CreateClusterRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/CreateClusterRequest",
  "title": "CreateClusterRequest",
  "type": "object",
  "required": [
    "cluster_name",
    "spark_version",
    "node_type_id"
  ],
  "properties": {
    "cluster_name": {
      "type": "string",
      "description": "A human-readable name for the cluster. This does not need to be unique.",
      "examples": [
        "my-data-cluster"
      ]
    },
    "spark_version": {
      "type": "string",
      "description": "The runtime version of the cluster. You can retrieve a list of available runtime versions using the Runtime Versions API.",
      "examples": [
        "14.3.x-scala2.12"
      ]
    },
    "node_type_id": {
      "type": "string",
      "description": "The node type for worker nodes. This field determines the cloud provider instance type.",
      "examples": [
        "i3.xlarge"
      ]
    },
    "driver_node_type_id": {
      "type": "string",
      "description": "The node type for the Spark driver. If not specified, defaults to the same value as node_type_id.",
      "example": "500123"
    },
    "num_workers": {
      "type": "integer",
      "description": "Number of worker nodes for a fixed-size cluster. A cluster has one Spark driver and num_workers executors. Set to 0 for a single-node cluster.",
      "examples": [
        2
      ]
    },
    "autoscale": {
      "$ref": "#/components/schemas/AutoScale"
    },
    "spark_conf": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      },
      "description": "A map of Spark configuration key-value pairs. These override the default Spark configuration values.",
      "example": "example_value"
    },
    "aws_attributes": {
      "$ref": "#/components/schemas/AwsAttributes"
    },
    "azure_attributes": {
      "$ref": "#/components/schemas/AzureAttributes"
    },
    "gcp_attributes": {
      "$ref": "#/components/schemas/GcpAttributes"
    },
    "custom_tags": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      },
      "description": "Additional tags for cluster resources. Tags are propagated to the cloud provider for cost tracking.",
      "example": "example_value"
    },
    "spark_env_vars": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      },
      "description": "Environment variables for all Spark processes. Use {{secrets/scope/key}} to reference secrets.",
      "example": "example_value"
    },
    "autotermination_minutes": {
      "type": "integer",
      "description": "Minutes of inactivity after which the cluster is automatically terminated. 0 disables auto-termination.",
      "default": 120,
      "example": 10
    },
    "enable_elastic_disk": {
      "type": "boolean",
      "description": "Whether to autoscale local storage. When enabled, Databricks monitors disk usage and attaches additional disks as needed.",
      "example": true
    },
    "instance_pool_id": {
      "type": "string",
      "description": "The optional ID of the instance pool to use for cluster nodes.",
      "example": "500123"
    },
    "policy_id": {
      "type": "string",
      "description": "The ID of the cluster policy to apply. Cluster policies constrain the configuration settings.",
      "example": "500123"
    },
    "enable_local_disk_encryption": {
      "type": "boolean",
      "description": "Whether to encrypt data on local disks.",
      "example": true
    },
    "runtime_engine": {
      "type": "string",
      "enum": [
        "STANDARD",
        "PHOTON"
      ],
      "description": "The runtime engine. PHOTON enables the Photon vectorized query engine for faster performance.",
      "example": "STANDARD"
    },
    "data_security_mode": {
      "type": "string",
      "enum": [
        "NONE",
        "SINGLE_USER",
        "USER_ISOLATION",
        "LEGACY_TABLE_ACL",
        "LEGACY_PASSTHROUGH",
        "LEGACY_SINGLE_USER",
        "LEGACY_SINGLE_USER_STANDARD"
      ],
      "description": "Data security mode for the cluster.",
      "example": "NONE"
    },
    "single_user_name": {
      "type": "string",
      "description": "The user name (email) of the single user for SINGLE_USER access mode.",
      "example": "example_value"
    },
    "init_scripts": {
      "type": "array",
      "items": {
        "$ref": "#/components/schemas/InitScriptInfo"
      },
      "description": "Init scripts to run when the cluster starts.",
      "example": []
    },
    "ssh_public_keys": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "SSH public keys to add to each Spark node.",
      "example": []
    }
  }
}