# AI API outages on September 11, 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 September 11, 2026?

Yes, measured. 6 outage(s) attributed to Google: requests to gemini-flash-lite-latest failed from up to 2 of 4 regions at once while no other provider was failing, first at 08:36 UTC, at least 14 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 |
| --- | --- | --- | --- | --- | --- |
| 08:36-08:37 | requests to gemini-flash-lite-latest | sa-east us-central | >=2 min | 2 | provider_outage |
| 10:15-10:18 | requests to gemini-flash-lite-latest | eu-hetzner sa-east | >=3 min | 2 | provider_outage |
| 12:12-12:16 | requests to gemini-flash-lite-latest | sa-east us-central | >=3 min | 2 | provider_outage |
| 12:56-12:58 | requests to gemini-flash-lite-latest | eu-hetzner sa-east | >=3 min | 2 | unattributed |
| 13:56-14:15 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east | >=20 min | 4 | unattributed |
| 14:33-14:38 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east | >=6 min | 3 | unattributed |
| 15:33-15:38 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east | >=6 min | 3 | unattributed |
| 16:12-16:13 | requests to gemini-flash-lite-latest | ap-tokyo us-central | <5 min | 2 | provider_outage |
| 16:32-16:36 | requests to gemini-flash-lite-latest | sa-east us-central | >=3 min | 2 | unattributed |
| 17:13-17:16 | requests to gemini-flash-lite-latest | ap-tokyo sa-east | >=3 min | 2 | provider_outage |
| 17:33-17:36 | requests to gemini-flash-lite-latest | ap-tokyo sa-east | >=3 min | 2 | provider_outage |

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

## Was the OpenAI API down on September 11, 2026?

Not by our measurements. No failure of OpenAI was seen from two or more regions at once. OpenAI's own status page opened 3 entries that day (self-reported, listed below).
- self-reported 07:53 UTC: Elevated errors for ChatGPT users in Europe (minor)
- self-reported 09:08 UTC: Elevated errors for GPT-5.6 Sol on the API (minor)
- self-reported 16:22 UTC: 1% of ChatGPT Work (mobile/web) turns are failing for existing threads (minor)

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

## Was the Claude API (Anthropic) down on September 11, 2026?

Not by our measurements. No failure of Anthropic was seen from two or more regions at once. Anthropic's own status page opened 1 entry that day (self-reported, listed below).
- self-reported 14:19 UTC: Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1 (major)

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

## Was the SambaNova API down on September 11, 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 |
| --- | --- | --- | --- | --- | --- |
| 01:48-01:53 | host probes | eu-hetzner sa-east | >=5 min | 3 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-09-11 · CC BY 4.0