Serverless infrastructure for AWS

Deploy containers as scalable microservices

Realtime APIs

Realtime APIs respond to requests in real-time and autoscale based on in-flight request volumes.

Batch APIs

Batch APIs run distributed and fault-tolerant batch processing jobs on-demand.

Async APIs

Async APIs process requests asynchronously and autoscale based on request queue length.

Reduce your AWS spend

Spot and reserved instance management

Cortex can run workloads on spot instances and fall back to on-demand instances to ensure reliability.

Multi-instance type clusters

Choose the ideal instance type for your workloads or mix and match several instance types in the same cluster.

Customizable autoscaling

Optimize the autoscaling behavior for each workload to ensure efficient resource utilization.

Forget about resource limits, cold starts, and timeouts

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.

Improve developer productivity

Serverless compute

Deploy any container without managing infrastructure.

Observability integrations

Monitor your workloads with pre-built dashboards or create custom ones.

Programmable deployments

Deploy programmatically from any CI/CD tool.

Local debugging

Debug your code locally before deploying to your cluster.

HTTP and gRPC

Expose APIs as HTTP or gRPC endpoints.

Traffic splitting

Configure A/B tests and shadow pipelines.

Create a cluster on your AWS account

EKS

Cortex runs on top of EKS to scale workloads reliably and cost-effectively.

SQS

Cortex automatically manages SQS queues for batch and async APIs.

EC2 Auto Scaling

Cortex automatically provisions EC2 instances to handle any workload.

VPC

Cortex deploys into a VPC on your account so your data stays private.

IAM

Cortex integrates with IAM to simplify authentication and authorization.

ECR

Cortex connects to public or private Docker container registries.

Common use cases

Realtime model serving

Deploy machine learning models as realtime HTTP or gRPC APIs and seamlessly scale inference across CPU or GPU instances.

Image, video, and audio processing

Build data processing pipelines that can scale to handle large structured or unstructured data sets.

Compute-intensive microservices

Deploy web scraping, file processing, and other compute-intensive workloads without managing instances, autoscaling groups, or load balancers.

Machine learning operations (MLOps)

Create services that continuously retrain and evaluate models to maintain their accuracy over time. Then update APIs to use the latest models.

Build scalable backends faster

Discovering Cortex has been a lifesaver, it is servicing half a billion API calls each month for us. The ease with which we’ve been able to deploy Cortex has facilitated rapid development across our team, enabling us to meet the needs of our highly demanding customers.

Madison Bahmer - Two Six Technologies