# AI API outages on October 29, 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 29, 2026?

Yes, measured. 9 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 13:22 UTC, at least 24 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 |
| --- | --- | --- | --- | --- | --- |
| 13:02-13:05 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner us-central | >=3 min | 3 | unattributed |
| 13:22-13:25 | requests to gemini-flash-lite-latest | eu-hetzner sa-east us-central | >=3 min | 3 | provider_outage |
| 13:42-13:45 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | unattributed |
| 14:02-14:05 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east | >=3 min | 3 | unattributed |
| 14:22-14:25 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | unattributed |
| 14:42-14:45 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | unattributed |
| 15:02-15:05 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | provider_outage |
| 15:22-15:25 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | provider_outage |
| 15:42-15:45 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | provider_outage |
| 16:02-16:05 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | unattributed |
| 16:22-16:25 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | provider_outage |
| 16:42-16:45 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | provider_outage |
| 17:02-17:05 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | provider_outage |
| 17:22-17:25 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner | >=3 min | 2 | provider_outage |
| 17:42-17:45 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner us-central | >=3 min | 3 | provider_outage |
| 18:02-18:05 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=3 min | 4 | unattributed |

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

## Was the targon API down on October 29, 2026?

Yes, measured. 1 outage(s) attributed to targon: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 23:25 UTC, each shorter than one 5-minute probe cycle. At least once targon's own host answered with an HTTP 5xx.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 23:25-23:25 | host probes | sa-east us-central | <5 min | 2 | provider_outage |

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

## Was the SambaNova API down on October 29, 2026?

Not attributably. 1 multi-region failure(s) of SambaNova coincided with failures of other providers, so the cause sat above SambaNova and is not blamed on it. SambaNova's status page lists nothing that day.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 06:15-06:15 | host probes | sa-east us-central | <5 min | 2 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-10-29 · CC BY 4.0