# AI API outages on July 31, 2026 (UTC)

Measured every 5 minutes from 4 regions. An outage is attributed to a provider only when it failed from 2+ regions at once and no other provider failed in the same minutes.

## 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.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 10:34-10:39 | host probes | eu-hetzner sa-east | >=5 min | 3 | provider_outage |
| 11:04-11:10 | host probes | sa-east us-central | >=6 min | 2 | unattributed |
| 11:29-12:07 | host probes | ap-tokyo eu-hetzner sa-east | >=38 min | 6 | unattributed |
| 13:40-14:19 | host probes | ap-tokyo sa-east us-central | >=40 min | 6 | unattributed |
| 15:09-15:29 | host probes | ap-tokyo eu-hetzner | >=20 min | 4 | unattributed |
| 15:52-16:05 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=13 min | 5 | unattributed |
| 17:19-17:40 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=20 min | 6 | unattributed |
| 19:19-19:42 | host probes | ap-tokyo eu-hetzner us-central | >=23 min | 5 | provider_outage |
| 20:14-20:20 | host probes | eu-hetzner sa-east us-central | >=6 min | 3 | unattributed |
| 21:27-21:49 | host probes | ap-tokyo sa-east us-central | >=22 min | 5 | unattributed |
| 22:09-22:22 | host probes | ap-tokyo sa-east us-central | >=13 min | 3 | provider_outage |
| 22:47-22:50 | host probes | ap-tokyo us-central | >=3 min | 2 | provider_outage |
| 23:25-23:39 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=14 min | 4 | provider_outage |
| 23:59-00:24 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=25 min | 6 | unattributed |

Live status now: https://llmlatency.dev/provider/friendli

## 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 06:18 UTC: Degraded performance on Claude Sonnet 5 (minor)

Live status now: https://llmlatency.dev/provider/anthropic

## 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.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 14:47-14:54 | requests to gemini-flash-lite-latest | ap-tokyo sa-east | >=7 min | 2 | unattributed |
| 15:12-15:19 | requests to gemini-flash-lite-latest | ap-tokyo sa-east | >=7 min | 2 | unattributed |

Live status now: https://llmlatency.dev/provider/google

## 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 16:46 UTC: Slower than usual scale-ups for B200s (minor)
- self-reported 23:52 UTC: Elevated inference 502s for a subset of models in a single US cluster (minor)

Live status now: https://llmlatency.dev/provider/baseten

Source: https://llmlatency.dev/incidents/2026-07-31 · CC BY 4.0