AI API outages on October 21, 2026
UTC day · measured every 5 minutes from 4 regions · method
On October 21, 2026 (UTC) our probes attributed 5 outage(s) to 2 provider(s): Gemini API (Google): 4; friendli API: 1. Providers’ own status pages opened 7 entries (OpenAI, Anthropic, baseten).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Gemini API (Google), friendli API, OpenAI API, Claude API (Anthropic), baseten API · all AI APIs, last 72 hours
Was the Gemini API (Google) down on October 21, 2026?
Yes, measured. 4 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 14:00 UTC, at least 1 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 08:00–08:01 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 1 other provider(s) — not attributed | timeout |
| 14:00–14:01 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | timeout |
| 14:20–14:21 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 2 other provider(s) — not attributed | timeout |
| 14:40–14:41 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | provider outage | timeout |
| 15:00–15:01 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | <5 min | 4 | shared with 1 other provider(s) — not attributed | timeout |
| 15:21–15:21 | 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 | timeout |
| 15:41–15:41 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), South America (São Paulo) | <5 min | 2 | provider outage | timeout |
| 16:01–16:01 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), South America (São Paulo) | <5 min | 2 | provider outage | timeout |
Current Gemini API (Google) status
Was the friendli API down on October 21, 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 00:55 UTC, at least 6 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 |
|---|---|---|---|---|---|---|
| 00:55–01:01 | host probes | 3 of 4: Europe (Germany), South America (São Paulo), US (Central) | ≥6 min | 6 | provider outage | http 502; http 503 |
Was the OpenAI API down on October 21, 2026?
Not by our measurements. No failure of OpenAI was seen from two or more regions at once; 2 single-region failure(s) are not called an outage. OpenAI’s own status page opened 4 entries that day (self-reported, listed below).
Self-reported on OpenAI’s status page, not verified by our probes:
- minor Degraded performance in ChatGPT, Codex, and APIs · resolved Oct 21, 03:28 UTC
- minor Elevated FedRAMP API error rates for Astra and Sol · resolved Oct 21, 19:34 UTC
- minor Elevated error rates for gpt-5.6-luna API requests · resolved Oct 21, 16:44 UTC
- major Authentication errors for some users · resolved Oct 20, 17:35 UTC
Was the Claude API (Anthropic) down on October 21, 2026?
Not by our measurements. No failure of Anthropic was seen from two or more regions at once; 2 single-region failure(s) are not called an outage. Anthropic’s own status page opened 1 entry that day (self-reported, listed below).
Self-reported on Anthropic’s status page, not verified by our probes:
- minor Degraded performance for Claude Fable 5 · resolved Oct 21, 20:29 UTC
Current Claude API (Anthropic) status
Was the baseten API down on October 21, 2026?
Not by our measurements. No failure of baseten was seen from two or more regions at once. 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 errors for image requests on multiple Model APIs · resolved Oct 21, 01:26 UTC
- minor Elevated errors on DeepSeek V4 Flash on Model APIs · resolved Oct 21, 02:28 UTC
68 single-region failure(s) were also recorded that day (yi-01ai 24, google 5, sensenova 3, sarvam 2, ai21 2, featherless 2, doubao 2, baichuan 2, iflytek 2, mistral 2). 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: Oct 20 · Last 72 hours
Machine-readable: incidents.json · Licence: CC BY 4.0