# AI API outages on September 3, 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 3, 2026?

Yes, measured. 3 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 42 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 |
| --- | --- | --- | --- | --- | --- |
| 08:00-08:13 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner us-central | >=13 min | 3 | unattributed |
| 13:10-13:35 | requests to gemini-flash-lite-latest | sa-east us-central | >=25 min | 3 | unattributed |
| 14:25-14:40 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east | >=15 min | 3 | provider_outage |
| 15:15-15:55 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=40 min | 6 | unattributed |
| 16:15-16:35 | requests to gemini-flash-lite-latest | eu-hetzner sa-east us-central | >=21 min | 5 | provider_outage |
| 17:10-17:15 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner | >=6 min | 2 | provider_outage |

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

## Was the SambaNova API down on September 3, 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 00:48 UTC, at least 2 minutes observed in total. SambaNova's status page lists nothing that day.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 00:48-00:50 | host probes | eu-hetzner sa-east | >=2 min | 2 | provider_outage |

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

## Was the Claude API (Anthropic) down on September 3, 2026?

Not by our measurements. No failure of Anthropic was seen from two or more regions at once. Anthropic's own status page opened 2 entries that day (self-reported, listed below).
- self-reported 12:37 UTC: Elevated errors for Claude Sonnet 5 (major)
- self-reported 13:26 UTC: Elevated errors for multiple models (major)

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

## Was the friendli API down on September 3, 2026?

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

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 17:55-18:05 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=11 min | 5 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-09-03 · CC BY 4.0