# AI API outages on August 5, 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 5, 2026? Yes, measured. 6 outage(s) attributed to friendli: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 01:55 UTC, at least 16 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 | | --- | --- | --- | --- | --- | --- | | 00:40-00:50 | host probes | ap-tokyo us-central | >=10 min | 2 | unattributed | | 01:10-01:20 | host probes | ap-tokyo eu-hetzner sa-east | >=10 min | 3 | unattributed | | 01:55-01:55 | host probes | ap-tokyo sa-east | <5 min | 2 | provider_outage | | 03:05-03:25 | host probes | eu-hetzner us-central | >=20 min | 4 | unattributed | | 05:40-05:50 | host probes | sa-east us-central | >=10 min | 3 | provider_outage | | 06:35-06:35 | host probes | sa-east us-central | <5 min | 2 | provider_outage | | 07:10-07:20 | host probes | eu-hetzner sa-east | >=10 min | 2 | unattributed | | 07:40-07:40 | host probes | eu-hetzner us-central | <5 min | 2 | provider_outage | | 10:00-10:35 | host probes | eu-hetzner sa-east us-central | >=35 min | 7 | unattributed | | 11:15-11:15 | host probes | eu-hetzner sa-east | <5 min | 2 | provider_outage | | 12:35-12:40 | host probes | eu-hetzner us-central | >=5 min | 3 | unattributed | | 13:15-13:20 | host probes | eu-hetzner us-central | >=5 min | 2 | unattributed | | 14:25-14:35 | host probes | sa-east us-central | >=10 min | 2 | unattributed | | 16:50-17:05 | host probes | sa-east us-central | >=15 min | 3 | unattributed | | 17:30-17:35 | host probes | ap-tokyo sa-east | >=5 min | 2 | unattributed | | 17:50-18:10 | host probes | ap-tokyo sa-east | >=20 min | 3 | unattributed | | 18:30-18:55 | host probes | ap-tokyo sa-east us-central | >=25 min | 4 | unattributed | | 19:15-19:15 | host probes | eu-hetzner us-central | <5 min | 2 | unattributed | | 19:40-19:45 | host probes | sa-east us-central | >=5 min | 2 | unattributed | | 20:40-20:45 | host probes | sa-east us-central | >=5 min | 3 | provider_outage | Live status now: https://llmlatency.dev/provider/friendli ## Was the Gemini API (Google) down on August 5, 2026? Yes, measured. 1 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 11:20 UTC, at least 4 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 | | --- | --- | --- | --- | --- | --- | | 11:20-11:25 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=4 min | 4 | provider_outage | | 12:10-12:15 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | unattributed | | 13:50-13:55 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 4 | unattributed | | 14:15-14:20 | requests to gemini-flash-lite-latest | ap-tokyo eu-hetzner sa-east | >=5 min | 3 | unattributed | Live status now: https://llmlatency.dev/provider/google ## Was the OpenAI API down on August 5, 2026? Yes, measured. 1 outage(s) attributed to OpenAI: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 23:00 UTC, at least 20 minutes observed in total. OpenAI's status page lists nothing that day. | UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict | | --- | --- | --- | --- | --- | --- | | 23:00-23:20 | host probes | eu-hetzner us-central | >=20 min | 3 | provider_outage | | 23:50-00:00 | host probes | ap-tokyo us-central | >=10 min | 3 | unattributed | Live status now: https://llmlatency.dev/provider/openai ## Was the yi-01ai API down on August 5, 2026? Yes, measured. 1 outage(s) attributed to yi-01ai: host probes failed from up to 2 of 4 regions at once while no other provider was failing, first at 06:10 UTC, at least 10 minutes observed in total. | UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict | | --- | --- | --- | --- | --- | --- | | 06:10-06:20 | host probes | ap-tokyo eu-hetzner | >=10 min | 3 | provider_outage | Live status now: https://llmlatency.dev/provider/yi-01ai ## Was the Claude API (Anthropic) down on August 5, 2026? Not by our measurements. No failure of Anthropic was seen from two or more regions at once; 1 single-region failure(s) are not called an outage. Anthropic's own status page opened 2 entries that day (self-reported, listed below). - self-reported 07:05 UTC: Degraded performance of multiple models (minor) - self-reported 13:51 UTC: Degraded performance for Claude Opus 5 (minor) Live status now: https://llmlatency.dev/provider/anthropic ## Was the SambaNova API down on August 5, 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 | | --- | --- | --- | --- | --- | --- | | 01:10-01:30 | host probes | eu-hetzner sa-east | >=20 min | 10 | unattributed | Live status now: https://llmlatency.dev/provider/sambanova ## Was the Cohere API down on August 5, 2026? Not by our measurements. No failure of Cohere was seen from two or more regions at once. Cohere's own status page opened 1 entry that day (self-reported, listed below). - self-reported 19:36 UTC: Documentation Content Loading Issues (major) Live status now: https://llmlatency.dev/provider/cohere ## Was the nebius API down on August 5, 2026? Not by our measurements. No failure of nebius was seen from two or more regions at once; 1 single-region failure(s) are not called an outage. nebius's own status page opened 1 entry that day (self-reported, listed below). - self-reported 14:27 UTC: Creation of new VMs is broken (none) Live status now: https://llmlatency.dev/provider/nebius ## Was the aleph-alpha API down on August 5, 2026? Not attributably. 1 multi-region failure(s) of aleph-alpha coincided with failures of other providers, so the cause sat above aleph-alpha and is not blamed on it. | UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict | | --- | --- | --- | --- | --- | --- | | 15:10-15:10 | host probes | ap-tokyo sa-east us-central | <5 min | 3 | unattributed | Live status now: https://llmlatency.dev/provider/aleph-alpha ## Was the iflytek API down on August 5, 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 | | --- | --- | --- | --- | --- | --- | | 10:55-11:05 | host probes | ap-tokyo sa-east | >=10 min | 2 | unattributed | Live status now: https://llmlatency.dev/provider/iflytek ## Was the stepfun API down on August 5, 2026? Not attributably. 1 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 | | --- | --- | --- | --- | --- | --- | | 12:50-12:55 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=5 min | 7 | unattributed | Live status now: https://llmlatency.dev/provider/stepfun ## Was the targon API down on August 5, 2026? Not attributably. 1 multi-region failure(s) of targon coincided with failures of other providers, so the cause sat above targon and is not blamed on it. | UTC | What failed | Regions | Duration (lower bound) | Failed probes | Verdict | | --- | --- | --- | --- | --- | --- | | 16:00-19:35 | host probes | ap-tokyo eu-hetzner sa-east us-central | >=216 min | 176 | unattributed | Live status now: https://llmlatency.dev/provider/targon Source: https://llmlatency.dev/incidents/2026-08-05 ยท CC BY 4.0