AI API outages on August 2, 2026
UTC day · measured every 5 minutes from 4 regions · method
On August 2, 2026 (UTC) our probes attributed 13 outage(s) to 3 provider(s): friendli API: 11; Gemini API (Google): 1; yi-01ai API: 1.
This page is history. Is it down right now?
Live status, updated every 30 minutes: friendli API, Gemini API (Google), yi-01ai API, stepfun API · all AI APIs, last 72 hours
Was the friendli API down on August 2, 2026?
Yes, measured. 11 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 00:00 UTC, at least 124 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 |
|---|---|---|---|---|---|---|
| 00:00–00:10 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥10 min | 4 | provider outage | http 503 |
| 01:50–02:10 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥20 min | 3 | provider outage | http 503 |
| 02:40–02:45 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥5 min | 2 | provider outage | http 503 |
| 03:20–03:20 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | <5 min | 2 | provider outage | http 503 |
| 05:10–05:20 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), US (Central) | ≥10 min | 3 | shared with 2 other provider(s) — not attributed | http 503 |
| 06:20–06:30 | host probes | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | ≥10 min | 4 | shared with 2 other provider(s) — not attributed | http 503 |
| 08:35–08:35 | host probes | 2 of 4: Asia (Tokyo), US (Central) | <5 min | 2 | provider outage | http 503 |
| 08:55–09:20 | host probes | 2 of 4: Europe (Germany), US (Central) | ≥25 min | 5 | shared with 2 other provider(s) — not attributed | http 503 |
| 10:50–11:15 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥25 min | 7 | provider outage | http 503 |
| 12:30–12:55 | host probes | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | ≥24 min | 3 | shared with 2 other provider(s) — not attributed | http 503 |
| 13:30–13:50 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), US (Central) | ≥20 min | 3 | shared with 3 other provider(s) — not attributed | http 503 |
| 14:15–14:20 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), US (Central) | ≥6 min | 4 | shared with 2 other provider(s) — not attributed | http 503 |
| 15:10–15:55 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥45 min | 9 | shared with 1 other provider(s) — not attributed | http 503 |
| 16:35–16:40 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥5 min | 2 | provider outage | http 503 |
| 18:40–18:45 | host probes | 2 of 4: Europe (Germany), South America (São Paulo) | ≥5 min | 2 | shared with 1 other provider(s) — not attributed | http 503 |
| 19:00–19:00 | host probes | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | provider outage | http 503 |
| 20:10–20:15 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥5 min | 2 | provider outage | http 503 |
| 21:10–21:25 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | ≥15 min | 2 | provider outage | http 503 |
| 22:40–23:20 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥40 min | 5 | provider outage | http 503 |
| 23:35–23:40 | host probes | 2 of 4: Europe (Germany), South America (São Paulo) | ≥4 min | 2 | shared with 1 other provider(s) — not attributed | http 503 |
Is the friendli API down right now? Live status →
Was the Gemini API (Google) down on August 2, 2026?
Yes, measured. 1 outage(s) attributed to Google: requests to gemini-flash-lite-latest failed from up to 3 of 4 regions at once while no other provider was failing, first at 21:30 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 14:25–14:25 | requests to gemini-flash-lite-latest | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 2 other provider(s) — not attributed | The read operation timed out |
| 21:30–21:30 | requests to gemini-flash-lite-latest | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | The read operation timed out |
Is the Gemini API (Google) down right now? Live status →
Was the yi-01ai API down on August 2, 2026?
Yes, measured. 1 outage(s) attributed to yi-01ai: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 09:55 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 09:55–09:55 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | <5 min | 2 | provider outage | timeout |
Is the yi-01ai API down right now? Live status →
Was the stepfun API down on August 2, 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 |
|---|---|---|---|---|---|---|
| 17:55–17:55 | host probes | 2 of 4: Europe (Germany), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
Is the stepfun API down right now? Live status →
61 single-region failure(s) were also recorded that day (friendli 22, yi-01ai 20, google 6, iflytek 4, sensenova 3, doubao 2, fireworks 1, baichuan 1, inference-net 1, siliconflow 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 1 · Last 72 hours · Aug 3 →
Machine-readable: incidents.json · Licence: CC BY 4.0