AI API outages on October 18, 2026
UTC day · measured every 5 minutes from 4 regions · method
On October 18, 2026 (UTC) our probes attributed 5 outage(s) to 2 provider(s): doubao API: 4; SambaNova 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: doubao API, SambaNova API, nebius API, yi-01ai API · all AI APIs, last 72 hours
Was the doubao API down on October 18, 2026?
Yes, measured. 4 outage(s) attributed to doubao: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 07:45 UTC, at least 57 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 07:45–07:55 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥10 min | 6 | provider outage | timeout |
| 09:13–09:38 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | ≥25 min | 3 | provider outage | timeout |
| 10:55–10:55 | host probes | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 14:05–14:26 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥21 min | 4 | provider outage | timeout |
| 15:05–15:30 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥25 min | 4 | shared with 4 other provider(s) — not attributed | timeout |
| 20:10–20:30 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥20 min | 3 | shared with 3 other provider(s) — not attributed | timeout |
| 21:35–21:36 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), US (Central) | <5 min | 3 | provider outage | timeout |
Is the doubao API down right now? Live status →
Was the SambaNova API down on October 18, 2026?
Yes, measured. 1 outage(s) attributed to SambaNova: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 13:30 UTC, each shorter than one 5-minute probe cycle. SambaNova’s status page lists nothing that day.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 13:30–13:30 | host probes | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | [SSL: UNEXPECTED_EOF_WHILE_READING] EOF occurred in violatio |
Is the SambaNova API down right now? Live status →
Was the nebius API down on October 18, 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:
- notice Partial IAM and console unavailability · resolved Oct 18, 14:07 UTC
Is the nebius API down right now? Live status →
Was the yi-01ai API down on October 18, 2026?
Not attributably. 1 multi-region failure(s) of yi-01ai coincided with failures of other providers, so the cause sat above yi-01ai and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 00:40–01:05 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥25 min | 3 | shared with 3 other provider(s) — not attributed | timeout |
Is the yi-01ai API down right now? Live status →
80 single-region failure(s) were also recorded that day (yi-01ai 20, doubao 15, iflytek 12, sensenova 10, stepfun 7, google 6, baichuan 5, nebius 2, openrouter 1, deepinfra 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.
Machine-readable: incidents.json · Licence: CC BY 4.0