google-genai-kotlin/com.google.genai.kotlin.types/Model

Model

@Serializable

data class Model(val name: String? = null, val displayName: String? = null, val description: String? = null, val version: String? = null, val endpoints: List<Endpoint>? = null, val labels: Map<String, String>? = null, val tunedModelInfo: TunedModelInfo? = null, val inputTokenLimit: Int? = null, val outputTokenLimit: Int? = null, val supportedActions: List<String>? = null, val defaultCheckpointId: String? = null, val checkpoints: List<Checkpoint>? = null, val temperature: Double? = null, val maxTemperature: Double? = null, val topP: Double? = null, val topK: Int? = null, val thinking: Boolean? = null)

A trained machine learning model.

Constructors

Model

constructor(name: String? = null, displayName: String? = null, description: String? = null, version: String? = null, endpoints: List<Endpoint>? = null, labels: Map<String, String>? = null, tunedModelInfo: TunedModelInfo? = null, inputTokenLimit: Int? = null, outputTokenLimit: Int? = null, supportedActions: List<String>? = null, defaultCheckpointId: String? = null, checkpoints: List<Checkpoint>? = null, temperature: Double? = null, maxTemperature: Double? = null, topP: Double? = null, topK: Int? = null, thinking: Boolean? = null)

Properties

checkpoints

val checkpoints: List<Checkpoint>? = null

The checkpoints of the model.

defaultCheckpointId

val defaultCheckpointId: String? = null

The default checkpoint id of a model version.

description

val description: String? = null

Description of the model.

displayName

val displayName: String? = null

Display name of the model.

endpoints

val endpoints: List<Endpoint>? = null

List of deployed models created from this base model. Note that a model could have been deployed to endpoints in different locations.

inputTokenLimit

val inputTokenLimit: Int? = null

The maximum number of input tokens that the model can handle.

labels

val labels: Map<String, String>? = null

Labels with user-defined metadata to organize your models.

maxTemperature

val maxTemperature: Double? = null

The maximum temperature value used for sampling set when the dataset was saved. This value is used to tune the degree of randomness.

name

val name: String? = null

Resource name of the model.

outputTokenLimit

val outputTokenLimit: Int? = null

The maximum number of output tokens that the model can generate.

supportedActions

val supportedActions: List<String>? = null

List of actions that are supported by the model.

temperature

val temperature: Double? = null

Temperature value used for sampling set when the dataset was saved. This value is used to tune the degree of randomness.

thinking

val thinking: Boolean? = null

Whether the model supports thinking features. If true, thoughts are returned only if the model supports thought and thoughts are available.

topK

val topK: Int? = null

Optional. Specifies the top-k sampling threshold. The model considers only the top k most probable tokens for the next token. This can be useful for generating more coherent and less random text. For example, a top_k of 40 means the model will choose the next word from the 40 most likely words.

topP

val topP: Double? = null

Optional. Specifies the nucleus sampling threshold. The model considers only the smallest set of tokens whose cumulative probability is at least top_p. This helps generate more diverse and less repetitive responses. For example, a top_p of 0.9 means the model considers tokens until the cumulative probability of the tokens to select from reaches 0.9. It's recommended to adjust either temperature or top_p, but not both.

tunedModelInfo

val tunedModelInfo: TunedModelInfo? = null

Information about the tuned model from the base model.

version

val version: String? = null

Version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model ID. The version ID is an auto-incrementing decimal number in string representation.