AI API outages on July 27, 2026
UTC day · measured every 5 minutes from 4 regions · method
On July 27, 2026 (UTC) our probes attributed 3 outage(s) to 3 provider(s): SambaNova API: 1; featherless API: 1; nscale API: 1. Providers’ own status pages opened 1 entry (nebius).
This page is history. Is it down right now?
Live status, updated every 30 minutes: SambaNova API, featherless API, nscale API, nebius API, deepinfra API, sensenova API · all AI APIs, last 72 hours
Was the SambaNova API down on July 27, 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 02:51 UTC, at least 11 minutes observed in total. SambaNova’s status page lists nothing that day.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 02:51–03:02 | host probes | 2 of 4: Europe (Germany), South America (São Paulo) | ≥11 min | 3 | provider outage | timeout |
| 04:03–04:44 | host probes | 2 of 4: Europe (Germany), South America (São Paulo) | ≥41 min | 9 | shared with 1 other provider(s) — not attributed | timeout |
Was the featherless API down on July 27, 2026?
Yes, measured. 1 outage(s) attributed to featherless: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 07:25 UTC, at least 23 minutes observed in total. At least once featherless’s own host answered with an HTTP 5xx.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 07:25–07:48 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥23 min | 16 | provider outage | http 503; timeout |
Current featherless API status
Was the nscale API down on July 27, 2026?
Yes, measured. 1 outage(s) attributed to nscale: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 15:35 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 15:35–15:35 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | <5 min | 2 | provider outage | timeout |
Was the nebius API down on July 27, 2026?
Not by our measurements. No failure of nebius was seen from two or more regions at once; 2 single-region failure(s) are not called an outage. 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 Network issues · resolved Jul 27, 20:03 UTC
Was the deepinfra API down on July 27, 2026?
Not attributably. 1 multi-region failure(s) of deepinfra coincided with failures of other providers, so the cause sat above deepinfra and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 15:06–15:12 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
Was the sensenova API down on July 27, 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 |
|---|---|---|---|---|---|---|
| 05:40–05:42 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥2 min | 2 | shared with 6 other provider(s) — not attributed | timeout |
Was the stepfun API down on July 27, 2026?
Not attributably. 1 multi-region failure(s) of stepfun coincided with failures of other providers, so the cause sat above stepfun and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 13:50–14:06 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥16 min | 3 | shared with 3 other provider(s) — not attributed | timeout |
Was the 01.AI API down on July 27, 2026?
Not attributably. 1 multi-region failure(s) of 01.AI coincided with failures of other providers, so the cause sat above 01.AI and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 05:57–06:08 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥10 min | 3 | shared with 5 other provider(s) — not attributed | timeout |
50 single-region failure(s) were also recorded that day (iflytek 9, google 6, sambanova 6, yi-01ai 4, baichuan 4, doubao 3, sensenova 3, stepfun 3, nebius 2, openai 2). 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: Jul 26 · Last 72 hours · Next: Jul 28
Machine-readable: incidents.json · Licence: CC BY 4.0