# AI API outages on September 22, 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 22, 2026?

Yes, measured. 7 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 11:35 UTC, at least 31 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 |
| --- | --- | --- | --- | --- | --- |
| 11:35-11:38 | requests to gemini-flash-lite-latest | eu-hetzner sa-east | >=3 min | 2 | provider_outage |
| 12:55-12:58 | requests to gemini-flash-lite-latest | eu-hetzner sa-east | >=3 min | 2 | provider_outage |
| 13:35-13:35 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | unattributed |
| 14:13-14:18 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | provider_outage |
| 14:33-14:38 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | provider_outage |
| 14:53-14:58 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | unattributed |
| 15:13-15:18 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | provider_outage |
| 15:33-15:38 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | unattributed |
| 15:53-16:18 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=25 min | 8 | unattributed |
| 16:33-16:38 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | provider_outage |
| 16:53-16:58 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | provider_outage |
| 17:13-17:38 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=25 min | 8 | unattributed |
| 17:53-17:58 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | unattributed |
| 18:13-18:15 | requests to gemini-flash-lite-latest | ap-tokyo sa-east us-central | >=2 min | 3 | unattributed |

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

## Was the SambaNova API down on September 22, 2026?

Yes, measured. 1 outage(s) attributed to SambaNova: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 07:05 UTC, at least 3 minutes observed in total. SambaNova's status page lists nothing that day.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 07:05-07:08 | host probes | eu-hetzner sa-east | >=3 min | 2 | provider_outage |
| 07:50-07:50 | host probes | sa-east us-central | <5 min | 2 | unattributed |

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

## Was the OpenAI API down on September 22, 2026?

Not by our measurements. No failure of OpenAI was seen from two or more regions at once; 1 single-region failure(s) are not called an outage. OpenAI's own status page opened 2 entries that day (self-reported, listed below).
- self-reported 09:58 UTC: Increased error rate for Plus and Pro users. (minor)
- self-reported 15:04 UTC: Elevated Error Rates for ChatGPT Work, across Plus, Pro, Business, Enterprise and Educatio (minor)

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

## Was the Claude API (Anthropic) down on September 22, 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 00:57 UTC: Elevated errors for multiple models (major)

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

## Was the nebius API down on September 22, 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 08:55 UTC: Object storage unavailable in eu-west1 (major)

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

## Was the hunyuan API down on September 22, 2026?

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

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 12:45-12:45 | host probes | sa-east us-central | <5 min | 2 | unattributed |

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

## Was the yi-01ai API down on September 22, 2026?

Not attributably. 1 multi-region failure(s) of yi-01ai coincided with failures of other providers, so the cause sat above yi-01ai and is not blamed on it.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 06:10-06:45 | host probes | ap-tokyo eu-hetzner | >=35 min | 5 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-09-22 · CC BY 4.0