Type Alias: ModelTarget

ModelTarget = z.infer<typeof ModelTargetSchema>

ModelTarget fields

One discovered model plus every alias accepted by the gateway.

• id: Canonical model id advertised by the gateway.
• aliases: Additional names that resolve to this model.
• displayName: Human-readable label shown to clients.
• family (optional): Detected model family used for grouping.
• modelServiceName (optional): Canonical model-service name for metadata lookup.
• endpoint (optional): Normalized serving endpoint backing this target, when discovered.
• endpoint.name: Serving endpoint invoke id.
• endpoint.displayName (optional): Human-readable label when the workspace provides one.
• endpoint.family (optional): Detected model family used for grouping and sort order.
• endpoint.task (optional): Databricks serving task reported for the endpoint.
• endpoint.state (optional): Serving endpoint lifecycle state.
• endpoint.description (optional): Workspace-provided endpoint description.
• endpoint.supportsTools (optional): True when the endpoint accepts tool calls.
• endpoint.profile (optional): Relative quality, speed, and cost scores.
• endpoint.profile.quality (optional): Relative quality score for ranking.
• endpoint.profile.speed (optional): Relative speed score for ranking.
• endpoint.profile.cost (optional): Relative cost score for ranking.
• endpoint.class (optional): Intent-oriented class assigned to this endpoint.
• endpoint.serviceNames (optional): Provider-specific service name aliases keyed by protocol.
• endpoint.modelServiceName (optional): Canonical model-service name used for metadata lookup.
• endpoint.reasoningEfforts (optional): Reasoning effort values this endpoint accepts.
• endpoint.status (optional): Retirement status for this endpoint.
• endpoint.status.deprecated (optional): True when the model should no longer be selected by default.
• endpoint.dimension (optional): Embedding vector size when the endpoint is an embedding model.
• capabilities: Protocol and feature capabilities for this target.
• capabilities.responses: True when the model can serve the Databricks Responses API.
• capabilities.openResponses: True when the model can serve OpenAI Responses.
• capabilities.chat: True when the model can serve Chat Completions.
• capabilities.anthropic: True when the model can serve Anthropic Messages.
• capabilities.embeddings: True when the model can serve embeddings.
• capabilities.aiGatewayCodex: True when the model is reachable through AI Gateway Codex.
• capabilities.tools: True when the model accepts tools.
• capabilities.reasoning: True when the model accepts reasoning effort.
• capabilities.streaming: True when the model can stream tokens.
• capabilities.parallelTools: True when the model can run multiple tools in one turn.
• capabilities.customTools: True when the model accepts custom tool definitions.
• capabilities.structuredOutput: True when the model can return structured output.
• capabilities.webSearch: True when the model can use web search.
• reasoningEfforts: Reasoning effort values this target accepts.