Current status by service (api.agents.inkeep.com run chat) is down

Text API (OpenAI GPT OSS 20B chat completion API) is down

Elevated errors across many models

Elevated errors on Claude Fable 5 and Claude Mythos 5

Feed blocked messages displayed in Vespa Cloud console is fake news.

Scheduled network maintenance

Elevated errors for GLM 5.2 on Model APIs. **Dedicated Inference is not affected**

Elevated inference 500s for a subset of models deployed in 1 cluster

Degraded metrics performance in dashboard and API. **Inference is not affected**

Unable to provision new endpoint certificates - affects new deployments with legacy endpoints

Computer Sandbox Issue

Inference - Chat (Google Gemma 4 31B IT) is down

Issues with prediction requests against custom model deployments

Elevated errors on Claude Opus 4.8

Data Center Failure Impacting Capacity

CEM Slowness

We’ve suspended access to Claude Mythos 5 and Claude Fable 5

Elevated errors in a single EU cluster

Intermittent Issues Affecting App/Bot Training on JP Search Instance

Intermittent Issues Affecting Analytics on IND Instance

搜索请求出现大量报错

Database Maintenance

Computer Sandbox Issue

US Central Region - Call recording availability is impacted

Elevated error rates on Opus 4.8

Degraded outbound DNS from runners

Amp unable to connect to threads

Production US Cluster Upgrade

Storage degraded - impacting app creation

Writer Agent SEV1 Outage (DB Lock Contention During Migration)

Writer Down

Elevated error rates on GLM 5.2 Model APIs. **Dedicated Inference is not affected**

Codex Usage Limits Depleting Faster Than Expected

Elevated errors on Opus 4.5

Brief Service Unavailability on June 29 for app.nanonets.com

Amp is seeing degraded performance

XO Platform Release (10.27.0/11.26.0) /XO Contact Center (v3.26.0) - IND Region

Issues with ChatGPT Windows desktop app

elevated errors on Opus 48

Elevated inference 500s for models in 1 cluster due to cloud provider outage

Elevated model deployment failures. **Inference is not affected**

FedRAMP workspaces and API orgs have degraded performance

Elevated errors for dedicated inference in a subset of clusters

Degraded service

Authentication issues on Vespa Cloud console

Small Number of Users Have Incorrectly Cancelled Subscription

Processing delay on Agent Tasks

Timeout on transcriptions using speaker labels

Agents UI freezing issue

Users may encounter issues using access token with Codex

Managed US AI Cloud Model Monitoring Planned Maintenance

ampcode.com returning 500

Interactions Tab Latency

Elevated errors on Opus 4.8 Fast

Elevated error rate on Claude Opus 4.8

Processing Delay on Agents

Pre-recorded Universal-3-pro and Universal-3-5-pro degradation in the EU

gpt-4o-mini high error rate

ISP Network-Related Issue

Slow message sending and media sending failures

Claude.ai is experiencing elevated error rates

Voice Agent third-party provider Instability (Anthropic LLMs)

Elevated error rate across multiple models

Users may experience elevated errors in ChatGPT uploading and downloading files

Document response incomplete (9:12 - 9:21 UTC)

Elevated errors for Claude Opus 4.8

Slower than usual scale-ups. High failure rate for new model deploys. Existing replicas aren't impacted.

Read AI is experiencing delays in meeting report proccessing.

Elevated errors across many models

Elevated errors for Claude Opus 4.8

Production Release - 26.6.2

Production Release - 26.6.2

Elevated Error Rates for Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 4.6, and Haiku 4.5

EURO - Data Explorer Upgarde Maintenance

Complete Service Outage – MEA Region

IND - Data Explorer Upgrade Maintenance

EURO Region Planned Maintenance Activity

MEA Region Planned Maintenance Activity

IND Region Planned Maintenance Activity

Microsoft STT Outage

Elevated errors when using Google Gemini models with Voice Agent

400 errors with PreRecorded STT ("REMOTE_CONTENT_ERROR" / "failed to return valid data") when passing a URL