AI API outages on August 1, 2026

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

On August 1, 2026 (UTC) our probes attributed 8 outage(s) to 1 provider(s): friendli API: 8. Providers’ own status pages opened 1 entry (baseten).

This page is history. Is it down right now?

Live status, updated every 30 minutes: friendli API, baseten API, minimax API, sensenova API, yi-01ai API · all AI APIs, last 72 hours

Was the friendli API down on August 1, 2026?

Yes, measured. 8 outage(s) attributed to friendli: host probes failed from up to 4 of 4 regions at once while no other provider was failing, first at 04:14 UTC, at least 125 minutes observed in total. At least once friendli’s own host answered with an HTTP 5xx.

UTCWhat failedRegionsDurationFailed probesVerdictError
00:49–01:54host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥65 min12shared with 1 other provider(s) — not attributedhttp 503
04:14–04:17host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥3 min2provider outagehttp 503
05:37–06:19host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥42 min6shared with 1 other provider(s) — not attributedhttp 503
06:37–06:44host probes2 of 4: Asia (Tokyo), Europe (Germany)≥7 min2provider outagehttp 503
07:07–07:19host probes2 of 4: Asia (Tokyo), Europe (Germany)≥12 min2shared with 2 other provider(s) — not attributedhttp 503
07:34–07:39host probes2 of 4: Europe (Germany), South America (São Paulo)≥5 min2provider outagehttp 503
08:14–08:22host probes3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)≥8 min4shared with 1 other provider(s) — not attributedhttp 503
09:12–09:14host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥2 min3shared with 1 other provider(s) — not attributedhttp 503
10:35–11:10host probes3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)≥35 min5shared with 3 other provider(s) — not attributedhttp 503
11:40–11:55host probes2 of 4: Europe (Germany), South America (São Paulo)≥15 min2shared with 1 other provider(s) — not attributedhttp 503
12:15–12:55host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥40 min7shared with 1 other provider(s) — not attributedhttp 503
13:50–14:20host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥30 min5shared with 2 other provider(s) — not attributedhttp 503
14:35–15:25host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥50 min7shared with 2 other provider(s) — not attributedhttp 503
16:10–16:20host probes2 of 4: Asia (Tokyo), US (Central)≥10 min3shared with 1 other provider(s) — not attributedhttp 503
16:45–17:50host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥64 min9shared with 4 other provider(s) — not attributedhttp 503
18:45–19:05host probes3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)≥20 min4provider outagehttp 503
19:40–20:30host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥50 min10provider outagehttp 503
22:05–22:15host probes2 of 4: Asia (Tokyo), US (Central)≥10 min2provider outagehttp 503
22:50–23:00host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥10 min2provider outagehttp 503
23:20–23:40host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥20 min8provider outagehttp 503

Is the friendli API down right now? Live status →

Was the baseten API down on August 1, 2026?

Not by our measurements. No failure of baseten was seen from two or more regions at once. baseten’s own status page opened 1 entry that day (self-reported, listed below).

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

Is the baseten API down right now? Live status →

Was the minimax API down on August 1, 2026?

Not attributably. 1 multi-region failure(s) of minimax coincided with failures of other providers, so the cause sat above minimax and is not blamed on it.

UTCWhat failedRegionsDurationFailed probesVerdictError
16:50–16:50host probes2 of 4: Asia (Tokyo), Europe (Germany)<5 min2shared with 3 other provider(s) — not attributedtimeout

Is the minimax API down right now? Live status →

Was the sensenova API down on August 1, 2026?

Not attributably. 1 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
07:07–07:19host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥12 min2shared with 2 other provider(s) — not attributedtimeout

Is the sensenova API down right now? Live status →

Was the yi-01ai API down on August 1, 2026?

Not attributably. 2 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
10:45–11:05host probes2 of 4: Asia (Tokyo), South America (São Paulo)≥20 min4shared with 3 other provider(s) — not attributedtimeout
14:55–15:00host probes2 of 4: Asia (Tokyo), Europe (Germany)≥5 min2shared with 1 other provider(s) — not attributedtimeout

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

53 single-region failure(s) were also recorded that day (yi-01ai 19, friendli 12, google 7, iflytek 4, sambanova 3, minimax 2, sensenova 2, featherless 1, baichuan 1, stepfun 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