> **Experimental**
>
> `@aws-cdk/aws-bedrock-alpha` is an [**experimental**](/stability) (alpha) package: its API may change in any release, without a major version bump.
# BedrockFoundationModelProps

Properties for configuring a Bedrock Foundation Model.

These properties define the model's capabilities and supported features.

Extends: BedrockFoundationModelProps
Used as props by: BedrockFoundationModel

- Stability: [Experimental](/cdk/api/stability.html)
- Source: [`bedrock/models.ts`](https://github.com/aws/aws-cdk/blob/v2.275.0-alpha.0/packages/@aws-cdk/aws-bedrock-alpha/bedrock/models.ts#L57)
- Type last changed: v2.274.0-alpha.0 · 21 Oct 2026

## Example

```ts
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import * as bedrock_alpha from '@aws-cdk/aws-bedrock-alpha';
const bedrockFoundationModelProps: bedrock_alpha.BedrockFoundationModelProps = {
  legacy: false,
  optimizedForAgents: false,
  supportedVectorType: [bedrock_alpha.VectorType.FLOATING_POINT],
  supportsAgents: false,
  supportsConfigurableDimensions: false,
  supportsCrossRegion: false,
  supportsKnowledgeBase: false,
  vectorDimensions: 123,
};
```

## Properties

- `legacy`: boolean = false — https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle.html A version is marked Legacy when there is a more recent version which provides superior performance. Amazon Bedrock sets an EOL date for Legacy versions.

- `optimizedForAgents`: boolean = false — Currently, some of the offered models are optimized with prompts/parsers fine-tuned for integrating with the agents architecture.

  When true, the model has been specifically optimized for agent interactions.

- `supportedVectorType`: [VectorType](/cdk/api/v2/docs/@aws-cdk_aws-bedrock-alpha.VectorType.html)[] = undefined — Embeddings models have different supported vector types.

  Defines whether the model supports floating-point or binary vectors.

- `supportsAgents`: boolean = false — Bedrock Agents can use this model.

  When true, the model can be used with Bedrock Agents for automated task execution.

- `supportsConfigurableDimensions`: boolean = false — Whether the number of vector dimensions can be chosen when the model is used by a knowledge base.

  Only applicable for embedding models. When true, `vectorDimensions` is
  passed to the knowledge base; when false, the model's dimension is fixed and
  `vectorDimensions` is informational only.

- `supportsCrossRegion`: boolean = false — Can be used with a Cross-Region Inference Profile.

  When true, the model supports inference across different AWS regions.

- `supportsKnowledgeBase`: boolean = false — Bedrock Knowledge Base can use this model.

  When true, the model can be used for knowledge base operations.

- `vectorDimensions`: number = undefined — Embedding models have different vector dimensions.

  Only applicable for embedding models. Defines the dimensionality of the vector embeddings.