AI API outages on July 31, 2026

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

On July 31, 2026 (UTC) our probes attributed 5 outage(s) to 1 provider(s): friendli API: 5. Providers’ own status pages opened 3 entries (Anthropic, baseten).

This page is history. Is it down right now?

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

Was the friendli API down on July 31, 2026?

Yes, measured. 5 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 10:34 UTC, at least 58 minutes observed in total. At least once friendli’s own host answered with an HTTP 5xx.

UTCWhat failedRegionsDurationFailed probesVerdictError
10:34–10:39host probes2 of 4: Europe (Germany), South America (São Paulo)≥5 min3provider outagehttp 503
11:04–11:10host probes2 of 4: South America (São Paulo), US (Central)≥6 min2shared with 1 other provider(s) — not attributedhttp 503
11:29–12:07host probes3 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo)≥38 min6shared with 1 other provider(s) — not attributedhttp 503
13:40–14:19host probes3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)≥40 min6shared with 1 other provider(s) — not attributedhttp 503
15:09–15:29host probes2 of 4: Asia (Tokyo), Europe (Germany)≥20 min4shared with 1 other provider(s) — not attributedhttp 503
15:52–16:05host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥13 min5shared with 2 other provider(s) — not attributedhttp 503
17:19–17:40host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥20 min6shared with 3 other provider(s) — not attributedhttp 503
19:19–19:42host probes3 of 4: Asia (Tokyo), Europe (Germany), US (Central)≥23 min5provider outagehttp 503
20:14–20:20host probes3 of 4: Europe (Germany), South America (São Paulo), US (Central)≥6 min3shared with 1 other provider(s) — not attributedhttp 503
21:27–21:49host probes3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)≥22 min5shared with 1 other provider(s) — not attributedhttp 503
22:09–22:22host probes3 of 4: Asia (Tokyo), South America (São Paulo), US (Central)≥13 min3provider outagehttp 503
22:47–22:50host probes2 of 4: Asia (Tokyo), US (Central)≥3 min2provider outagehttp 503
23:25–23:39host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥14 min4provider outagehttp 503
23:59–00:24host probes4 of 4: Asia (Tokyo), Europe (Germany), South America (São Paulo), US (Central)≥25 min6shared with 1 other provider(s) — not attributedhttp 503

Is the friendli API down right now? Live status →

Was the Claude API (Anthropic) down on July 31, 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 Gemini API (Google) down on July 31, 2026?

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

UTCWhat failedRegionsDurationFailed probesVerdictError
14:47–14:54requests to gemini-flash-lite-latest2 of 4: Asia (Tokyo), South America (São Paulo)≥7 min2shared with 1 other provider(s) — not attributedThe read operation timed out
15:12–15:19requests to gemini-flash-lite-latest2 of 4: Asia (Tokyo), South America (São Paulo)≥7 min2shared with 1 other provider(s) — not attributedThe read operation timed out

Is the Gemini API (Google) down right now? Live status →

Was the baseten API down on July 31, 2026?

Not by our measurements. No failure of baseten was seen from two or more regions at once. baseten’s own status page opened 2 entries 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 →

49 single-region failure(s) were also recorded that day (yi-01ai 14, google 11, friendli 11, stepfun 2, novita 1, writer 1, sensenova 1, aleph-alpha 1, glm 1, doubao 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