# AI API outages on August 3, 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 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.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 00:00-00:15 | host probes | ap-tokyo eu-hetzner sa-east | >=15 min | 3 | provider_outage |
| 00:55-00:55 | host probes | sa-east us-central | <5 min | 2 | provider_outage |
| 01:20-01:25 | host probes | ap-tokyo eu-hetzner us-central | >=5 min | 3 | provider_outage |
| 03:15-03:50 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=35 min | 7 | unattributed |
| 04:20-04:30 | host probes | ap-tokyo sa-east us-central | >=10 min | 3 | provider_outage |
| 05:05-05:05 | host probes | sa-east us-central | <5 min | 2 | provider_outage |
| 07:55-08:20 | host probes | eu-hetzner sa-east us-central | >=26 min | 4 | unattributed |
| 08:50-09:00 | host probes | eu-hetzner sa-east | >=10 min | 2 | unattributed |
| 09:20-09:35 | host probes | ap-tokyo sa-east | >=15 min | 3 | unattributed |
| 09:55-10:20 | host probes | ap-tokyo us-central | >=25 min | 5 | provider_outage |
| 11:40-11:45 | host probes | eu-hetzner us-central | >=4 min | 2 | unattributed |
| 12:05-12:15 | host probes | eu-hetzner sa-east us-central | >=10 min | 3 | provider_outage |
| 13:15-13:30 | host probes | sa-east us-central | >=15 min | 2 | provider_outage |
| 13:50-13:55 | host probes | eu-hetzner sa-east | >=5 min | 2 | unattributed |
| 14:20-14:30 | host probes | eu-hetzner sa-east | >=10 min | 2 | provider_outage |
| 16:45-17:00 | host probes | eu-hetzner sa-east | >=14 min | 2 | provider_outage |
| 17:44-18:00 | host probes | eu-hetzner us-central | >=16 min | 3 | provider_outage |
| 18:55-19:20 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=25 min | 5 | unattributed |
| 22:50-23:05 | host probes | sa-east us-central | >=15 min | 4 | provider_outage |
| 23:48-00:00 | host probes | ap-tokyo eu-hetzner | >=12 min | 3 | provider_outage |

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

## 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.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 16:10-16:10 | host probes | ap-tokyo sa-east us-central | <5 min | 3 | provider_outage |

Live status now: https://llmlatency.dev/provider/aleph-alpha

## 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 12:52 UTC: Error rates across multiple models (minor)
- self-reported 15:13 UTC: Degraded performance on Claude Sonnet 5 (minor)

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

## 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.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 12:20-12:35 | host probes | sa-east us-central | >=15 min | 3 | unattributed |
| 14:05-14:05 | host probes | ap-tokyo sa-east | <5 min | 2 | unattributed |

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

## 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.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 11:20-11:25 | host probes | sa-east us-central | >=5 min | 3 | unattributed |
| 14:05-14:05 | host probes | sa-east us-central | <5 min | 2 | unattributed |

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

## 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.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 11:35-11:40 | host probes | ap-tokyo sa-east | >=5 min | 2 | unattributed |
| 12:20-13:05 | host probes | ap-tokyo sa-east | >=45 min | 5 | unattributed |
| 16:25-16:35 | host probes | ap-tokyo sa-east | >=10 min | 2 | unattributed |

Live status now: https://llmlatency.dev/provider/yi-01ai

Source: https://llmlatency.dev/incidents/2026-08-03 · CC BY 4.0