AI API outages on August 17, 2026
UTC day · measured every 5 minutes from 4 regions · method
On August 17, 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 4 entries (Anthropic, baseten, nebius).
This page is history. Is it down right now?
Live status, updated every 30 minutes: Claude API (Anthropic), baseten API, nebius API · all AI APIs, last 72 hours
Was the Claude API (Anthropic) down on August 17, 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:
- minor Degraded performance for Claude Opus 5, Claude Sonnet 5 · resolved Aug 17, 15:29 UTC
Is the Claude API (Anthropic) down right now? Live status →
Was the baseten API down on August 17, 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 Aug 17, 13:35 UTC
- minor Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic · resolved Aug 17, 17:41 UTC
Is the baseten API down right now? Live status →
Was the nebius API down on August 17, 2026?
Not by our measurements. No failure of nebius was seen from two or more regions at once. nebius’s own status page opened 1 entry that day (self-reported, listed below).
Self-reported on nebius’s status page, not verified by our probes:
- minor Issues logging to the Management Console · resolved Aug 17, 13:00 UTC
Is the nebius API down right now? Live status →
39 single-region failure(s) were also recorded that day (yi-01ai 27, sambanova 2, openai 2, iflytek 2, aleph-alpha 1, deepinfra 1, friendli 1, sarvam 1, google 1, reka 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.
← Aug 16 · Last 72 hours · Aug 18 →
Machine-readable: incidents.json · Licence: CC BY 4.0