Segal Endpoints
Serve a model or application from a containerized inference service with a managed network endpoint.
Engineering-led activation. Production access depends on an authorized provider account, a customer-specific service binding and confirmed availability.
How the service fits.
Containerized inference applications. Replica, authentication and scaling options follow the supported deployment configuration.
- 1
Publish a versioned inference container
- 2
Select a supported accelerator and replica policy
- 3
Expose the application endpoint with the required access controls
Service architecture
- Image, startup command and listening port are explicit
- Model artifacts and secrets are mounted separately
- Scaling follows the deployment’s supported policy
Operating boundaries
- A model benchmark is required for latency and throughput claims
- Scale-to-zero and cold-start behavior depend on the service configuration
- Credentials for private models are never included in public examples
Deployment & support
Segal provides the branded service experience and coordinates configuration, support and commercial scope. The infrastructure service is supplied through OVHcloud; provider eligibility and applicable service terms must be confirmed before activation.
Upstream service: AI Deploy. Provider specifications were reviewed on 24 October 2026; actual inventory and quota are checked separately.
Upstream technical reference