AI API outages on July 24, 2026

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

On July 24, 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.

This page is history. Is it down right now?

Live status, updated every 30 minutes: Together AI API, novita API · all AI APIs, last 72 hours

Was the Together AI API down on July 24, 2026?

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

UTCWhat failedRegionsDurationFailed probesVerdictError
11:00–11:06host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥6 min8shared with 2 other provider(s) — not attributedtimeout

Is the Together AI API down right now? Live status →

Was the novita API down on July 24, 2026?

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

UTCWhat failedRegionsDurationFailed probesVerdictError
11:00–11:06host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥6 min9shared with 2 other provider(s) — not attributedtimeout

Is the novita API down right now? Live status →

14 single-region failure(s) were also recorded that day (sambanova 4, sensenova 3, google 1, stepfun 1, doubao 1, featherless 1, replicate 1, yi-01ai 1, baichuan 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