Sign in

v1

latestOpenAPI 3.0.0Apache 2.0 License2026-07-14108906717.7 KB

Deploys a custom model for on-demand inference in Amazon Bedrock. After you deploy your custom model, you use the deployment's Amazon Resource Name (ARN) as the modelId parameter when you submit prompts and generate responses with model inference.

For more information about setting up on-demand inference for custom models, see Set up inference for a custom model.

The following actions are related to the CreateCustomModelDeployment operation:

post/model-customization/custom-model-deployments

Request body

modelDeploymentNamestring required

The name for the custom model deployment. The name must be unique within your Amazon Web Services account and Region.

modelArnstring required

The Amazon Resource Name (ARN) of the custom model to deploy for on-demand inference. The custom model must be in the <code>Active</code> state.

descriptionstring

A description for the custom model deployment to help you identify its purpose.

clientRequestTokenstring

A unique, case-sensitive identifier to ensure that the operation completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-idempotency.html">Ensuring idempotency</a>.

Response

Success

customModelDeploymentArnstring required

The Amazon Resource Name (ARN) of the custom model deployment. Use this ARN as the <code>modelId</code> parameter when invoking the model with the <code>InvokeModel</code> or <code>Converse</code> operations.