AI API outages on August 28, 2026
UTC day · measured every 5 minutes from 4 regions · method
On August 28, 2026 (UTC) no AI API outage could be attributed to a provider: nothing failed from two or more regions at once without other providers failing alongside. Providers’ own status pages opened 1 entry (Anthropic).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Claude API (Anthropic), stepfun API · all AI APIs, last 72 hours
Was the Claude API (Anthropic) down on August 28, 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 Code and Claude Cowork · resolved Aug 28, 20:21 UTC
Is the Claude API (Anthropic) down right now? Live status →
Was the stepfun API down on August 28, 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 |
|---|---|---|---|---|---|---|
| 07:15–07:20 | 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 stepfun API down right now? Live status →
92 single-region failure(s) were also recorded that day (yi-01ai 28, google 18, sambanova 5, iflytek 4, doubao 4, writer 3, openai 3, hyperbolic 2, qwen 2, sensenova 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.
← Aug 27 · Last 72 hours · Aug 29 →
Machine-readable: incidents.json · Licence: CC BY 4.0