# AI API outages on July 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 Cerebras API down on July 28, 2026?

Yes, measured. 1 outage(s) attributed to Cerebras: requests to gpt-oss-120b failed from up to 2 of 4 regions at once while no other provider was failing, first at 03:26 UTC, at least 14 minutes observed in total. Cerebras's status page lists nothing that day.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 03:26-03:40 | requests to gpt-oss-120b | eu-hetzner us-central | >=14 min | 2 | provider_outage |
| 18:15-18:40 | requests to gpt-oss-120b | ap-tokyo eu-hetzner sa-east us-central | >=25 min | 6 | unattributed |

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

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

Yes, measured. 1 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 14:25 UTC, at least 5 minutes observed in total.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 12:31-12:56 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner us-central | >=25 min | 4 | unattributed |
| 14:25-14:30 | 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

Source: https://llmlatency.dev/incidents/2026-07-28 · CC BY 4.0