# AI API outages on October 12, 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 SambaNova API down on October 12, 2026?

Yes, measured. 3 outage(s) attributed to SambaNova: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 01:01 UTC, at least 16 minutes observed in total. SambaNova's status page lists nothing that day.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 00:30-00:45 | host probes | sa-east us-central | >=15 min | 5 | unattributed |
| 01:01-01:10 | host probes | eu-hetzner sa-east us-central | >=9 min | 4 | provider_outage |
| 02:20-02:21 | host probes | eu-hetzner sa-east us-central | <5 min | 3 | provider_outage |
| 03:45-03:51 | host probes | eu-hetzner sa-east us-central | >=6 min | 5 | provider_outage |

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

## Was the Gemini API (Google) down on October 12, 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 07:00 UTC, at least 1 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 |
| --- | --- | --- | --- | --- | --- |
| 07:00-07:01 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=1 min | 4 | provider_outage |

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

## Was the yi-01ai API down on October 12, 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 13:26 UTC, at least 4 minutes observed in total.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 12:50-13:05 | host probes | ap-tokyo us-central | >=15 min | 3 | unattributed |
| 13:26-13:30 | host probes | ap-tokyo eu-hetzner | >=4 min | 2 | provider_outage |

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

## Was the Groq API down on October 12, 2026?

Not by our measurements. No failure of Groq was seen from two or more regions at once; 1 single-region failure(s) are not called an outage. Groq's own status page opened 2 entries that day (self-reported, listed below).
- self-reported 03:37 UTC: GroqCloud Console Errors Affecting Multiple Regions (minor)
- self-reported 18:17 UTC: Model Performance or Availability Issue (major)

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

## Was the doubao API down on October 12, 2026?

Not attributably. 1 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 |
| --- | --- | --- | --- | --- | --- |
| 13:55-13:55 | host probes | ap-tokyo sa-east | <5 min | 2 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-10-12 · CC BY 4.0