Website • Slack • Docs

Cost-effective serverless computing

Cortex is a highly-scalable serverless computing platform that is up to 90% less expensive than AWS Lambda. It is designed for scaling compute-intensive realtime, async, and batch workloads on your AWS account. Organizations worldwide use Cortex to scale microservices, data processing, machine learning, and other applications in production.

Maximize compute utilization

Workload autoscaling - set autoscaling policies per workload based on its traffic.

Resource requests - configure CPU, GPU, and memory requests per workload, without limits.

Container deployments - customize the runtime and request concurrency for each container.

Minimize compute costs

Cluster autoscaling - elastically scale your cluster to meet demand.

Spot instances - run workloads on spot instances without sacrificing reliability.

Multi-instance - use multiple instance types to optimize price-performance ratio per workload.

Visualize and control spend

Metrics dashboard - monitor latency and resource utilization with pre-built dashboards.

Spend visibility - visualize your spend using the latest AWS pricing information.

Resource limits - set limits on resource consumption globally and per workload.