{"providers":[{"source_name":"OpenAI Status","source_tier":1,"currentState":"open","incidents30d":27,"medianResolveMinutes":100.21666666666667,"resolveSampleSize":85,"lastIncident":{"title":"OpenAI: Delayed Costs Data in the Compliance API","publishedAt":1794586207000,"isOpen":true,"updates":[{"status":"identified","body":"We have identified an issue causing delays in publishing Organization cost data through the Costs API. API and ChatGPT usage are not affected. We are working to restore normal data freshness.","at":"2026-11-13T16:10:07.000Z"},{"status":"monitoring","body":"We’ve applied a mitigation and are monitoring the affected services to confirm recovery. Delays in cost data are still expected.","at":"2026-11-13T18:56:44.000Z"},{"status":"monitoring","body":"We are monitoring the affected services to confirm recovery. Delays in cost data are still expected.","at":"2026-11-14T05:31:20.000Z"}]}},{"source_name":"Fireworks AI Status","source_tier":1,"currentState":"resolved","incidents30d":54,"medianResolveMinutes":20.358333333333334,"resolveSampleSize":96,"lastIncident":{"title":"Fireworks AI: Service Degradation for GLM 5.3 Flash","publishedAt":1794663446000,"isOpen":false,"updates":[{"status":"investigating","body":"We are seeing impacted performance for GLM 5.3 Flash. We are actively investigating.","at":"2026-11-14T13:37:26.000Z"},{"status":"resolved","body":"We've resolved the incident and the affected service is now operational.","at":"2026-11-14T15:02:48.000Z"}]}},{"source_name":"GitHub Status","source_tier":1,"currentState":"resolved","incidents30d":34,"medianResolveMinutes":76.08092500000001,"resolveSampleSize":94,"lastIncident":{"title":"GitHub: Copilot experiencing degraded model availability for some GPT models","publishedAt":1794600831325,"isOpen":false,"updates":[{"status":"investigating","body":"We are investigating reports of degraded performance for Copilot AI Model Providers","at":"2026-11-13T20:13:51.431Z"},{"status":"investigating","body":"We are experiencing degraded availability for gpt-5.6-sol-fast, gpt-5.6-sol, gpt-6.1-terra, and gpt-6-luna in Copilot products and IDE surfaces. This is due to an issue with an upstream model provider. While we work with them to resolve the issue, we recommend choosing another model or selecting 'Auto' to continue using Copilot.","at":"2026-11-13T20:14:07.400Z"},{"status":"investigating","body":"We are in contact with the upstream provider and monitoring as they work towards resolution. For customers who are impacted we recommend choosing another model or selecting ‘Auto’ to continue using Copilot.","at":"2026-11-13T20:47:09.681Z"},{"status":"investigating","body":"The upstream provider has made mitigations and we are seeing the affected models begin to recover.","at":"2026-11-13T21:17:48.112Z"},{"status":"resolved","body":"Between 19:05 and 21:27 UTC on November 13, 2026, GitHub Copilot experienced degradation affecting GPT-6.1 Terra, GPT-5.6 Sol, and GPT-6 Luna models. Users encountered elevated error rates when using these models.The degradation was caused by an issue with an upstream model provider. GitHub engineers detected the issue through automated monitoring and coordinated with the provider. Our automated model-warning system activated in-product warnings for affected models during the incident. Service returned to normal after the provider implemented a mitigation.","at":"2026-11-13T21:38:45.908Z"}]}},{"source_name":"Anthropic Status","source_tier":1,"currentState":"resolved","incidents30d":15,"medianResolveMinutes":73.20236666666666,"resolveSampleSize":65,"lastIncident":{"title":"Anthropic: Elevated purchasing errors on claude.ai","publishedAt":1794624873309,"isOpen":false,"updates":[{"status":"investigating","body":"We are investigating elevated errors affecting purchases, plan upgrades and cancellations on claude.ai. Core functionality is not affected. We will provide an update as soon as possible.","at":"2026-11-14T02:54:33.497Z"},{"status":"monitoring","body":"Purchases on claude.ai are working normally, and delayed plan changes and payments are now being applied. Some customers who recently paid may need to wait up to an hour for their plan to update. There is no need to pay again. We are monitoring for recovery.","at":"2026-11-14T03:09:15.546Z"},{"status":"resolved","body":"The issue affecting purchases and plan changes on claude.ai has been resolved, and delayed plan changes and payments have now been applied. Impact occurred from 18:34 PT on November 13 / 02:34 UTC on November 14 to 20:03 PT on November 13 / 04:03 UTC on November 14.","at":"2026-11-14T04:23:05.193Z"}]}},{"source_name":"Baseten Status","source_tier":1,"currentState":"resolved","incidents30d":8,"medianResolveMinutes":43.275816666666664,"resolveSampleSize":57,"lastIncident":{"title":"Baseten: Elevated errors for multiple models on Model APIs","publishedAt":1794633135000,"isOpen":false,"updates":[{"status":"identified","body":"DeepSeek V4.1 Flash is fully recovered. We expect GLM 5.3 to recover in the next 10 minutes","at":"2026-11-14T06:35:15.539Z"},{"status":"monitoring","body":"GLM 5.3 has recovered and we are continuing to monitor","at":"2026-11-14T06:45:10.073Z"},{"status":"resolved","body":"This incident has been resolved.","at":"2026-11-14T06:58:20.507Z"},{"status":"investigating","body":"We are seeing elevated errors on GLM 5.3 and DeepSeek V4.1 Flash","at":"2026-11-14T07:06:51.338Z"}]}},{"source_name":"Cloudflare Status","source_tier":1,"currentState":"resolved","incidents30d":5,"medianResolveMinutes":344.35365,"resolveSampleSize":11,"lastIncident":{"title":"Cloudflare is currently having an issue with the r8.im registry used for Replicate model publishing and builds is currently restricted","publishedAt":1794581726179,"isOpen":false,"updates":[{"status":"identified","body":"The issue has been identified and a fix is being implemented.","at":"2026-11-13T14:55:26.179Z"},{"status":"monitoring","body":"A fix has been implemented and we are monitoring the results.","at":"2026-11-13T23:34:56.651Z"},{"status":"resolved","body":"This incident has been resolved.","at":"2026-11-14T00:51:29.308Z"}]}},{"source_name":"Deepgram Status","source_tier":1,"currentState":"resolved","incidents30d":5,"medianResolveMinutes":251.412475,"resolveSampleSize":52,"lastIncident":{"title":"Deepgram: Elevated errors for Flux streaming STT and Voice Age… — STT Streaming API, Voice Agent API","publishedAt":1793904128991,"isOpen":false,"updates":[{"status":"investigating","body":"We are currently investigating elevated errors for Flux streaming speech-to-text requests at our US endpoint. Voice Agent sessions configured with a Flux listen model may fail to start with a FAILED_TO_START_LISTENING error. Other models are not affected.","at":"2026-11-05T18:42:09.051Z"},{"status":"monitoring","body":"A fix has been implemented and we are monitoring the results.","at":"2026-11-05T18:51:57.709Z"},{"status":"resolved","body":"This incident has been resolved.","at":"2026-11-06T01:14:54.554Z"}]}},{"source_name":"Runway Status","source_tier":1,"currentState":"resolved","incidents30d":5,"medianResolveMinutes":97.62639166666668,"resolveSampleSize":52,"lastIncident":{"title":"Runway: Seedance video generations failing or delayed","publishedAt":1793749761134,"isOpen":false,"updates":[{"status":"investigating","body":"Our engineering team is investigating a problem affecting users. We're aware of the problem and are working towards a solution. We will provide an update soon.","at":"2026-11-03T23:49:21.187Z"},{"status":"investigating","body":"We've spotted that something has gone wrong. We're currently investigating the issue, and will provide an update soon.","at":"2026-11-03T23:55:26.299Z"},{"status":"monitoring","body":"A fix has been implemented and we are monitoring the results.","at":"2026-11-04T00:21:06.057Z"},{"status":"resolved","body":"This incident has now been resolved.","at":"2026-11-04T04:55:35.221Z"}]}},{"source_name":"Langfuse Status","source_tier":1,"currentState":"resolved","incidents30d":4,"medianResolveMinutes":65.85833333333333,"resolveSampleSize":30,"lastIncident":{"title":"Langfuse: Slow trace data retirival across API and UI in EU","publishedAt":1792568806000,"isOpen":false,"updates":[{"status":"investigating","body":"Slow traces data serving across API and UI","at":"2026-10-21T07:46:46.000Z"},{"status":"identified","body":"Slow clickhouse read replicas affecting performance across the service. Draining and replacing them.","at":"2026-10-21T08:31:54.000Z"},{"status":"resolved","body":"All replicas look healthy again","at":"2026-10-21T08:45:40.000Z"},{"status":"monitoring","body":"Looks like some timeout are still occurring. Monitoring.","at":"2026-10-21T08:56:10.000Z"},{"status":"resolved","body":"should be finally resolved","at":"2026-10-21T09:39:42.000Z"}]}},{"source_name":"E2B Status","source_tier":1,"currentState":"resolved","incidents30d":3,"medianResolveMinutes":141.18333333333334,"resolveSampleSize":19,"lastIncident":{"title":"E2B: Template builds failing on Ubuntu package installs","publishedAt":1794412932000,"isOpen":false,"updates":[{"status":"identified","body":"Some template builds are failing when they install packages with apt. Ubuntu's package servers (<https://status.canonical.com/>) are currently unreachable, so build steps that run apt-get update or apt-get install may fail. Running sandboxes and sandbox creation are not affected. If your build fails on an apt step, please retry it or wait once the upstream issue is resolved. Templates that don't install Ubuntu packages are expected to build normally. We're monitoring the issue and will post an update when builds are back to normal.","at":"2026-11-11T16:57:41.000Z"},{"status":"resolved","body":"Ubuntu’s package servers are reachable again and template builds that install packages with apt are completing normally.","at":"2026-11-11T19:12:58.000Z"}]}},{"source_name":"Pinecone Status","source_tier":1,"currentState":"resolved","incidents30d":3,"medianResolveMinutes":102.51666666666667,"resolveSampleSize":47,"lastIncident":{"title":"Pinecone: [Serverless][GCP][us-central1] Elevated errors and timeouts on read operations for some indexes","publishedAt":1794329403000,"isOpen":false,"updates":[{"status":"investigating","body":"We are currently investigating this issue.","at":"2026-11-10T17:29:15.537Z"},{"status":"monitoring","body":"A fix has been implemented and we are monitoring the results.","at":"2026-11-10T18:54:53.952Z"},{"status":"resolved","body":"This incident has been resolved.","at":"2026-11-10T19:02:06.218Z"}]}},{"source_name":"Cartesia Status","source_tier":1,"currentState":"resolved","incidents30d":3,"medianResolveMinutes":64.01666666666667,"resolveSampleSize":19,"lastIncident":{"title":"Cartesia: Elevated latency for instant voice cloning","publishedAt":1792771035000,"isOpen":false,"updates":[{"status":"identified","body":"Instant Voice Cloning latency is elevated, we are investigating.","at":"2026-10-23T15:57:15.000Z"},{"status":"monitoring","body":"We have mitigated the issue on our end and are continuing to monitor the state of our service.","at":"2026-10-23T16:26:14.000Z"},{"status":"resolved","body":"This incident has been resolved.","at":"2026-10-23T17:01:16.000Z"}]}},{"source_name":"ElevenLabs Status","source_tier":1,"currentState":"resolved","incidents30d":2,"medianResolveMinutes":135.225,"resolveSampleSize":30,"lastIncident":{"title":"ElevenLabs: Scribe v3 Live outage","publishedAt":1794359419000,"isOpen":false,"updates":[{"status":"investigating","body":"We are currently investigating an issue with Scribe v3 Live, resulting in the model being unavailable at this time.","at":"2026-11-11T01:10:19.000Z"},{"status":"monitoring","body":"We have identified and remedied the issue, Scribe v3 Live is available again. We are continuing to monitor performance. The outage occurred between 00:50AM to 01:11AM BST.","at":"2026-11-11T01:19:46.000Z"},{"status":"resolved","body":"We have verified the implemented fix has remained stable and Scribe v3 Live is fully operational since 01:11AM BST.","at":"2026-11-11T03:03:51.000Z"}]}},{"source_name":"AssemblyAI Status","source_tier":1,"currentState":"resolved","incidents30d":2,"medianResolveMinutes":76.79151666666667,"resolveSampleSize":39,"lastIncident":{"title":"AssemblyAI: Elevated errors and delays for Universal-3 Pro, Universal-3.5 Pro and… — Asynchronous API","publishedAt":1793655773189,"isOpen":false,"updates":[{"status":"identified","body":"We've identified an issue causing a significant portion of pre-recorded transcription requests using Universal-3.5 Pro and Universal-3.6 Pro to fail or take longer than usual to complete, across all regions. Streaming is not affected. We've identified the cause and are rolling back a recent change, and we're beginning to see recovery.","at":"2026-11-02T21:42:53.323Z"},{"status":"identified","body":"Error rates are decreasing as our rollback progresses, and we're continuing to work on fully resolving the issue. Some requests may still fail or take longer than usual to complete.","at":"2026-11-02T22:08:24.085Z"},{"status":"identified","body":"We've applied a fix and error rates have dropped significantly. Some pre-recorded requests using Universal-3 Pro, Universal-3.5 Pro and Universal-3.6 Pro may still take longer than usual to complete while we work through the backlog.","at":"2026-11-02T22:42:10.086Z"},{"status":"monitoring","body":"Error rates and processing times have returned to normal. We're monitoring to make sure performance remains stable.","at":"2026-11-02T22:44:51.105Z"},{"status":"resolved","body":"We have continued to see good performance after the rollback, and error rates and processing times have remained in the normal ranges. We are now marking this issue as resolved. Any requests that returned an error during this incident can be safely resubmitted.","at":"2026-11-02T22:58:44.395Z"}]}},{"source_name":"Hugging Face Status","source_tier":1,"currentState":"resolved","incidents30d":1,"medianResolveMinutes":null,"resolveSampleSize":0,"lastIncident":{"title":"Hugging Face: Degraded performance - AWS CDN (Singapore)","publishedAt":1794559560000,"isOpen":false,"updates":[]}},{"source_name":"Speechmatics Status","source_tier":1,"currentState":"resolved","incidents30d":1,"medianResolveMinutes":124.39915,"resolveSampleSize":31,"lastIncident":{"title":"Speechmatics: Degraded performance and errors for Batch transcription in US2 — Batch SaaS - US2","publishedAt":1794342871331,"isOpen":false,"updates":[{"status":"investigating","body":"We are investigating elevated error rates and slow responses on the Batch transcription API in the US2 region. Some requests to submit or retrieve jobs may fail or time out, and jobs may take longer than usual to complete.","at":"2026-11-10T20:34:31.522Z"},{"status":"monitoring","body":"A fix has been implemented and we are monitoring the results.","at":"2026-11-10T21:38:28.327Z"},{"status":"resolved","body":"This incident has been resolved.","at":"2026-11-10T22:34:39.722Z"}]}},{"source_name":"Lambda Labs Status","source_tier":1,"currentState":"resolved","incidents30d":1,"medianResolveMinutes":312.26666666666665,"resolveSampleSize":26,"lastIncident":{"title":"Lambda Labs: Service disruption in us-east-3","publishedAt":1794067697000,"isOpen":false,"updates":[{"status":"investigating","body":"Severity Level: Medium We’re currently investigating a potential issue with our On-Demand Cloud in the us-east-3 region. Users may experience connectivity issues with existing instances in us-east-3. Launching new instances in the region is currently unavailable. Our teams are actively working to identify the root cause and mitigate or resolve the issue. Thank you for your patience and understanding during this time. --- In the event you’re unsure as to whether your service is impacted by this incident, please open a support ticket. We’ll get back to you as soon as possible. <https://support.lambdalabs.com/hc/en-us/requests/new> To be automatically notified when the status of this incident changes, please click on the “Subscribe to updates” button.","at":"2026-11-07T16:08:17.000Z"},{"status":"resolved","body":"Severity Level: Medium This incident has been resolved. Between approximately 15:31 and 16:27 UTC, a fault in network equipment in the us-east-3 region disrupted some connectivity to instances in the region. Our teams found the cause and applied a fix. Service has been fully restored, and we have monitored the region since then to confirm it is stable. We’re also working on follow-up actions to prevent this from happening again. We apologize for the disruption and thank you for your patience. --- If you’re experiencing issues with your instances in us-east-3, please open a support ticket and we’ll get back to you as soon as possible. <https://support.lambdalabs.com/hc/en-us/requests/new>","at":"2026-11-07T17:26:49.000Z"}]}},{"source_name":"Cerebras Status","source_tier":1,"currentState":"resolved","incidents30d":1,"medianResolveMinutes":175.75153333333333,"resolveSampleSize":29,"lastIncident":{"title":"Cerebras: Partial Service Disruption — GPT-OSS-120B, Qwen-3.8-27b","publishedAt":1793725663713,"isOpen":false,"updates":[{"status":"monitoring","body":"Some models may be temporarily unavailable since 16:52, Nov 3rd UTC. We have identified the root cause, implemented the fix and are monitoring the situation.","at":"2026-11-03T17:07:43.770Z"},{"status":"resolved","body":"This incident has been resolved.","at":"2026-11-03T19:41:04.693Z"}]}},{"source_name":"Groq Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":89.125,"resolveSampleSize":26,"lastIncident":{"title":"Groq: Model Performance or Availability Issue","publishedAt":1791829067000,"isOpen":false,"updates":[{"status":"identified","body":"We have identified the problem affecting the minimaxai/minimax-m2.7 service. The issue was traced to hardware connectivity issues. A fix is in progress. Users may still see API failures until the fix completes.","at":"2026-10-12T18:17:47.000Z"},{"status":"resolved","body":"The issues affecting minimaxai/minimax-m2.7 have been resolved. The model is operating normally. Root cause: hardware connectivity issues. We apologize for the disruption and thank you for your patience.","at":"2026-10-12T18:36:13.000Z"}]}},{"source_name":"Perplexity Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":26.608333333333334,"resolveSampleSize":2,"lastIncident":{"title":"Perplexity: Elevated API errors and timeouts","publishedAt":1791585531000,"isOpen":false,"updates":[{"status":"investigating","body":"Users may experience errors or timeouts when making API requests. We are investigating elevated API errors and timeouts.","at":"2026-10-09T22:38:51.000Z"},{"status":"monitoring","body":"The issue causing elevated API errors and timeouts has been mitigated.","at":"2026-10-09T23:01:42.000Z"},{"status":"monitoring","body":"Correction to our previous updates: we do not believe the API was affected by this incident and it remains operational.","at":"2026-10-09T23:10:27.000Z"},{"status":"resolved","body":"The issue affecting the Website, App, and Computer has been resolved. All services are operational. The API remained operational throughout this incident.","at":"2026-10-09T23:15:40.000Z"}]}},{"source_name":"Azure Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":null,"resolveSampleSize":0,"lastIncident":{"title":"Azure OpenAI and Foundry agent Service intermittent request failures and increased latency","publishedAt":1790676000000,"isOpen":false,"updates":[]}},{"source_name":"Hume AI Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":85.73333333333333,"resolveSampleSize":13,"lastIncident":{"title":"Hume AI: TTS is down","publishedAt":1789783803000,"isOpen":false,"updates":[{"status":"investigating","body":"TTS is currently down. We have identified the issue and working on a fix.","at":"2026-09-19T02:10:03.000Z"},{"status":"investigating","body":"TTS is back up. An image was erroneously removed from our artifactory which briefly caused an outage. We have addressed the underlying issue.","at":"2026-09-19T02:15:27.000Z"},{"status":"resolved","body":"The issue has been resolved.","at":"2026-09-19T02:16:53.000Z"}]}},{"source_name":"Stability AI Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":247.71666666666667,"resolveSampleSize":1,"lastIncident":{"title":"Stability AI: Investigating elevated 500s for generation endpoints","publishedAt":1789403600000,"isOpen":false,"updates":[{"status":"investigating","body":"🚧 We are currently investigating reports of elevated 500s affecting our generation API endpoints. Our engineering team is actively working to identify the root cause. We will provide another update as soon as we have more information. Thank you for your patience.","at":"2026-09-14T16:33:21.000Z"},{"status":"identified","body":"⚠️ We have identified the cause of the issue affecting the outages in our API Platform, Brand Studio, and Stable Audio suite of products. We are working on a fix and will provide an update shortly.","at":"2026-09-14T16:52:15.000Z"},{"status":"monitoring","body":"✅ A fix has been implemented for the issue affecting API Platform, Brand Studio, and Stable Audio suite of products, and we are currently monitoring the results to ensure stability. We’ll continue to keep a close eye and provide a final update once we confirm everything is fully operational.","at":"2026-09-14T17:55:34.000Z"},{"status":"resolved","body":"🟢 This incident has been resolved. All systems are now operating normally. We apologize for any inconvenience this may have caused and thank you for your patience.","at":"2026-09-14T20:41:03.000Z"}]}},{"source_name":"Vercel Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":93.84288333333333,"resolveSampleSize":1,"lastIncident":{"title":"Vercel: Elevated error rate on Connect and Passport","publishedAt":1789062135875,"isOpen":false,"updates":[{"status":"investigating","body":"We've identified an issue where some customers may experience increased errors from Connect and Passport. We are currently investigating this issue. We will provide additional updates as they become available.","at":"2026-09-10T17:42:15.922Z"},{"status":"identified","body":"The issue has been identified and a fix is being implemented.","at":"2026-09-10T18:13:20.242Z"},{"status":"resolved","body":"Connect and Passport have fully recovered. This incident has been resolved.","at":"2026-09-10T19:16:06.440Z"}]}},{"source_name":"Cohere Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":186.6,"resolveSampleSize":18,"lastIncident":{"title":"Cohere: Multiple Endpoint Disruptions","publishedAt":1788277263000,"isOpen":false,"updates":[{"status":"investigating","body":"🔎 We are currently investigating this live incident.","at":"2026-09-01T15:41:03.000Z"},{"status":"identified","body":"🛠️ We have identified the root cause as an ongoing Google Cloud Platform (GCP) outage. Our team is actively monitoring the situation while we wait for GCP to resolve the underlying issue. ([reference](https://status.cloud.google.com/incidents/J5ia5t9p3g9Q5Wi7r8Ev \"reference\"))","at":"2026-09-01T16:21:28.000Z"},{"status":"monitoring","body":"👀 We are monitoring to make sure the incident has been fully resolved.","at":"2026-09-01T19:47:31.000Z"},{"status":"resolved","body":"🎉 The issue has been resolved and we are back to normal.","at":"2026-09-01T20:03:17.000Z"}]}},{"source_name":"Weights & Biases Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":376.06801666666667,"resolveSampleSize":31,"lastIncident":{"title":"Weights & Biases: Errors fetching media files","publishedAt":1784154902160,"isOpen":false,"updates":[{"status":"investigating","body":"We are currently experiencing elevated errors fetching media files in Weights & Biases.","at":"2026-07-15T22:35:02.352Z"},{"status":"resolved","body":"This incident has been resolved.","at":"2026-07-16T00:06:10.584Z"}]}},{"source_name":"Browserbase Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":70.75,"resolveSampleSize":13,"lastIncident":{"title":"Browserbase: Issue with Browserbase proxies","publishedAt":1777342225000,"isOpen":false,"updates":[{"status":"investigating","body":"We are currently experiencing a disruption that is impacting sessions with proxies.","at":"2026-04-28T02:53:27.000Z"},{"status":"monitoring","body":"We are monitoring the resolution of the earlier disruption. Our team has released a fix and we will continue providing updates here as this fix progresses. Thank you for your patience.","at":"2026-04-28T02:53:43.000Z"},{"status":"resolved","body":"After monitoring the fix, we can confirm our team has resolved the disruption. We appreciate your patience and understanding with our team today as we worked to address this.","at":"2026-04-28T03:09:47.000Z"}]}},{"source_name":"Google Cloud Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":118,"resolveSampleSize":1,"lastIncident":{"title":"Google Cloud: Vertex AI Gemini API customers experienced increased error rates when accessing the global endpoint.","publishedAt":1772195820000,"isOpen":false,"updates":[]}},{"source_name":"SambaNova Status","source_tier":1,"currentState":"resolved","incidents30d":0,"medianResolveMinutes":127.83815,"resolveSampleSize":15,"lastIncident":{"title":"SambaNova: E5-Mistral-7B-Instruct down","publishedAt":1768609513117,"isOpen":false,"updates":[{"status":"investigating","body":"We are currently having issues with E5-Mistral-7B-Instruct down . All other models are responding fine","at":"2026-01-17T00:25:13.205Z"},{"status":"resolved","body":"E5-Mistral-7B-Instruct IS back in service","at":"2026-01-17T02:33:03.398Z"}]}}]}