AI API outages on August 20, 2026

UTC day · measured every 5 minutes from 4 regions · method

On August 20, 2026 (UTC) our probes attributed 2 outage(s) to 1 provider(s): OpenRouter API: 2. Providers’ own status pages opened 2 entries (Anthropic).

This page is history. Is it down right now?

Live status, updated every 30 minutes: OpenRouter API, Claude API (Anthropic) · all AI APIs, last 72 hours

Was the OpenRouter API down on August 20, 2026?

Yes, measured. 2 outage(s) attributed to OpenRouter: requests to nvidia/nemotron-3-nano-30b-a3b:free failed from up to 4 of 4 regions at once while no other provider was failing, first at 08:50 UTC, at least 8 minutes observed in total.

UTCWhat failedRegionsDurationFailed probesVerdictError
08:50–08:58requests to nvidia/nemotron-3-nano-30b-a3b:free4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥8 min4provider outageThe read operation timed out
09:15–09:15requests to nvidia/nemotron-3-nano-30b-a3b:free3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)<5 min3provider outageThe read operation timed out
09:40–09:48requests to nvidia/nemotron-3-nano-30b-a3b:free4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥8 min4shared with 1 other provider(s) — not attributedThe read operation timed out
10:05–10:05requests to nvidia/nemotron-3-nano-30b-a3b:free2 of 4: Asia (Tokyo), South America (São Paulo)<5 min2shared with 1 other provider(s) — not attributedThe read operation timed out

Is the OpenRouter API down right now? Live status →

Was the Claude API (Anthropic) down on August 20, 2026?

Not by our measurements. No failure of Anthropic was seen from two or more regions at once. Anthropic’s own status page opened 2 entries that day (self-reported, listed below).

Self-reported on Anthropic’s status page, not verified by our probes:

Is the Claude API (Anthropic) down right now? Live status →

41 single-region failure(s) were also recorded that day (yi-01ai 24, google 5, friendli 3, sensenova 3, sambanova 2, nebius 1, doubao 1, baichuan 1, iflytek 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.

· Last 72 hours ·

Machine-readable: incidents.json · Licence: CC BY 4.0