# AI API outages on October 17, 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 doubao API down on October 17, 2026?

Yes, measured. 3 outage(s) attributed to doubao: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 06:53 UTC, at least 32 minutes observed in total.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 06:53-06:55 | host probes | eu-hetzner sa-east us-central | >=2 min | 3 | provider_outage |
| 07:35-07:45 | host probes | ap-tokyo sa-east | >=10 min | 3 | provider_outage |
| 16:20-16:40 | host probes | eu-hetzner sa-east | >=20 min | 3 | provider_outage |

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

## Was the yi-01ai API down on October 17, 2026?

Not attributably. 3 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 |
| --- | --- | --- | --- | --- | --- |
| 01:35-01:35 | host probes | ap-tokyo sa-east | <5 min | 2 | unattributed |
| 04:05-04:10 | host probes | ap-tokyo sa-east | >=5 min | 2 | unattributed |
| 10:50-11:05 | host probes | ap-tokyo sa-east | >=15 min | 3 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-10-17 · CC BY 4.0