AI
53 providers, each with the state its own status page reports.
Providers
4 with open incidents
- AI21 LabsOperational
- AnthropicOperational
- AssemblyAIOperational
- BasetenOperational
- Bland AIOperational
- Bolt.newOperational
- BraintrustOperational
- CartesiaOperational
- CerebrasOperational
- CohereOperational
- ComposioOperational
- CoreWeavePartial outage1 open
- DeepgramOperational
- DeepLPartial outage1 open
- DeepSeekOperational
- E2BOperational
- ElevenLabsPartial outage1 open
- ExaOperational
- falOperational
- Fireworks AIOperational
- GitHub CopilotOperational
- GroqOperational
- HeliconeOperational
- HeyGenOperational
- Hugging FaceOperational
- Hume AIOperational
- Jina AIOperational
- Lambda CloudOperational
- LangfuseOperational
- LangSmithNot reporting
- LlamaCloudOperational
- LovableOperational
- Luma AIOperational
- ModalOperational
- OpenAIOperational
- OpenRouterOperational
- PerplexityOperational
- PoeOperational
- ReplicateDegraded1 open
- Retell AIOperational
- RunPodOperational
- RunwayOperational
- SambaNova CloudOperational
- SmitheryOperational
- Stability AIOperational
- TabnineOperational
- TavilyOperational
- Together AIMajor outage
- v0Operational
- VectaraOperational
- Voyage AIOperational
- WindsurfOperational
- xAIOperational
Recent incidents
Last 14 days, newest first, open ones on top.
- Scribe v3 Live outage
ElevenLabs says it is investigating an outage of Scribe v3 Live, with the model currently unavailable. The incident status is investigating, and no cause has been given yet.
- Elevated error rates on Free product traffic
DeepL says error rates rose from 10:04 GMT on 10 Nov 2026 across DeepL Pro and Free Translate, Write and Glossaries, affecting roughly 10% of free traffic. At 12:13 GMT it said error rates had recovered and regular service was restored.
- Changes to Cloudflare Workers are not producing Event Subscription events
- Fedramp Customers have Delayed Purges
Replicate says a bug in its purge pipeline is delaying purges for FedRAMP customers, so stale content may be served until it expires. Non-FedRAMP customers are not affected. The issue is identified, and the provider says it is still working on a fix.
- Storage Service Degradation
CoreWeave says storage services in US-EAST-13A were degraded and under investigation as of 15:13 UTC on 2026-11-05. At 16:26 UTC it said the issue is mitigated and it is monitoring the affected services.
- Object Storage Service Degradation in US-EAST-04
- Service degradation
Fireworks AI says service degradation affected deployment creation, dedicated training, and batch inference. On 2026-11-06 at 18:28 UTC, it said dedicated deployments, training, and batch inference were restored, and the incident is in monitoring.
- Jina AIDegradedDegraded performance: jina-clip-v2
Jina AI says jina-clip-v2 in us-central1 is in a degraded performance state and is under investigation. It reports P99 latency of 11851ms against a 5000ms SLO, with a 0.80% error rate.
- ReplicateDegradedNetwork Performance Issues in St. Louis, USA
Replicate says network performance issues in St. Louis, USA are affected, and the incident is in monitoring status. The provider says Cloudflare identified the issues in the St. Louis (STL) location, a fix has been implemented, and results are being monitored.
- AnthropicOperationalElevated errors on Fable 52 and Mythos 52
- ModalDegradedSome Sandboxes experiencing creation failures
- ReplicateDegradedPrediction issue on OpenAI models via Replicate
- xAIMajor outage[grok.com] Usage data slow or unavailable for some users.
- Jina AIDegradedDegraded performance: jina-clip-v2
- ReplicateDegradedAccount Analytics Filter Issue
- Jina AIDegradedDegraded performance: jina-clip-v2
- Fireworks AIDegradedService Degradation for Kimi K3
Fireworks AI says it is seeing impacted performance for Kimi K3 and is actively investigating. The incident is currently in the investigating status, with the update posted at 2026-11-10 06:01 UTC.
- Fireworks AIDegradedService Degradation for Kimi K3 US
Fireworks AI says it is investigating a service degradation affecting Kimi K3 US, with impacted performance reported as of 2026-11-10 05:50 UTC. The incident is currently in the investigating state.
- OpenAIOperationalIncorrect cost data in Costs API exports
The provider says Costs API exports published between November 6 and 9 contain incorrect cost data. It has identified the issue and is correcting the affected records, with the incident currently in a monitoring state and an update to follow once recovery is confirmed.
- DeepgramPartial outageFlux TTS high latency and websocket disconnects
- DeepgramPartial outageFlux TTS high latency and websocket disconnects
- Jina AIDegradedDegraded performance: jina-clip-v2
Jina AI says jina-clip-v2 in us-central1 is in degraded performance, with P99 latency of 11397ms against a 5000ms SLO and an error rate of 0.64%, both matching baseline. The incident is currently investigating.
- GitHub CopilotPartial outageDegraded availability for GPT-5.3 Codex and GPT-5.6 models in Copilot
GitHub Copilot says GPT-5.3 Codex, GPT-5.6 Luna, and GPT-5.6 Sol had degraded availability in Copilot products and IDE surfaces, due to an issue with an upstream model provider. The issue has been mitigated, and the provider is monitoring the service to ensure stability.
- xAIPartial outage[Third-party models] Elevated errors for OpenAI model requests
- OpenAIDegradedElevated Errors On API
- OpenAIDegradedElevated ChatGPT Conversation Errors
- ReplicateDegradedNetwork Performance Issues in Eastern North America
- ReplicateDegradedChanges made to Workers may be delayed or disrupted
Replicate says creating, editing and deleting Workers is affected, so changes to Workers may be delayed or disrupted. Workers that are already deployed are unaffected. The current status is monitoring, and the provider says it is continuing to monitor for further issues.
- ReplicateDegradedSpectrum Availability issues
- Bolt.newDegradedFeatures → Prompting Degraded