bedrock/aws.sdk.kotlin.services.bedrock/createCustomModel

createCustomModel

inline suspend fun BedrockClient.createCustomModel(crossinline block: CreateCustomModelRequest.Builder.() -> Unit): CreateCustomModelResponse

Creates a new custom model in Amazon Bedrock. After the model is active, you can use it for inference.

To use the model for inference, you must purchase Provisioned Throughput for it. You can't use On-demand inference with these custom models. For more information about Provisioned Throughput, see Provisioned Throughput.

The model appears in ListCustomModels with a customizationType of imported. To track the status of the new model, you use the GetCustomModel API operation. The model can be in the following states:

Creating - Initial state during validation and registration
Active - Model is ready for use in inference
Failed - Creation process encountered an error

Related APIs

Samples

import aws.sdk.kotlin.services.bedrock.model.ModelDataSource
import aws.sdk.kotlin.services.bedrock.model.S3DataSource
import aws.sdk.kotlin.services.bedrock.model.Tag

fun main() { 
   //sampleStart 
   // Successful CreateCustomModel API call
val resp = bedrockClient.createCustomModel {
    modelName = "SampleModel"
    modelSourceConfig = ModelDataSource.S3DataSource(S3DataSource {
        s3Uri = "s3://my-bucket/folder"
    }
    )
    roleArn = "arn:aws:iam::123456789012:role/SampleRole"
    modelKmsKeyArn = "arn:aws:kms:us-east-1:123456789012:key/1234abcd-12ab-34cd-56ef-1234567890ab"
    modelTags = listOf<Tag>(
        Tag {
            key = "foo"
            value = "foo"
        },
        Tag {
            key = "foo"
            value = "foo"
        }            
    )
    clientRequestToken = "foo"
} 
   //sampleEnd
}