AI API outages on September 1, 2026
UTC day · measured every 5 minutes from 4 regions · method
On September 1, 2026 (UTC) our probes attributed 3 outage(s) to 2 provider(s): Gemini API (Google): 2; friendli API: 1. Providers’ own status pages opened 5 entries (Anthropic, Cohere, nebius).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Gemini API (Google), friendli API, Claude API (Anthropic), Cohere API, nebius API · all AI APIs, last 72 hours
Was the Gemini API (Google) down on September 1, 2026?
Yes, measured. 2 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 14:35 UTC, at least 5 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 14:35–14:35 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), South America (São Paulo) | <5 min | 2 | provider outage | The read operation timed out |
| 17:25–17:30 | requests to gemini-flash-lite-latest | 2 of 4: South America (São Paulo), US (Central) | ≥5 min | 2 | provider outage | The read operation timed out |
Is the Gemini API (Google) down right now? Live status →
Was the friendli API down on September 1, 2026?
Yes, measured. 1 outage(s) attributed to friendli: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 23:00 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 23:00–23:00 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | timeout |
Is the friendli API down right now? Live status →
Was the Claude API (Anthropic) down on September 1, 2026?
Not by our measurements. No failure of Anthropic was seen from two or more regions at once; 1 single-region failure(s) are not called an outage. Anthropic’s own status page opened 3 entries that day (self-reported, listed below).
Self-reported on Anthropic’s status page, not verified by our probes:
- minor Degraded performance on Claude for Microsoft Office 365 · resolved Sep 1, 16:22 UTC
- minor Degraded performance on platform.claude.com and Claude for Microsoft Office 365 · resolved Sep 1, 18:07 UTC
- minor Delays in credit purchases · resolved Sep 2, 01:24 UTC
Is the Claude API (Anthropic) down right now? Live status →
Was the Cohere API down on September 1, 2026?
Not attributably. 1 multi-region failure(s) of Cohere coincided with failures of other providers, so the cause sat above Cohere and is not blamed on it. Cohere’s own status page opened 1 entry that day (self-reported, listed below).
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 14:55–14:58 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥3 min | 3 | shared with 2 other provider(s) — not attributed | http 503 |
Self-reported on Cohere’s status page, not verified by our probes:
- minor Multiple Endpoint Disruptions · resolved Sep 1, 20:03 UTC
Is the Cohere API down right now? Live status →
Was the nebius API down on September 1, 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 on nebius’s status page, not verified by our probes:
- major Connectivity issues for newly created worker nodes · resolved Sep 1, 16:26 UTC
Is the nebius API down right now? Live status →
67 single-region failure(s) were also recorded that day (yi-01ai 26, google 18, sambanova 9, iflytek 3, writer 2, openai 2, hunyuan 2, stepfun 1, anthropic 1, mistral 1). A failure seen from one region cannot be separated from a problem on that network path, so none of them is called an outage.
How is an outage told apart from a network problem?
Each provider is probed every five minutes from 4 independent regions. A failure is attributed to the provider only when it is seen from two or more regions at once and no other provider fails in the same minutes; a failure shared with other providers has a cause above all of them and is not blamed on anyone. Durations are lower bounds: we see the first and last failed probe, not the real start and end. Status-page entries are the provider’s own words, shown next to the measurement, not instead of it.
← Aug 31 · Last 72 hours · Sep 2 →
Machine-readable: incidents.json · Licence: CC BY 4.0