# AI API outages on October 8, 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 8, 2026?

Yes, measured. 2 outage(s) attributed to Google: requests to gemini-flash-lite-latest failed from up to 3 of 4 regions at once while no other provider was failing, first at 01:30 UTC, each shorter than one 5-minute probe cycle.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 01:30-01:30 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | provider_outage |
| 05:50-05:50 | requests to gemini-flash-lite-latest | ap-tokyo sa-east us-central | <5 min | 3 | unattributed |
| 16:38-18:30 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=112 min | 20 | unattributed |
| 18:50-19:10 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=20 min | 8 | unattributed |
| 19:30-19:30 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | unattributed |
| 21:10-21:10 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | unattributed |
| 23:50-23:50 | 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 aleph-alpha API down on October 8, 2026?

Yes, measured. 1 outage(s) attributed to aleph-alpha: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 10:57 UTC, at least 17 minutes observed in total.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 10:57-11:15 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=17 min | 6 | provider_outage |
| 11:50-11:57 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=7 min | 8 | unattributed |

Live status now: https://llmlatency.dev/provider/aleph-alpha

## Was the yi-01ai API down on October 8, 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 05:30 UTC, each shorter than one 5-minute probe cycle.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 01:40-01:40 | host probes | ap-tokyo sa-east | <5 min | 2 | unattributed |
| 05:30-05:30 | host probes | ap-tokyo sa-east | <5 min | 2 | provider_outage |
| 13:17-13:45 | host probes | ap-tokyo eu-hetzner sa-east | >=28 min | 3 | unattributed |
| 15:27-15:40 | host probes | ap-tokyo eu-hetzner | >=13 min | 2 | unattributed |

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

## Was the OpenAI API down on October 8, 2026?

Not by our measurements. No failure of OpenAI was seen from two or more regions at once; 6 single-region failure(s) are not called an outage. OpenAI's own status page opened 1 entry that day (self-reported, listed below).
- self-reported 03:17 UTC: Some APAC users are seeing errors in ChatGPT Work, conversations, and GPTs. (minor)

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

## Was the TypeSafe API down on October 8, 2026?

Not attributably. 2 multi-region failure(s) of TypeSafe coincided with failures of other providers, so the cause sat above TypeSafe and is not blamed on it. TypeSafe's status page lists nothing that day.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 12:50-12:50 | requests to jev-1.13.0 | ap-tokyo sa-east us-central | <5 min | 3 | unattributed |
| 12:50-12:52 | host probes | ap-tokyo eu-hetzner | >=2 min | 2 | unattributed |

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

## Was the nebius API down on October 8, 2026?

Not by our measurements. No failure of nebius was seen from two or more regions at once; 2 single-region failure(s) are not called an outage. nebius's own status page opened 1 entry that day (self-reported, listed below).
- self-reported 08:30 UTC: Metrics unavailable in Management Console for Monitoring in eu-west1 (minor)

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

## Was the iflytek API down on October 8, 2026?

Not attributably. 1 multi-region failure(s) of iflytek coincided with failures of other providers, so the cause sat above iflytek and is not blamed on it.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 17:33-17:45 | host probes | eu-hetzner sa-east | >=12 min | 2 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-10-08 · CC BY 4.0