v2
latestOpenAPI 3.1.02026-08-07139158192.4 KBDrain a serving deployment (platform admin)
Moves the deployment to draining. The reconcile loop drains its pool members so no replica takes new traffic while in-flight requests finish. Idempotent on an already-draining deployment.
Path parameters
Response
Draining
Live catalog routing weight of this deployment's backend. Only present when backendRegistered is true. May differ from backendWeight (the row mirror) while a rollout ramp is in flight.
Live catalog health of this deployment's backend (the kill switch). Only present when backendRegistered is true.
Whether this deployment's pool:// backend is currently present on the catalog model row. Absent when the live catalog state could not be read; false until the first replica passes readiness.
Routing weight of the catalog backend. 0 = standby (blue/green starts here)
Inference engine, e.g. vllm or sglang
Engine container image override; absent = the engine's default
True when replicas and their private endpoint pool are for direct operator testing only. Isolated deployments never register a catalog backend, never participate in blue/green rollout, and cannot receive gateway traffic.
Exclusive text-request byte ceiling for routing eligibility; 0 or absent = unbounded. Routing hint only, not a context limit.
Inclusive text-request byte floor for routing eligibility; 0 or absent = unbounded. Routing hint only, not a context limit.
Stable logical capacity lane within the public model. Blue/green only replaces versions in the same node pool; empty preserves legacy model-wide grouping.
Org that owns the managed replicas (and their metering)
Endpoint pool the deployment's replicas register in
Catalog model this deployment serves capacity for
Model id the engine serves; must equal the catalog backend ref
Human-readable cause for degraded/failed states
Generation marker for blue/green within one public model and node pool
Staged-checkpoint reference; absent = the engine loads from its own source