Segal Endpoints
Serve a model or application from a containerized inference service with a managed network endpoint.
The supported upstream service is AI Deploy. Segal supplies the branded application and support boundary; activation depends on the approved customer configuration and applicable provider terms.
Request and resource flow
- Publish a versioned inference container.
- Select a supported accelerator and replica policy.
- Expose the application endpoint with the required access controls.
Configuration responsibilities
- Image, startup command and listening port are explicit.
- Model artifacts and secrets are mounted separately.
- Scaling follows the deployment’s supported policy.
Supported scope
Containerized inference applications. Replica, authentication and scaling options follow the supported deployment configuration.
- 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.
Read your organization’s inventory
Open the Endpoints workspace after signing in. The server resolves your active organization and its allowed OVHcloud resources. It does not accept a provider project ID from the browser.
The authenticated endpoint is GET /api/infrastructure/endpoints. Supply an allowed region where needed, and a zero-based page for inventory pagination. Each response reports the requested region and the next page when one exists. Project-wide inventories may contain resources from more than one region; an unreported resource region is not inferred from a seed catalog.
The endpoint uses the Segal browser session. Demonstration sk_segal_ keys do not grant production access. Provider credentials stay server-side. A missing connection returns an explicit error rather than sample resources.
Ordering and changes
New orders and configuration changes for this service are engineering-assisted. The workspace reads authorized provider inventory; it does not imply an automated purchase or provisioning workflow. Request a configuration review before committing to a plan.
Activation and service evidence
Follow provider setup before enabling live access. Demo resources, website imagery and documentation examples do not verify capacity, certification, latency or delivery. Confirm regional availability, contract scope, recovery ownership and final customer pricing before production use.
Read the product architecture. Upstream technical reference: AI Deploy (reviewed 24 October 2026).