
| 18:40–18:41 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), Europe (Germany) | <5 min | 2 | provider outage | timeout |
| 19:20–19:21 | 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 |
| 19:40–19:40 | 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 writer API down on October 20, 2026?
Yes, measured. 1 outage(s) attributed to writer: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 20:25 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 20:25–20:25 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | <5 min | 2 | provider outage | timeout |
Was the baseten API down on October 20, 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:
- minor Elevated errors on Model APIs · resolved Oct 20, 01:43 UTC
- major DeepSeek V4.1 Flash Fast Outage on Model APIs · resolved Oct 20, 19:10 UTC
Was the doubao API down on October 20, 2026?
Not attributably. 4 multi-region failure(s) of doubao coincided with failures of other providers, so the cause sat above doubao and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 02:20–02:35 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥15 min | 3 | shared with 3 other provider(s) — not attributed | timeout |
| 03:30–03:50 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | ≥20 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
| 07:10–07:19 | host probes | 2 of 4: Europe (Germany), South America (São Paulo) | ≥9 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 18:16–18:30 | host probes | 2 of 4: Europe (Germany), US (Central) | ≥14 min | 2 | shared with 2 other provider(s) — not attributed | timeout |
Was the yi-01ai API down on October 20, 2026?
Not attributably. 6 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 |
|---|---|---|---|---|---|---|
| 04:55–05:25 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥30 min | 4 | shared with 1 other provider(s) — not attributed | timeout |
| 06:10–06:30 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥20 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
| 11:50–11:55 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 12:30–12:30 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 14:00–14:25 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥25 min | 3 | shared with 2 other provider(s) — not attributed | timeout |
| 15:05–15:05 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | <5 min | 2 | shared with 3 other provider(s) — not attributed | timeout |
66 single-region failure(s) were also recorded that day (yi-01ai 16, iflytek 11, sensenova 9, doubao 8, google 5, stepfun 5, baichuan 2, writer 2, hunyuan 1, sarvam 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: Oct 19 · Last 72 hours
Machine-readable: incidents.json · Licence: CC BY 4.0