# AI API outages on September 24, 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 September 24, 2026? Yes, measured. 7 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 05:15 UTC, at least 2 minutes observed in total. At least once Google's own host answered with an HTTP 5xx. | UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict | | --- | --- | --- | --- | --- | --- | | 05:15-05:15 | requests to gemini-flash-lite-latest | ap-tokyo sa-east us-central | <5 min | 3 | provider_outage | | 05:55-05:55 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | unattributed | | 12:00-12:00 | requests to gemini-flash-lite-latest | eu-hetzner us-central | <5 min | 2 | unattributed | | 13:00-13:00 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 13:20-13:20 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | provider_outage | | 13:40-13:40 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 14:00-14:00 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 14:20-14:20 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 14:40-14:40 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 15:00-15:00 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 15:20-15:20 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | provider_outage | | 15:40-15:40 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 16:00-16:00 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 16:20-16:20 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 16:40-16:40 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | provider_outage | | 17:00-17:00 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east | <5 min | 3 | unattributed | | 17:40-17:40 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | <5 min | 4 | unattributed | | 18:00-18:00 | requests to gemini-flash-lite-latest | eu-hetzner sa-east us-central | <5 min | 3 | provider_outage | | 18:40-18:40 | requests to gemini-flash-lite-latest | sa-east us-central | <5 min | 2 | provider_outage | | 19:00-19:00 | requests to gemini-flash-lite-latest | ap-tokyo sa-east us-central | <5 min | 3 | provider_outage | Live status now: https://llmlatency.dev/provider/google ## Was the doubao API down on September 24, 2026? Yes, measured. 2 outage(s) attributed to doubao: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 06:25 UTC, each shorter than one 5-minute probe cycle. | UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict | | --- | --- | --- | --- | --- | --- | | 06:25-06:25 | host probes | eu-hetzner us-central | <5 min | 2 | provider_outage | | 13:05-13:10 | host probes | eu-hetzner us-central | >=5 min | 3 | unattributed | | 20:20-20:20 | host probes | eu-hetzner us-central | <5 min | 2 | provider_outage | Live status now: https://llmlatency.dev/provider/doubao ## Was the OpenAI API down on September 24, 2026? Not by our measurements. No failure of OpenAI was seen from two or more regions at once; 1 single-region failure(s) are not called an outage. OpenAI's own status page opened 1 entry that day (self-reported, listed below). - self-reported 18:59 UTC: Elevated Error Rates on GPT-6 Astra Pro (none) Live status now: https://llmlatency.dev/provider/openai ## Was the SambaNova API down on September 24, 2026? Not attributably. 2 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 | | --- | --- | --- | --- | --- | --- | | 15:45-15:45 | host probes | eu-hetzner sa-east | <5 min | 2 | unattributed | | 23:25-23:40 | host probes | eu-hetzner sa-east us-central | >=15 min | 4 | unattributed | Live status now: https://llmlatency.dev/provider/sambanova ## Was the baseten API down on September 24, 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 07:23 UTC: Elevated inference 500s for a subset of models deployed in 1 US-East cluster (major) - self-reported 18:35 UTC: Intermittent 5xx for a subset of models in 1 US Central cluster (minor) Live status now: https://llmlatency.dev/provider/baseten ## Was the hunyuan API down on September 24, 2026? Not attributably. 1 multi-region failure(s) of hunyuan coincided with failures of other providers, so the cause sat above hunyuan and is not blamed on it. | UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict | | --- | --- | --- | --- | --- | --- | | 09:45-10:00 | host probes | eu-hetzner sa-east | >=15 min | 5 | unattributed | Live status now: https://llmlatency.dev/provider/hunyuan ## Was the iflytek API down on September 24, 2026? Not attributably. 1 multi-region failure(s) of iflytek coincided with failures of other providers, so the cause sat above iflytek and is not blamed on it. | UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict | | --- | --- | --- | --- | --- | --- | | 16:05-16:05 | host probes | ap-tokyo eu-hetzner us-central | <5 min | 3 | unattributed | Live status now: https://llmlatency.dev/provider/iflytek ## Was the yi-01ai API down on September 24, 2026? Not attributably. 1 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 | | --- | --- | --- | --- | --- | --- | | 11:45-12:25 | host probes | ap-tokyo sa-east | >=40 min | 5 | unattributed | Live status now: https://llmlatency.dev/provider/yi-01ai Source: https://llmlatency.dev/incidents/2026-09-24 ยท CC BY 4.0