AI API outages on September 15, 2026
UTC day · measured every 5 minutes from 4 regions · method
On September 15, 2026 (UTC) no AI API outage could be attributed to a provider: nothing failed from two or more regions at once without other providers failing alongside. Providers’ own status pages opened 5 entries (OpenAI, Anthropic, baseten).
This page is history. Is it down right now?
Live status, updated every 30 minutes: OpenAI API, Claude API (Anthropic), Gemini API (Google), SambaNova API, baseten API, reka API · all AI APIs, last 72 hours
Was the OpenAI API down on September 15, 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 Elevated errors from GPT-5.6 and GPT-5.6 Instant on paid plans · resolved Sep 15, 07:53 UTC
- minor Ads Manager login issues · resolved Sep 15, 16:54 UTC
- major Elevated errors with gpt-image-2.5-flare · resolved Sep 16, 00:30 UTC
Was the Claude API (Anthropic) down on September 15, 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 on Anthropic’s status page, not verified by our probes:
- major Intermittent error spikes for Claude Mythos 5.1 and Claude Fable 5.1 · resolved Sep 15, 11:14 UTC
Current Claude API (Anthropic) status
Was the Gemini API (Google) down on September 15, 2026?
Not attributably. 6 multi-region failure(s) of Google coincided with failures of other providers, so the cause sat above Google and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 13:00–13:15 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), South America (São Paulo) | ≥15 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 13:55–13:55 | 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 |
| 14:55–15:00 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), South America (São Paulo) | ≥5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 15:15–15:15 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), South America (São Paulo) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 17:55–17:55 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 19:55–19:55 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | shared with 2 other provider(s) — not attributed | http 503 |
Current Gemini API (Google) status
Was the SambaNova API down on September 15, 2026?
Not attributably. 1 multi-region failure(s) of SambaNova coincided with failures of other providers, so the cause sat above SambaNova and is not blamed on it. SambaNova’s status page lists nothing that day.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 07:00–00:15 | host probes | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | ≥1035 min | 225 | shared with 6 other provider(s) — not attributed | timeout |
Was the baseten API down on September 15, 2026?
Not by our measurements. No failure of baseten was seen from two or more regions at once. baseten’s own status page opened 1 entry that day (self-reported, listed below).
Self-reported on baseten’s status page, not verified by our probes:
- minor Elevated errors for models in a single India-based cluster · resolved Sep 15, 02:07 UTC
Was the reka API down on September 15, 2026?
Not attributably. 2 multi-region failure(s) of reka coincided with failures of other providers, so the cause sat above reka and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 08:15–08:15 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | <5 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
| 11:10–11:10 | host probes | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
17 single-region failure(s) were also recorded that day (google 11, hunyuan 2, novita 1, openrouter 1, deepseek 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 14 · Last 72 hours · Next: Sep 16
Machine-readable: incidents.json · Licence: CC BY 4.0