cortex

Website • Slack • Docs

Serverless containers on AWS

Deploy, manage, and scale containers without managing infrastructure.

Build APIs faster

• Realtime APIs - respond to requests in real-time and autoscale based on in-flight request volumes.
• Batch APIs - run distributed and fault-tolerant batch processing jobs on-demand.
• Async APIs - process requests asynchronously and autoscale based on request queue length.

Scale without limits

• No resource limits - allocate as much CPU, GPU, and memory as each workload requires.
• No cold starts - keep a minimum number of API replicas running to ensure that requests are handled in real-time.
• No timeouts - run workloads for as long as you want.

Reduce your AWS spend

• Spot instance management - Cortex runs workloads on spot instances and fall back to on-demand instances to ensure reliability.
• Multi-instance type clusters - Cortex runs different workloads on different EC2 instances to ensure efficient resource utilization.
• Efficient autoscaling - Cortex optimizes the autoscaling behavior of each workload to minimize idle resources.