AI API outages on September 29, 2026
UTC day · measured every 5 minutes from 4 regions · method
On September 29, 2026 (UTC) our probes attributed 5 outage(s) to 4 provider(s): doubao API: 2; iflytek API: 1; inference-net API: 1; kimi API: 1. Providers’ own status pages opened 6 entries (OpenAI, Anthropic, TypeSafe, baseten).
This page is history. Is it down right now?
Live status, updated every 30 minutes: doubao API, iflytek API, inference-net API, kimi API, OpenAI API, Claude API (Anthropic) · all AI APIs, last 72 hours
Was the doubao API down on September 29, 2026?
Yes, measured. 2 outage(s) attributed to doubao: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 08:30 UTC, at least 6 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 03:55–04:05 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥10 min | 3 | shared with 1 other provider(s) — not attributed | timeout |
| 08:30–08:35 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo) | ≥5 min | 4 | provider outage | timeout |
| 20:30–20:31 | host probes | 2 of 4: Europe (Germany), South America (São Paulo) | <5 min | 2 | provider outage | timeout |
Was the iflytek API down on September 29, 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 13:15 UTC, at least 6 minutes observed in total.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 08:50–09:05 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥15 min | 3 | shared with 4 other provider(s) — not attributed | timeout |
| 09:30–09:55 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥25 min | 4 | shared with 6 other provider(s) — not attributed | timeout |
| 13:15–13:21 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | ≥6 min | 2 | provider outage | timeout |
| 14:55–15:10 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥15 min | 3 | shared with 3 other provider(s) — not attributed | timeout |
Was the inference-net API down on September 29, 2026?
Yes, measured. 1 outage(s) attributed to inference-net: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 22:00 UTC, at least 11 minutes observed in total. At least once inference-net’s own host answered with an HTTP 5xx.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 22:00–22:10 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥11 min | 12 | provider outage | http 500 |
Current inference-net API status
Was the kimi API down on September 29, 2026?
Yes, measured. 1 outage(s) attributed to kimi: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 23:20 UTC, at least 36 minutes observed in total. At least once kimi’s own host answered with an HTTP 5xx.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 23:20–23:55 | host probes | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥36 min | 32 | provider outage | http 521 |
Was the OpenAI API down on September 29, 2026?
Not by our measurements. No failure of OpenAI was seen from two or more regions at once; 1 single-region failure(s) are not called an outage. OpenAI’s own status page opened 2 entries that day (self-reported, listed below).
Self-reported on OpenAI’s status page, not verified by our probes:
- notice Support available via email · resolved Sep 29, 23:18 UTC
- minor Elevated errors across ChatGPT, Codex, and the API including the Agents API · resolved Sep 29, 23:14 UTC
Was the Claude API (Anthropic) down on September 29, 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 on claude.ai, Claude Code, Claude Cowork and the Claude API · resolved Sep 29, 16:27 UTC
Current Claude API (Anthropic) status
Was the TypeSafe API down on September 29, 2026?
Not by our measurements. No failure of TypeSafe was seen from two or more regions at once; 1 single-region failure(s) are not called an outage. TypeSafe’s own status page opened 1 entry that day (self-reported, listed below).
Self-reported on TypeSafe’s status page, not verified by our probes:
- notice Routine operational maintenance · resolved Sep 29, 15:32 UTC
Was the Gemini API (Google) down on September 29, 2026?
Not attributably. 2 multi-region failure(s) of Google coincided with failures of other providers, so the cause sat above Google and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 12:35–12:45 | requests to gemini-flash-lite-latest | 4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central) | ≥9 min | 4 | shared with 1 other provider(s) — not attributed | timeout |
| 14:16–14:25 | requests to gemini-flash-lite-latest | 2 of 4: Europe (Germany), US (Central) | ≥9 min | 2 | shared with 2 other provider(s) — not attributed | timeout |
Current Gemini API (Google) status
Was the baseten API down on September 29, 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 Metrics degradation in UI and API. **Inference not affected** · resolved Sep 29, 01:28 UTC
- major Elevated 500s in Single us-central Region · resolved Sep 29, 19:57 UTC
Was the baichuan API down on September 29, 2026?
Not attributably. 6 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 |
|---|---|---|---|---|---|---|
| 05:55–05:56 | host probes | 2 of 4: Asia (Tokyo), Europe (Germany) | <5 min | 2 | shared with 2 other provider(s) — not attributed | [Errno 101] Network is unreachable; timeout |
| 07:20–07:45 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥25 min | 3 | shared with 2 other provider(s) — not attributed | [Errno 101] Network is unreachable; timeout |
| 08:50–08:55 | host probes | 2 of 4: Asia (Tokyo), South America (São Paulo) | ≥5 min | 2 | shared with 4 other provider(s) — not attributed | [Errno 101] Network is unreachable; timeout |
| 12:45–12:50 | host probes | 2 of 4: Asia (Tokyo), US (Central) | ≥5 min | 2 | shared with 1 other provider(s) — not attributed | [Errno 101] Network is unreachable; timeout |
| 14:00–14:10 | host probes | 3 of 4: Asia (Tokyo), South America (São Paulo), US (Central) | ≥10 min | 3 | shared with 5 other provider(s) — not attributed | [Errno 101] Network is unreachable; timeout |
| 15:25–15:55 | host probes | 3 of 4: Asia (Tokyo), Europe (Germany), US (Central) | ≥30 min | 6 | shared with 2 other provider(s) — not attributed | [Errno 101] Network is unreachable; timeout |
Was the sarvam API down on September 29, 2026?
Not attributably. 1 multi-region failure(s) of sarvam coincided with failures of other providers, so the cause sat above sarvam and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 18:00–18:00 | host probes | 2 of 4: South America (São Paulo), US (Central) | <5 min | 2 | shared with 1 other provider(s) — not attributed | http 502; timeout |
Was the sensenova API down on September 29, 2026?
Not attributably. 1 multi-region failure(s) of sensenova coincided with failures of other providers, so the cause sat above sensenova and is not blamed on it.
| UTC | What failed | Regions | Duration | Failed probes | Verdict | Error |
|---|---|---|---|---|---|---|
| 09:25–09:30 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥5 min | 2 | shared with 4 other provider(s) — not attributed | timeout |
Was the stepfun API down on September 29, 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 |
|---|---|---|---|---|---|---|
| 06:00–06:10 | host probes | 2 of 4: South America (São Paulo), US (Central) | ≥10 min | 3 | shared with 2 other provider(s) — not attributed | timeout |
81 single-region failure(s) were also recorded that day (baichuan 20, iflytek 15, doubao 10, sensenova 9, google 7, aleph-alpha 4, nebius 3, stepfun 3, cerebras 1, perplexity 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: Sep 28 · Last 72 hours · Next: Sep 30
Machine-readable: incidents.json · Licence: CC BY 4.0