# AI API outages on October 16, 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 16, 2026?

Yes, measured. 8 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 07:30 UTC, at least 40 minutes observed in total. At least once Google's own host answered with an HTTP 5xx.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 07:30-07:30 | requests to gemini-flash-lite-latest | ap-tokyo sa-east | <5 min | 2 | provider_outage |
| 09:02-09:22 | requests to gemini-flash-lite-latest | eu-hetzner sa-east | >=20 min | 3 | unattributed |
| 09:43-09:50 | requests to gemini-flash-lite-latest | eu-hetzner sa-east | >=7 min | 2 | provider_outage |
| 12:10-12:10 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | unattributed |
| 12:50-12:50 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | unattributed |
| 13:10-13:43 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=33 min | 5 | unattributed |
| 14:30-14:30 | requests to gemini-flash-lite-latest | ap-tokyo us-central | <5 min | 2 | unattributed |
| 14:50-14:50 | requests to gemini-flash-lite-latest | ap-tokyo us-central | <5 min | 2 | unattributed |
| 15:10-15:30 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=20 min | 6 | provider_outage |
| 16:10-16:30 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=20 min | 5 | unattributed |
| 16:50-16:50 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | provider_outage |
| 17:10-17:10 | requests to gemini-flash-lite-latest | ap-tokyo sa-east us-central | <5 min | 3 | provider_outage |
| 17:50-17:50 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | provider_outage |
| 18:10-18:10 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | unattributed |
| 18:30-18:43 | requests to gemini-flash-lite-latest | eu-hetzner sa-east us-central | >=13 min | 3 | unattributed |
| 19:10-19:10 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | provider_outage |
| 20:10-20:22 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner | >=13 min | 2 | provider_outage |

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

## Was the doubao API down on October 16, 2026?

Yes, measured. 1 outage(s) attributed to doubao: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 03:00 UTC, at least 18 minutes observed in total.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 02:05-02:08 | host probes | ap-tokyo eu-hetzner | >=3 min | 2 | unattributed |
| 03:00-03:18 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=18 min | 6 | provider_outage |

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

## Was the yi-01ai API down on October 16, 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 01:05 UTC, at least 5 minutes observed in total.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 01:05-01:10 | host probes | ap-tokyo sa-east | >=5 min | 2 | provider_outage |

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

## Was the nebius API down on October 16, 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 13:02 UTC: CLI login issues (major)

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

## Was the glm API down on October 16, 2026?

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

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 12:43-12:52 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=10 min | 5 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-10-16 · CC BY 4.0