Skip to main content
A TrueFoundry Service represents a continuously running application that typically provides a set of APIs for interaction. Services can be dynamically scaled based on incoming traffic or resource demands. Services are perfect for scenarios where real-time responses are essential, such as:
  • Hosting Real-time Model Inference (e.g., Flask, FastAPI)
  • Fueling Dynamic Website Backends
  • Creating Model Demos (e.g., Streamlit, Gradio)
TrueFoundry makes it easy to configure various aspects of your service deployment.

Dockerize Code

Deploy from Github, local machine or a prebuilt image.

Customize Resources

Set CPU, GPU, memory resources and spot/on-demand instances.

Environment Variables And Secrets

Set environment variables and secrets for your service.

Pause/Resume

Pause/Resume to save cost

Domain Mapping to Endpoints

Expose ports and map DNS to endpoints.

Endpoint Authentication

Add authentication to your endpoints.

Autoscaling

Autoscale on CPU, traffic or time based policies.

Rollout Strategy

Configure Canary, Blue/Green rollout strategies.

Access Cloud Services

Access S3 / GCS /Azure Container / other cloud managed services.

Health Probes

Setup probes to check the health of your service.

Mounting Volumes

Mount volumes to cache data

Deploy Programatically

Deploy using Python and CLI

Setup CI/CD

Setup with your favorite CI/CD tool.

Clone, Update, and Rollback

Clone, update version, rollback to previous version and promote to production

View Metrics

View the most important metrics for your service.

View Logs

View the logs on a service or per pod.

Set Up Alerts

Setup alerts and nottifications for your service