# AI API outages on October 21, 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 Gemini API (Google) down on October 21, 2026?

Yes, measured. 4 outage(s) attributed to Google: requests to gemini-flash-lite-latest failed from up to 4 of 4 regions at once while no other provider was failing, first at 14:00 UTC, at least 1 minutes observed in total.

| UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict |
| --- | --- | --- | --- | --- | --- |
| 08:00-08:01 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed |
| 14:00-14:01 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | provider_outage |
| 14:20-14:21 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed |
| 14:40-14:41 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | provider_outage |
| 15:00-15:01 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed |
| 15:21-15:21 | requests to gemini-flash-lite-latest | ap-tokyo sa-east | <5 min | 2 | unattributed |
| 15:41-15:41 | requests to gemini-flash-lite-latest | eu-hetzner sa-east | <5 min | 2 | provider_outage |
| 16:01-16:01 | requests to gemini-flash-lite-latest | eu-hetzner sa-east | <5 min | 2 | provider_outage |

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

## Was the friendli API down on October 21, 2026?

Yes, measured. 1 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 00:55 UTC, at least 6 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 |
| --- | --- | --- | --- | --- | --- |
| 00:55-01:01 | host probes | eu-hetzner sa-east us-central | >=6 min | 6 | provider_outage |

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

## Was the OpenAI API down on October 21, 2026?

Not by our measurements. No failure of OpenAI was seen from two or more regions at once; 2 single-region failure(s) are not called an outage. OpenAI's own status page opened 4 entries that day (self-reported, listed below).
- self-reported 02:26 UTC: Degraded performance in ChatGPT, Codex, and APIs (minor)
- self-reported 14:17 UTC: Elevated FedRAMP API error rates for Astra and Sol (minor)
- self-reported 15:34 UTC: Elevated error rates for gpt-5.6-luna API requests (minor)
- self-reported 22:36 UTC: Authentication errors for some users (major)

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

## Was the Claude API (Anthropic) down on October 21, 2026?

Not by our measurements. No failure of Anthropic was seen from two or more regions at once; 2 single-region failure(s) are not called an outage. Anthropic's own status page opened 1 entry that day (self-reported, listed below).
- self-reported 19:49 UTC: Degraded performance for Claude Fable 5 (minor)

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

## Was the baseten API down on October 21, 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 01:05 UTC: Elevated errors for image requests on multiple Model APIs (minor)
- self-reported 01:48 UTC: Elevated errors on DeepSeek V4 Flash on Model APIs (minor)

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

Source: https://llmlatency.dev/incidents/2026-10-21 · CC BY 4.0