Outage in Amazon AI

Increased Error Rates - N. Virginia

Resolved Minor

September 21, 2026 - Started about 4 hours ago - Lasted 32 minutes

Incident Report

Summary AI Generated

A 32-minute incident in AWS US-EAST-1 caused elevated API error rates affecting new EC2 instance launches, including failures with RunInstances, CreateFleet, and related launch workflows, while existing instances remained unaffected. The disruption impacted a broad range of services including ECS, EKS, SageMaker, OpenSearch, Fargate, and several networking components such as Transit Gateway, PrivateLink, and Site-to-Site VPN. Engineers identified signs of recovery and recommended retrying failed API calls to mitigate impact during resolution.

We are investigating increased API error rates in the US-EAST-1 Region.

Components affected

Amazon AI Amazon CloudFront Amazon AI Amazon Elastic Compute Cloud Amazon AI Amazon Elastic Compute Cloud (N. Virginia) Amazon AI Amazon Elastic Container Service Amazon AI Amazon Elastic Container Service (N. Virginia) Amazon AI Amazon Elastic Kubernetes Service Amazon AI Amazon Elastic Kubernetes Service (N. Virginia) Amazon AI Amazon Elastic Load Balancing Amazon AI Amazon Elastic Load Balancing (N. Virginia) Amazon AI Amazon Elastic MapReduce Amazon AI Amazon Elastic MapReduce (N. Virginia) Amazon AI Amazon OpenSearch Service Amazon AI Amazon OpenSearch Service (N. Virginia) Amazon AI Amazon SageMaker Amazon AI Amazon SageMaker (N. Virginia) Amazon AI Amazon WorkSpaces Amazon AI Amazon WorkSpaces (N. Virginia) Amazon AI AWS AppSync Amazon AI AWS AppSync (N. Virginia) Amazon AI AWS DataSync Amazon AI AWS DataSync (N. Virginia) Amazon AI AWS Global Accelerator Amazon AI AWS NAT Gateway Amazon AI AWS NAT Gateway (N. Virginia) Amazon AI AWS Site-to-Site VPN Amazon AI AWS Site-to-Site VPN (N. Virginia) Amazon AI AWS Transit Gateway Amazon AI AWS Transit Gateway (N. Virginia) Amazon AI AWS VPCE PrivateLink Amazon AI AWS VPCE PrivateLink (N. Virginia) Amazon AI Traffic Mirroring Amazon AI Traffic Mirroring (N. Virginia) Amazon AI AWS Fargate Amazon AI AWS Fargate (N. Virginia)

Latest Updates ( sorted recent to last )

UPDATE about 4 hours ago - at 09/21/2026 11:44PM

We can confirm increased error rates affecting new instance launches, including elevated API error rates for RunInstances, CreateFleet, and related EC2 launch workflows in the US-EAST-1 Region. Customers attempting to launch new EC2 instances may experience launch failures or elevated API response latency. Our engineers are actively engaged and working towards recovering the issue. We are seeing initial signs of recovery. Existing instances remain unaffected. We recommend retrying failed RunInstances and CreateFleet API calls. We will provide an update by 5:30 PM PDT or sooner.

UPDATE about 4 hours ago - at 09/21/2026 11:26PM

We are investigating increased API error rates in the US-EAST-1 Region.

Latest Amazon AI outages

Elevated connectivity issues with a single Avalability zone - Frankfurt - 2 months ago

Fable 5 and Mythos 5 Access - N. Virginia - 3 months ago

Increased Error Rate and Latency - N. Virginia - 5 months ago

Increased Error Rates - Zurich - 7 months ago

Region Availability - Bahrain - 7 months ago

The Status Page Aggregator with Early Outage Detection

With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.

Start free trial

No credit card required · Cancel anytime · 6320 services available

Integrations with Slack Microsoft Teams Google Chat Datadog PagerDuty Zapier Discord Webhook