AI API outages on August 21, 2026
UTC day · measured every 5 minutes from 4 regions · method
On August 21, 2026 (UTC) our probes attributed 1 outage(s) to 1 provider(s): OpenRouter API: 1.
This page is history. Is it down right now?
Live status, updated every 30 minutes: OpenRouter API, friendli API, yi-01ai API · all AI APIs, last 72 hours
Was the OpenRouter API down on August 21, 2026?
Yes, measured. 1 outage(s) attributed to OpenRouter: requests to nvidia/nemotron-3-nano-30b-a3b:free failed from up to 3 of 4 regions at once while no other provider was failing, first at 11:20 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 10:48–10:55 | requests to nvidia/nemotron-3-nano-30b-a3b:free | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥7 min | 4 | shared with 2 other provider(s) — not attributed | The read operation timed out |
| 11:20–11:20 | requests to nvidia/nemotron-3-nano-30b-a3b:free | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | The read operation timed out |
Is the OpenRouter API down right now? Live status →
Was the friendli API down on August 21, 2026?
Not attributably. 2 multi-region failure(s) of friendli coincided with failures of other providers, so the cause sat above friendli and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 04:45–05:35 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥50 min | 27 | shared with 1 other provider(s) — not attributed | timeout |
| 06:00–06:00 | 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 |
Is the friendli API down right now? Live status →
Was the yi-01ai API down on August 21, 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 |
|---|---|---|---|---|---|---|
| 07:20–07:43 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | ≥23 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
Is the yi-01ai API down right now? Live status →
48 single-region failure(s) were also recorded that day (yi-01ai 23, google 7, sambanova 5, friendli 3, openrouter 3, cohere 1, deepseek 1, doubao 1, nebius 1, stepfun 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.
← Aug 20 · Last 72 hours · Aug 22 →
Machine-readable: incidents.json · Licence: CC BY 4.0