# AI API outages on October 28, 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 yi-01ai API down on October 28, 2026?

Yes, measured. 2 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 10:55 UTC, at least 43 minutes observed in total.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 10:55-11:10 | host probes | ap-tokyo sa-east | >=15 min | 2 | provider_outage |
| 12:22-12:50 | host probes | ap-tokyo eu-hetzner | >=28 min | 5 | provider_outage |

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

## Was the Gemini API (Google) down on October 28, 2026?

Yes, measured. 1 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 16:40 UTC, at least 5 minutes observed in total.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 13:02-14:25 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=83 min | 15 | unattributed |
| 14:42-16:02 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=80 min | 16 | unattributed |
| 16:20-16:22 | requests to gemini-flash-lite-latest | eu-hetzner sa-east | >=2 min | 2 | unattributed |
| 16:40-16:45 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | provider_outage |
| 17:02-18:25 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=83 min | 17 | unattributed |

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

## Was the glm API down on October 28, 2026?

Yes, measured. 1 outage(s) attributed to glm: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 20:55 UTC, each shorter than one 5-minute probe cycle.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 20:55-20:55 | host probes | sa-east us-central | <5 min | 2 | provider_outage |

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

## Was the Claude API (Anthropic) down on October 28, 2026?

Not by our measurements. No failure of Anthropic was seen from two or more regions at once. Anthropic's own status page opened 2 entries that day (self-reported, listed below).
- self-reported 03:59 UTC: Elevated errors affecting the Gmail connector (minor)
- self-reported 16:19 UTC: Elevated errors affecting the Google Calendar connector (minor)

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

## Was the nebius API down on October 28, 2026?

Not by our measurements. No failure of nebius was seen from two or more regions at once. nebius's own status page opened 1 entry that day (self-reported, listed below).
- self-reported 11:00 UTC: Compute Cloud: disk images and snapshots partial unavailability (major)

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

## Was the baichuan API down on October 28, 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 (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 14:35-14:35 | host probes | ap-tokyo us-central | <5 min | 2 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-10-28 · CC BY 4.0