AI API outages on August 3, 2026

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

On August 3, 2026 (UTC) our probes attributed 14 outage(s) to 2 provider(s): friendli API: 13; aleph-alpha API: 1. Providers’ own status pages opened 2 entries (Anthropic).

This page is history. Is it down right now?

Live status, updated every 30 minutes: friendli API, aleph-alpha API, Claude API (Anthropic), sensenova API, stepfun API, yi-01ai API · all AI APIs, last 72 hours

Was the friendli API down on August 3, 2026?

Yes, measured. 13 outage(s) attributed to friendli: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 00:00 UTC, at least 147 minutes observed in total. At least once friendli’s own host answered with an HTTP 5xx.

UTCWhat failedRegionsDurationFailed probesVerdictError
00:00–00:15host probes3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo)≥15 min3provider outagehttp 503
00:55–00:55host probes2 of 4: South America (São Paulo), US (Central)<5 min2provider outagehttp 503
01:20–01:25host probes3 of 4: Asia (Tokyo), Europe (Germany), US (Central)≥5 min3provider outagehttp 503
03:15–03:50host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥35 min7shared with 4 other provider(s) — not attributedhttp 503
04:20–04:30host probes3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)≥10 min3provider outagehttp 503
05:05–05:05host probes2 of 4: South America (São Paulo), US (Central)<5 min2provider outagehttp 503
07:55–08:20host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥26 min4shared with 2 other provider(s) — not attributedhttp 503
08:50–09:00host probes2 of 4: Europe (Germany), South America (São Paulo)≥10 min2shared with 2 other provider(s) — not attributedhttp 503
09:20–09:35host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥15 min3shared with 3 other provider(s) — not attributedhttp 503
09:55–10:20host probes2 of 4: Asia (Tokyo), US (Central)≥25 min5provider outagehttp 503
11:40–11:45host probes2 of 4: Europe (Germany), US (Central)≥4 min2shared with 1 other provider(s) — not attributedhttp 503
12:05–12:15host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥10 min3provider outagehttp 503
13:15–13:30host probes2 of 4: South America (São Paulo), US (Central)≥15 min2provider outagehttp 503
13:50–13:55host probes2 of 4: Europe (Germany), South America (São Paulo)≥5 min2shared with 3 other provider(s) — not attributedhttp 503
14:20–14:30host probes2 of 4: Europe (Germany), South America (São Paulo)≥10 min2provider outagehttp 503
16:45–17:00host probes2 of 4: Europe (Germany), South America (São Paulo)≥14 min2provider outagehttp 503
17:44–18:00host probes2 of 4: Europe (Germany), US (Central)≥16 min3provider outagehttp 503
18:55–19:20host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥25 min5shared with 2 other provider(s) — not attributedhttp 503
22:50–23:05host probes2 of 4: South America (São Paulo), US (Central)≥15 min4provider outagehttp 503
23:48–00:00host probes2 of 4: Asia (Tokyo), Europe (Germany)≥12 min3provider outagehttp 503

Is the friendli API down right now? Live status →

Was the aleph-alpha API down on August 3, 2026?

Yes, measured. 1 outage(s) attributed to aleph-alpha: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 16:10 UTC, each shorter than one 5-minute probe cycle. At least once aleph-alpha’s own host answered with an HTTP 5xx.

UTCWhat failedRegionsDurationFailed probesVerdictError
16:10–16:10host probes3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)<5 min3provider outagehttp 503

Is the aleph-alpha API down right now? Live status →

Was the Claude API (Anthropic) down on August 3, 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 →

Was the sensenova API down on August 3, 2026?

Not attributably. 2 multi-region failure(s) of sensenova coincided with failures of other providers, so the cause sat above sensenova and is not blamed on it.

UTCWhat failedRegionsDurationFailed probesVerdictError
12:20–12:35host probes2 of 4: South America (São Paulo), US (Central)≥15 min3shared with 2 other provider(s) — not attributed[Errno 104] Connection reset by peer; timeout
14:05–14:05host probes2 of 4: Asia (Tokyo), South America (São Paulo)<5 min2shared with 2 other provider(s) — not attributedtimeout

Is the sensenova API down right now? Live status →

Was the stepfun API down on August 3, 2026?

Not attributably. 2 multi-region failure(s) of stepfun coincided with failures of other providers, so the cause sat above stepfun and is not blamed on it.

UTCWhat failedRegionsDurationFailed probesVerdictError
11:20–11:25host probes2 of 4: South America (São Paulo), US (Central)≥5 min3shared with 2 other provider(s) — not attributed[Errno 101] Network is unreachable; timeout
14:05–14:05host probes2 of 4: South America (São Paulo), US (Central)<5 min2shared with 2 other provider(s) — not attributedtimeout

Is the stepfun API down right now? Live status →

Was the yi-01ai API down on August 3, 2026?

Not attributably. 3 multi-region failure(s) of yi-01ai coincided with failures of other providers, so the cause sat above yi-01ai and is not blamed on it.

UTCWhat failedRegionsDurationFailed probesVerdictError
11:35–11:40host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥5 min2shared with 1 other provider(s) — not attributedtimeout
12:20–13:05host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥45 min5shared with 4 other provider(s) — not attributedtimeout
16:25–16:35host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥10 min2shared with 3 other provider(s) — not attributedtimeout

Is the yi-01ai API down right now? Live status →

77 single-region failure(s) were also recorded that day (yi-01ai 18, friendli 15, google 9, iflytek 7, sensenova 6, baichuan 6, doubao 5, stepfun 3, openai 2, featherless 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.

· Last 72 hours ·

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