AI API outages on October 5, 2026
UTC day · measured every 5 minutes from 4 regions · method
On October 5, 2026 (UTC) our probes attributed 5 outage(s) to 4 provider(s): TypeSafe API: 2; Gemini API (Google): 1; doubao API: 1; iflytek API: 1. Providers’ own status pages opened 6 entries (OpenAI, Anthropic).
This page is history. Is it down right now?
Live status, updated every 30 minutes: TypeSafe API, Gemini API (Google), doubao API, iflytek API, OpenAI API, Claude API (Anthropic) · all AI APIs, last 72 hours
Was the TypeSafe API down on October 5, 2026?
Yes, measured. 2 outage(s) attributed to TypeSafe: host probes, requests to jev-1.13.0 failed from up to 4 of 4 regions at once while no other provider was failing, first at 23:10 UTC, at least 3 minutes observed in total. At least once TypeSafe’s own host answered with an HTTP 5xx. TypeSafe’s status page lists nothing that day.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 23:10–23:10 | requests to jev-1.13.0 | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | http 503 |
| 23:10–23:12 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥3 min | 4 | provider outage | http 503 |
Is the TypeSafe API down right now? Live status →
Was the Gemini API (Google) down on October 5, 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 17:30 UTC, each shorter than one 5-minute probe cycle.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 17:30–17:30 | requests to gemini-flash-lite-latest | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | <5 min | 3 | provider outage | timeout |
Is the Gemini API (Google) down right now? Live status →
Was the doubao API down on October 5, 2026?
Yes, measured. 1 outage(s) attributed to doubao: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 07:42 UTC, at least 17 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 07:42–08:00 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥17 min | 4 | provider outage | timeout |
| 08:55–09:15 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥20 min | 5 | shared with 3 other provider(s) — not attributed | timeout |
| 10:50–10:50 | host probes | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 2 other provider(s) — not attributed | timeout |
Is the doubao API down right now? Live status →
Was the iflytek API down on October 5, 2026?
Yes, measured. 1 outage(s) attributed to iflytek: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 10:18 UTC, at least 5 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 10:18–10:23 | host probes | 2 of 4: Europe (Germany), South America (São Paulo) | ≥5 min | 3 | provider outage | timeout |
| 12:00–12:20 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥20 min | 4 | shared with 3 other provider(s) — not attributed | timeout |
Is the iflytek API down right now? Live status →
Was the OpenAI API down on October 5, 2026?
Not by our measurements. No failure of OpenAI was seen from two or more regions at once. OpenAI’s own status page opened 5 entries that day (self-reported, listed below).
Self-reported on OpenAI’s status page, not verified by our probes:
- minor Elevated Work Mode errors · resolved — UTC
- minor Issues saving and editing Pages · resolved Oct 5, 13:04 UTC
- notice Admin Console Intermittently Inaccessible · resolved Oct 5, 21:07 UTC
- minor Elevated errors in ChatGPT conversations · resolved Oct 6, 00:01 UTC
- notice Elevated error rates in Codex Cloud · resolved — UTC
Is the OpenAI API down right now? Live status →
Was the Claude API (Anthropic) down on October 5, 2026?
Not by our measurements. No failure of Anthropic was seen from two or more regions at once. 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:
- major Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1 · resolved Oct 5, 13:21 UTC
Is the Claude API (Anthropic) down right now? Live status →
Was the baichuan API down on October 5, 2026?
Not attributably. 2 multi-region failure(s) of baichuan coincided with failures of other providers, so the cause sat above baichuan and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 09:10–09:23 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥13 min | 3 | shared with 2 other provider(s) — not attributed | timeout |
| 12:20–12:20 | host probes | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | [Errno 101] Network is unreachable |
Is the baichuan API down right now? Live status →
Was the writer API down on October 5, 2026?
Not attributably. 1 multi-region failure(s) of writer coincided with failures of other providers, so the cause sat above writer and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 15:55–15:55 | host probes | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | timeout |
Is the writer API down right now? Live status →
49 single-region failure(s) were also recorded that day (yi-01ai 18, google 6, iflytek 6, doubao 5, hunyuan 4, baichuan 3, writer 1, sarvam 1, friendli 1, deepseek 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.
Machine-readable: incidents.json · Licence: CC BY 4.0