API Reference
All HTTP endpoints are versioned under /api/v1/ and require a bearer token. gRPC services are exposed on port 50051.
Authentication
Section titled “Authentication”Authorization: Bearer <token>Obtain tokens via the Admin → API Keys page or the /api/v1/auth/token endpoint.
Inference
Section titled “Inference” POST
/api/v1/inference Run a synchronous inference against the active model version.
GET
/api/v1/inference/{id} Fetch a stored inference record by ID.
Models
Section titled “Models” GET
/api/v1/models POST
/api/v1/models Register a new model version.
POST
/api/v1/models/{name}/promote Promote a version to production.
Datasources
Section titled “Datasources” GET
/api/v1/datasources POST
/api/v1/datasources DELETE
/api/v1/datasources/{id} Observability
Section titled “Observability” GET
/api/v1/stats/inference Aggregated latency and throughput statistics.
OpenAPI
Section titled “OpenAPI”The full OpenAPI spec is published at /api/v1/openapi.json on every running device.