# AI API outages on October 20, 2026 (UTC)

Measured every 5 minutes from 4 regions. An outage is attributed to a provider only when it failed from 2+ regions at once and no other provider failed in the same minutes.

## 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 (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 14:00-14:01 | requests to gemini-flash-lite-latest | eu-hetzner us-central | <5 min | 2 | unattributed |
| 14:20-14:21 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed |
| 14:40-14:41 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed |
| 15:00-15:01 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed |
| 15:20-15:21 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed |
| 15:40-15:41 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed |
| 16:00-16:01 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | provider_outage |
| 16:20-16:21 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | provider_outage |
| 16:40-16:41 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed |
| 17:00-17:01 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | provider_outage |
| 17:20-17:20 | requests to gemini-flash-lite-latest | ap-tokyo sa-east us-central | <5 min | 3 | unattributed |
| 17:40-17:41 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=1 min | 4 | unattributed |
| 18:40-18:41 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner | <5 min | 2 | provider_outage |
| 19:20-19:21 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | provider_outage |
| 19:40-19:40 | requests to gemini-flash-lite-latest | ap-tokyo sa-east us-central | <5 min | 3 | provider_outage |

Live status now: https://llmlatency.dev/provider/google

## 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 (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 20:25-20:25 | host probes | ap-tokyo sa-east | <5 min | 2 | provider_outage |

Live status now: https://llmlatency.dev/provider/writer

## 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 01:35 UTC: Elevated errors on Model APIs (minor)
- self-reported 19:04 UTC: DeepSeek V4.1 Flash Fast Outage on Model APIs (major)

Live status now: https://llmlatency.dev/provider/baseten

## 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 (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 02:20-02:35 | host probes | ap-tokyo sa-east | >=15 min | 3 | unattributed |
| 03:30-03:50 | host probes | ap-tokyo eu-hetzner | >=20 min | 3 | unattributed |
| 07:10-07:19 | host probes | eu-hetzner sa-east | >=9 min | 2 | unattributed |
| 18:16-18:30 | host probes | eu-hetzner us-central | >=14 min | 2 | unattributed |

Live status now: https://llmlatency.dev/provider/doubao

## 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 (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 04:55-05:25 | host probes | ap-tokyo us-central | >=30 min | 4 | unattributed |
| 06:10-06:30 | host probes | ap-tokyo sa-east | >=20 min | 3 | unattributed |
| 11:50-11:55 | host probes | ap-tokyo sa-east | >=5 min | 2 | unattributed |
| 12:30-12:30 | host probes | ap-tokyo sa-east | <5 min | 2 | unattributed |
| 14:00-14:25 | host probes | ap-tokyo sa-east | >=25 min | 3 | unattributed |
| 15:05-15:05 | host probes | ap-tokyo sa-east | <5 min | 2 | unattributed |

Live status now: https://llmlatency.dev/provider/yi-01ai

Source: https://llmlatency.dev/incidents/2026-10-20 · CC BY 4.0