AI API outages on August 13, 2026

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

On August 13, 2026 (UTC) our probes attributed 3 outage(s) to 2 provider(s): OpenAI API: 2; featherless API: 1. Providers’ own status pages opened 1 entry (Anthropic).

This page is history. Is it down right now?

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

Was the OpenAI API down on August 13, 2026?

Yes, measured. 2 outage(s) attributed to OpenAI: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 20:40 UTC, at least 31 minutes observed in total. OpenAI’s status page lists nothing that day.

UTCWhat failedRegionsDurationFailed probesVerdictError
00:05–01:20host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥75 min14shared with 2 other provider(s) — not attributedtimeout
02:00–02:30host probes3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo)≥30 min4shared with 3 other provider(s) — not attributedtimeout
03:15–04:10host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥55 min9shared with 5 other provider(s) — not attributedtimeout
04:30–05:10host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥40 min10shared with 2 other provider(s) — not attributedtimeout
05:55–06:00host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥5 min3shared with 1 other provider(s) — not attributedtimeout
06:20–06:45host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥26 min5shared with 1 other provider(s) — not attributedtimeout
08:00–09:00host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥60 min11shared with 5 other provider(s) — not attributedtimeout
09:15–09:25host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥10 min6shared with 2 other provider(s) — not attributedtimeout
09:45–09:55host probes2 of 4: Asia (Tokyo), Europe (Germany)≥10 min2shared with 2 other provider(s) — not attributedtimeout
10:15–11:50host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥95 min18shared with 3 other provider(s) — not attributedtimeout
12:10–12:15host probes2 of 4: Europe (Germany), US (Central)≥5 min3shared with 1 other provider(s) — not attributedtimeout
12:30–12:35host probes3 of 4: Asia (Tokyo), Europe (Germany), US (Central)≥5 min3shared with 2 other provider(s) — not attributedtimeout
13:00–13:30host probes2 of 4: Asia (Tokyo), US (Central)≥30 min4shared with 3 other provider(s) — not attributedtimeout
13:45–14:35host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥50 min11shared with 3 other provider(s) — not attributedtimeout
14:55–16:25host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥90 min20shared with 3 other provider(s) — not attributedtimeout
16:40–17:00host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥20 min5shared with 3 other provider(s) — not attributedtimeout
17:15–18:20host probes3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo)≥64 min9shared with 3 other provider(s) — not attributedtimeout
18:55–19:30host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥35 min6shared with 1 other provider(s) — not attributedtimeout
20:10–20:20host probes2 of 4: Asia (Tokyo), Europe (Germany)≥10 min3shared with 2 other provider(s) — not attributedhttp 520; timeout
20:40–20:50host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥11 min3provider outagetimeout
21:10–21:20host probes2 of 4: Europe (Germany), South America (São Paulo)≥10 min2shared with 1 other provider(s) — not attributedtimeout
21:50–22:10host probes2 of 4: South America (São Paulo), US (Central)≥20 min4provider outagetimeout
22:25–22:50host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥26 min6shared with 1 other provider(s) — not attributedtimeout
23:55–00:10host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥15 min3shared with 2 other provider(s) — not attributedtimeout

Is the OpenAI API down right now? Live status →

Was the featherless API down on August 13, 2026?

Yes, measured. 1 outage(s) attributed to featherless: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 19:50 UTC, each shorter than one 5-minute probe cycle. At least once featherless’s own host answered with an HTTP 5xx.

UTCWhat failedRegionsDurationFailed probesVerdictError
19:50–19:50host probes2 of 4: Asia (Tokyo), Europe (Germany)<5 min2provider outagehttp 502

Is the featherless API down right now? Live status →

Was the Claude API (Anthropic) down on August 13, 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:

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

Was the SambaNova API down on August 13, 2026?

Not attributably. 1 multi-region failure(s) of SambaNova coincided with failures of other providers, so the cause sat above SambaNova and is not blamed on it. SambaNova’s status page lists nothing that day.

UTCWhat failedRegionsDurationFailed probesVerdictError
22:15–22:30host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥16 min15shared with 1 other provider(s) — not attributedtimeout

Is the SambaNova API down right now? Live status →

81 single-region failure(s) were also recorded that day (yi-01ai 29, doubao 17, iflytek 14, openai 7, friendli 4, deepinfra 2, google 2, ernie 1, featherless 1, sensenova 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