databricks-model-serving
Installation
SKILL.md
Model Serving Endpoints
FIRST: Use the parent databricks-core skill for CLI basics, authentication, and profile selection.
Gateway boundary: This skill owns legacy AI Gateway configuration attached to a Model Serving endpoint, such as
serving-endpoints put-ai-gateway. An explicit Unity Gateway / Unity AI Gateway request or anydatabricks ai-gatewaymodel service, MCP service, or model provider service belongs todatabricks-unity-gateway.
Model Serving provides managed endpoints for serving LLMs, custom ML models, and external models as scalable REST APIs. Endpoints are identified by name (unique per workspace).
Endpoint Types
| Type | When to Use | Key Detail |
|---|---|---|
| Pay-per-token | Foundation Model APIs (Llama, GPT-5, Claude, Gemini, etc.) | Uses system.ai.* catalog models, pre-provisioned in every workspace. Discover at runtime — see Foundation Model API endpoints below. |
| Provisioned throughput | Dedicated GPU capacity | Guaranteed throughput, higher cost |
| Custom model | Your own MLflow models or containers | Deploy any model with an MLflow signature |