AI API outages on August 25, 2026
UTC day · measured every 5 minutes from 4 regions · method
On August 25, 2026 (UTC) our probes attributed 5 outage(s) to 3 provider(s): Gemini API (Google): 3; Mistral API: 1; friendli API: 1. Providers’ own status pages opened 2 entries (baseten).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Gemini API (Google), Mistral API, friendli API, baseten API, 01.AI API · all AI APIs, last 72 hours
Was the Gemini API (Google) down on August 25, 2026?
Yes, measured. 3 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 07:35 UTC, at least 3 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 07:35–07:35 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | The read operation timed out |
| 10:05–10:08 | requests to gemini-flash-lite-latest | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | ≥3 min | 3 | shared with 1 other provider(s) — not attributed | The read operation timed out |
| 11:45–11:48 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥3 min | 3 | shared with 1 other provider(s) — not attributed | The read operation timed out |
| 12:10–12:13 | requests to gemini-flash-lite-latest | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | ≥3 min | 3 | provider outage | The read operation timed out |
| 13:25–13:28 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥3 min | 4 | shared with 2 other provider(s) — not attributed | The read operation timed out |
| 13:50–13:53 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), South America (São Paulo) | ≥3 min | 2 | shared with 1 other provider(s) — not attributed | The read operation timed out |
| 14:15–14:18 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥3 min | 4 | shared with 1 other provider(s) — not attributed | The read operation timed out |
| 14:40–14:40 | requests to gemini-flash-lite-latest | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | provider outage | The read operation timed out |
| 15:05–15:05 | 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 |
Current Gemini API (Google) status
Was the Mistral API down on August 25, 2026?
Yes, measured. 1 outage(s) attributed to Mistral: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 22:05 UTC, at least 5 minutes observed in total. At least once Mistral’s own host answered with an HTTP 5xx.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 22:05–22:10 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥5 min | 7 | provider outage | http 500; timeout |
Was the friendli API down on August 25, 2026?
Yes, measured. 1 outage(s) attributed to friendli: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 18:10 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 18:10–18:10 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | timeout |
Was the baseten API down on August 25, 2026?
Not by our measurements. No failure of baseten was seen from two or more regions at once; 3 single-region failure(s) are not called an outage. baseten’s own status page opened 2 entries that day (self-reported, listed below).
Self-reported on baseten’s status page, not verified by our probes:
- minor Elevated inference 500s for models in an EU cluster due to provider outage · resolved Aug 25, 13:15 UTC
- minor Elevated errors for deepseek-ai/DeepSeek-V4-Flash-0731 on Model APIs. **Dedicated Inferenc · resolved Aug 25, 16:59 UTC
Was the 01.AI API down on August 25, 2026?
Not attributably. 3 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 |
|---|---|---|---|---|---|---|
| 03:55–04:15 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥20 min | 4 | shared with 5 other provider(s) — not attributed | timeout |
| 08:45–09:25 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥40 min | 5 | shared with 5 other provider(s) — not attributed | timeout |
| 13:50–14:00 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | ≥10 min | 4 | shared with 1 other provider(s) — not attributed | timeout |
84 single-region failure(s) were also recorded that day (yi-01ai 21, iflytek 14, google 8, baichuan 7, doubao 7, sensenova 5, stepfun 4, nscale 4, baseten 3, minimax 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.
Previous: Aug 24 · Last 72 hours · Next: Aug 26
Machine-readable: incidents.json · Licence: CC BY 4.0