* [Health Check](health-check.md): Enable health check on the upstream node, and will automatically filter unhealthy nodes during load balancing to ensure system stability.
* Router
* [radixtree](router-radixtree.md)
* [Stand Alone Model](stand-alone.md): Supports to load route rules from local yaml file, it is more friendly such as under the kubernetes(k8s).
* [prometheus](plugins/prometheus.md): Expose metrics related to APISIX and proxied upstream services in Prometheus exposition format, which can be scraped by a Prometheus Server.
* [OpenTracing](plugins/zipkin.md): Supports Zikpin and Apache SkyWalking.
* [fault-injection](plugins/fault-injection.md): The specified response body, response code, and response time can be returned, which provides processing capabilities in different failure scenarios, such as service failure, service overload, and high service delay.
The recommended approach is to deploy APISIX with [AWS CDK](https://aws.amazon.com/cdk/) on [AWS Fargate](https://aws.amazon.com/fargate/) which helps you decouple the APISIX layer and the upstream layer on top of a fully-managed and secure serverless container compute environment with autoscaling capabilities.
See [this guide](https://github.com/pahud/cdk-samples/blob/master/typescript/apisix/README.md) by [Pahud Hsieh](https://github.com/pahud) and learn how to provision the recommended architecture 100% in AWS CDK.