AI API outages on September 18, 2026
UTC day · measured every 5 minutes from 4 regions · method
On September 18, 2026 (UTC) our probes attributed 1 outage(s) to 1 provider(s): Gemini API (Google): 1. Providers’ own status pages opened 3 entries (OpenAI).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Gemini API (Google), OpenAI API, iflytek API · all AI APIs, last 72 hours
Was the Gemini API (Google) down on September 18, 2026?
Yes, measured. 1 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 12:58 UTC, at least 7 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 12:58–13:05 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), South America (São Paulo) | ≥7 min | 2 | provider outage | timeout |
Current Gemini API (Google) status
Was the OpenAI API down on September 18, 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:
- notice Delayed support responses · resolved Sep 19, 01:10 UTC
- notice Overbilling for OpenAI-hosted containers in the Agent API · resolved Sep 19, 07:52 UTC
- notice SSO sign-in and SCIM provisioning issues · resolved Sep 18, 23:18 UTC
Was the iflytek API down on September 18, 2026?
Not attributably. 1 multi-region failure(s) of iflytek coincided with failures of other providers, so the cause sat above iflytek and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 15:20–15:25 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
27 single-region failure(s) were also recorded that day (google 7, sambanova 7, iflytek 4, stepfun 4, baichuan 2, nebius 1, sarvam 1, friendli 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 17 · Last 72 hours · Next: Sep 19
Machine-readable: incidents.json · Licence: CC BY 4.0