Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.
For DeployedModel this field is
optional, and the default value is n1-standard-2. For
BatchPredictionJob or as
part of WorkerPoolSpec this
field is required.
For DeployedModel this field is
optional, and the default value is n1-standard-2. For
BatchPredictionJob or as
part of WorkerPoolSpec this
field is required.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],null,["# Interface MachineSpecOrBuilder (1.4.0)\n\n public interface MachineSpecOrBuilder extends MessageOrBuilder\n\nImplements\n----------\n\n[MessageOrBuilder](https://cloud.google.com/java/docs/reference/protobuf/latest/com.google.protobuf.MessageOrBuilder.html)\n\nMethods\n-------\n\n### getAcceleratorCount()\n\n public abstract int getAcceleratorCount()\n\nThe number of accelerators to attach to the machine.\n\n`int32 accelerator_count = 3;`\n\n### getAcceleratorType()\n\n public abstract AcceleratorType getAcceleratorType()\n\nImmutable. The type of accelerator(s) that may be attached to the machine\nas per\naccelerator_count.\n\n`\n.google.cloud.vertexai.v1.AcceleratorType accelerator_type = 2 [(.google.api.field_behavior) = IMMUTABLE];\n`\n\n### getAcceleratorTypeValue()\n\n public abstract int getAcceleratorTypeValue()\n\nImmutable. The type of accelerator(s) that may be attached to the machine\nas per\naccelerator_count.\n\n`\n.google.cloud.vertexai.v1.AcceleratorType accelerator_type = 2 [(.google.api.field_behavior) = IMMUTABLE];\n`\n\n### getMachineType()\n\n public abstract String getMachineType()\n\nImmutable. The type of the machine.\n\nSee the [list of machine types supported for\nprediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types)\n\nSee the [list of machine types supported for custom\ntraining](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types).\n\nFor DeployedModel this field is\noptional, and the default value is `n1-standard-2`. For\nBatchPredictionJob or as\npart of WorkerPoolSpec this\nfield is required.\n\n`string machine_type = 1 [(.google.api.field_behavior) = IMMUTABLE];`\n\n### getMachineTypeBytes()\n\n public abstract ByteString getMachineTypeBytes()\n\nImmutable. The type of the machine.\n\nSee the [list of machine types supported for\nprediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types)\n\nSee the [list of machine types supported for custom\ntraining](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types).\n\nFor DeployedModel this field is\noptional, and the default value is `n1-standard-2`. For\nBatchPredictionJob or as\npart of WorkerPoolSpec this\nfield is required.\n\n`string machine_type = 1 [(.google.api.field_behavior) = IMMUTABLE];`\n\n### getTpuTopology()\n\n public abstract String getTpuTopology()\n\nImmutable. The topology of the TPUs. Corresponds to the TPU topologies\navailable from GKE. (Example: tpu_topology: \"2x2x1\").\n\n`string tpu_topology = 4 [(.google.api.field_behavior) = IMMUTABLE];`\n\n### getTpuTopologyBytes()\n\n public abstract ByteString getTpuTopologyBytes()\n\nImmutable. The topology of the TPUs. Corresponds to the TPU topologies\navailable from GKE. (Example: tpu_topology: \"2x2x1\").\n\n`string tpu_topology = 4 [(.google.api.field_behavior) = IMMUTABLE];`"]]
