# AI API outages on August 13, 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 OpenAI API down on August 13, 2026?

Yes, measured. 2 outage(s) attributed to OpenAI: host probes failed from up to 3 of 4 regions at once while no other provider was failing, first at 20:40 UTC, at least 31 minutes observed in total. OpenAI's status page lists nothing that day.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 00:05-01:20 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=75 min | 14 | unattributed |
| 02:00-02:30 | host probes | ap-tokyo eu-hetzner sa-east | >=30 min | 4 | unattributed |
| 03:15-04:10 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=55 min | 9 | unattributed |
| 04:30-05:10 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=40 min | 10 | unattributed |
| 05:55-06:00 | host probes | ap-tokyo sa-east | >=5 min | 3 | unattributed |
| 06:20-06:45 | host probes | eu-hetzner sa-east us-central | >=26 min | 5 | unattributed |
| 08:00-09:00 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=60 min | 11 | unattributed |
| 09:15-09:25 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=10 min | 6 | unattributed |
| 09:45-09:55 | host probes | ap-tokyo eu-hetzner | >=10 min | 2 | unattributed |
| 10:15-11:50 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=95 min | 18 | unattributed |
| 12:10-12:15 | host probes | eu-hetzner us-central | >=5 min | 3 | unattributed |
| 12:30-12:35 | host probes | ap-tokyo eu-hetzner us-central | >=5 min | 3 | unattributed |
| 13:00-13:30 | host probes | ap-tokyo us-central | >=30 min | 4 | unattributed |
| 13:45-14:35 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=50 min | 11 | unattributed |
| 14:55-16:25 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=90 min | 20 | unattributed |
| 16:40-17:00 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=20 min | 5 | unattributed |
| 17:15-18:20 | host probes | ap-tokyo eu-hetzner sa-east | >=64 min | 9 | unattributed |
| 18:55-19:30 | host probes | eu-hetzner sa-east us-central | >=35 min | 6 | unattributed |
| 20:10-20:20 | host probes | ap-tokyo eu-hetzner | >=10 min | 3 | unattributed |
| 20:40-20:50 | host probes | eu-hetzner sa-east us-central | >=11 min | 3 | provider_outage |
| 21:10-21:20 | host probes | eu-hetzner sa-east | >=10 min | 2 | unattributed |
| 21:50-22:10 | host probes | sa-east us-central | >=20 min | 4 | provider_outage |
| 22:25-22:50 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=26 min | 6 | unattributed |
| 23:55-00:10 | host probes | eu-hetzner sa-east us-central | >=15 min | 3 | unattributed |

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

## Was the featherless API down on August 13, 2026?

Yes, measured. 1 outage(s) attributed to featherless: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 19:50 UTC, each shorter than one 5-minute probe cycle. At least once featherless's own host answered with an HTTP 5xx.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 19:50-19:50 | host probes | ap-tokyo eu-hetzner | <5 min | 2 | provider_outage |

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

## Was the Claude API (Anthropic) down on August 13, 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 14:33 UTC: Elevated errors for Claude Mythos 5, Claude Fable 5, and Claude Sonnet 5 (major)

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

## Was the SambaNova API down on August 13, 2026?

Not attributably. 1 multi-region failure(s) of SambaNova coincided with failures of other providers, so the cause sat above SambaNova and is not blamed on it. SambaNova's status page lists nothing that day.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 22:15-22:30 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=16 min | 15 | unattributed |

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

Source: https://llmlatency.dev/incidents/2026-08-13 · CC BY 4.0