AI API outages on August 4, 2026
UTC day · measured every 5 minutes from 4 regions · method
On August 4, 2026 (UTC) our probes attributed 14 outage(s) to 2 provider(s): friendli API: 12; Gemini API (Google): 2. Providers’ own status pages opened 3 entries (Anthropic).
This page is history. Is it down right now?
Live status, updated every 30 minutes: friendli API, Gemini API (Google), Claude API (Anthropic), yi-01ai API · all AI APIs, last 72 hours
Was the friendli API down on August 4, 2026?
Yes, measured. 12 outage(s) attributed to friendli: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 02:00 UTC, at least 89 minutes observed in total. At least once friendli’s own host answered with an HTTP 5xx.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 00:38–01:05 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥27 min | 5 | shared with 1 other provider(s) — not attributed | http 503 |
| 02:00–02:20 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), US (Central) | ≥20 min | 4 | provider outage | http 503 |
| 04:10–04:15 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥5 min | 3 | provider outage | http 503 |
| 04:55–05:00 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥5 min | 2 | provider outage | http 503 |
| 06:20–06:23 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | ≥3 min | 2 | shared with 1 other provider(s) — not attributed | http 503 |
| 06:58–07:25 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥27 min | 4 | shared with 3 other provider(s) — not attributed | http 503 |
| 08:35–10:00 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥85 min | 12 | shared with 5 other provider(s) — not attributed | http 503 |
| 10:48–10:55 | host probes | 2 of 4: Europe (Germany), US (Central) | ≥7 min | 2 | provider outage | http 503 |
| 12:05–12:08 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥3 min | 4 | shared with 4 other provider(s) — not attributed | http 503 |
| 14:10–14:45 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥35 min | 7 | shared with 2 other provider(s) — not attributed | http 503 |
| 16:15–16:35 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥20 min | 3 | shared with 1 other provider(s) — not attributed | http 503 |
| 17:13–17:23 | host probes | 2 of 4: Europe (Germany), US (Central) | ≥10 min | 4 | provider outage | http 503 |
| 17:40–18:00 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥20 min | 5 | shared with 2 other provider(s) — not attributed | http 503 |
| 18:20–18:27 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), US (Central) | ≥7 min | 3 | provider outage | http 503 |
| 19:05–19:13 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥9 min | 4 | provider outage | http 503 |
| 19:35–19:40 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥5 min | 2 | shared with 4 other provider(s) — not attributed | http 503 |
| 19:55–20:00 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥5 min | 2 | provider outage | http 503 |
| 20:15–20:15 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | <5 min | 2 | provider outage | http 503 |
| 20:40–20:46 | host probes | 2 of 4: Europe (Germany), US (Central) | ≥6 min | 2 | provider outage | http 503 |
| 21:11–21:40 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥29 min | 5 | shared with 2 other provider(s) — not attributed | http 503 |
| 22:20–22:25 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥5 min | 2 | shared with 1 other provider(s) — not attributed | http 503 |
| 23:00–23:05 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥5 min | 3 | provider outage | http 503 |
| 23:20–23:30 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥10 min | 3 | provider outage | http 503 |
Is the friendli API down right now? Live status →
Was the Gemini API (Google) down on August 4, 2026?
Yes, measured. 2 outage(s) attributed to Google: requests to gemini-flash-lite-latest failed from up to 4 of 4 regions at once while no other provider was failing, first at 06:40 UTC, at least 8 minutes observed in total. At least once Google’s own host answered with an HTTP 5xx.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 05:50–05:58 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥8 min | 4 | shared with 1 other provider(s) — not attributed | http 503 |
| 06:15–06:23 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥8 min | 4 | shared with 1 other provider(s) — not attributed | http 503 |
| 06:40–06:48 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥8 min | 4 | provider outage | http 503 |
| 07:05–07:13 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥8 min | 4 | shared with 3 other provider(s) — not attributed | http 503 |
| 07:30–07:38 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥8 min | 4 | shared with 4 other provider(s) — not attributed | http 503 |
| 07:55–08:03 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥8 min | 4 | shared with 1 other provider(s) — not attributed | http 503 |
| 08:20–08:28 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥8 min | 4 | shared with 3 other provider(s) — not attributed | http 503 |
| 12:05–12:05 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | The read operation timed out |
| 13:20–13:28 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥8 min | 3 | shared with 2 other provider(s) — not attributed | The read operation timed out |
| 13:45–13:45 | requests to gemini-flash-lite-latest | 2 of 4: Asia (Tokyo), US (Central) | <5 min | 2 | provider outage | The read operation timed out |
| 23:45–23:45 | 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 | The read operation timed out |
Is the Gemini API (Google) down right now? Live status →
Was the Claude API (Anthropic) down on August 4, 2026?
Not by our measurements. No failure of Anthropic was seen from two or more regions at once. Anthropic’s own status page opened 3 entries that day (self-reported, listed below).
Self-reported on Anthropic’s status page, not verified by our probes:
- minor Elevated errors on Claude Sonnet 5 · resolved Aug 4, 06:55 UTC
- minor Elevated errors on Claude Sonnet 5 · resolved Aug 4, 11:52 UTC
- major Elevated errors across many models · resolved Aug 4, 21:59 UTC
Is the Claude API (Anthropic) down right now? Live status →
Was the yi-01ai API down on August 4, 2026?
Not attributably. 2 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 |
|---|---|---|---|---|---|---|
| 04:30–04:38 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | ≥8 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
| 07:40–07:45 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥5 min | 2 | shared with 3 other provider(s) — not attributed | timeout |
Is the yi-01ai API down right now? Live status →
74 single-region failure(s) were also recorded that day (yi-01ai 25, friendli 19, google 8, iflytek 5, stepfun 5, sensenova 3, doubao 3, siliconflow 2, sambanova 1, openai 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 3 · Last 72 hours · Aug 5 →
Machine-readable: incidents.json · Licence: CC BY 4.0