AI API outages on September 10, 2026
UTC day · measured every 5 minutes from 4 regions · method
On September 10, 2026 (UTC) our probes attributed 9 outage(s) to 1 provider(s): Gemini API (Google): 9. Providers’ own status pages opened 5 entries (OpenAI, Anthropic).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Gemini API (Google), OpenAI API, Claude API (Anthropic), sensenova API · all AI APIs, last 72 hours
Was the Gemini API (Google) down on September 10, 2026?
Yes, measured. 9 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 11:57 UTC, at least 4 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 11:57–11:58 | requests to gemini-flash-lite-latest | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | provider outage | timeout |
| 13:17–13:18 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), Europe (Germany), US (Central) | <5 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
| 13:38–13:38 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), South America (São Paulo) | <5 min | 2 | provider outage | timeout |
| 13:57–13:58 | requests to gemini-flash-lite-latest | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | timeout |
| 14:17–14:18 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | timeout |
| 14:38–14:38 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | <5 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
| 14:58–14:58 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), South America (São Paulo) | <5 min | 2 | provider outage | timeout |
| 15:17–15:18 | requests to gemini-flash-lite-latest | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | provider outage | timeout |
| 15:37–15:38 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | timeout |
| 15:58–15:58 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), Europe (Germany) | <5 min | 2 | provider outage | timeout |
| 16:17–16:18 | requests to gemini-flash-lite-latest | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 17:17–17:18 | requests to gemini-flash-lite-latest | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | provider outage | timeout |
Current Gemini API (Google) status
Was the OpenAI API down on September 10, 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 on OpenAI’s status page, not verified by our probes:
- minor Unable to open shared ChatGPT Project using direct link · resolved Sep 10, 14:28 UTC
- minor Elevated errors affecting ChatGPT Work · resolved Sep 10, 21:30 UTC
- notice Delays in customer support responses · resolved Sep 10, 21:48 UTC
Was the Claude API (Anthropic) down on September 10, 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 on Anthropic’s status page, not verified by our probes:
- major Degraded functionality for Claude Cowork on Windows · resolved Sep 14, 19:14 UTC
- minor Elevated latency on the Claude API for some users · resolved Sep 10, 23:24 UTC
Current Claude API (Anthropic) status
Was the sensenova API down on September 10, 2026?
Not attributably. 1 multi-region failure(s) of sensenova coincided with failures of other providers, so the cause sat above sensenova and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 13:12–13:13 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
31 single-region failure(s) were also recorded that day (google 18, sambanova 3, deepinfra 2, iflytek 2, doubao 1, meta-llama 1, nebius 1, writer 1, inference-net 1, aleph-alpha 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.
Previous: Sep 9 · Last 72 hours · Next: Sep 11
Machine-readable: incidents.json · Licence: CC BY 4.0