Skip to content

Variable: ServingEndpointSummarySchema

const ServingEndpointSummarySchema: ZodObject<{ class: ZodOptional<ZodEnum<{ chat-balanced: "chat-balanced"; chat-fast: "chat-fast"; chat-thinking: "chat-thinking"; embedding: "embedding"; }>>; description: ZodOptional<ZodString>; dimension: ZodOptional<ZodNumber>; displayName: ZodOptional<ZodString>; family: ZodOptional<ZodString>; modelServiceName: ZodOptional<ZodString>; name: ZodString; profile: ZodOptional<ZodObject<{ cost: ZodOptional<ZodNumber>; quality: ZodOptional<ZodNumber>; speed: ZodOptional<ZodNumber>; }, $strip>>; reasoningEfforts: ZodOptional<ZodArray<ZodEnum<{ high: "high"; low: "low"; max: "max"; medium: "medium"; minimal: "minimal"; none: "none"; xhigh: "xhigh"; }>>>; serviceNames: ZodOptional<ZodRecord<ZodString, ZodString>>; state: ZodOptional<ZodString>; status: ZodOptional<ZodObject<{ deprecated: ZodDefault<ZodBoolean>; }, $strip>>; supportsTools: ZodOptional<ZodBoolean>; task: ZodOptional<ZodString>; }, $strip>

Browser-safe normalized Model Serving endpoint metadata.

  • name: Serving endpoint invoke id.
  • displayName (optional): Human-readable label when the workspace provides one.
  • family (optional): Detected model family used for grouping and sort order.
  • task (optional): Databricks serving task reported for the endpoint.
  • state (optional): Serving endpoint lifecycle state.
  • description (optional): Workspace-provided endpoint description.
  • supportsTools (optional): True when the endpoint accepts tool calls.
  • profile (optional): Relative quality, speed, and cost scores.
  • profile.quality (optional): Relative quality score for ranking.
  • profile.speed (optional): Relative speed score for ranking.
  • profile.cost (optional): Relative cost score for ranking.
  • class (optional): Intent-oriented class assigned to this endpoint.
  • serviceNames (optional): Provider-specific service name aliases keyed by protocol.
  • modelServiceName (optional): Canonical model-service name used for metadata lookup.
  • reasoningEfforts (optional): Reasoning effort values this endpoint accepts.
  • status (optional): Retirement status for this endpoint.
  • status.deprecated (optional): True when the model should no longer be selected by default.
  • dimension (optional): Embedding vector size when the endpoint is an embedding model.