Skip to content

BedrockModelOptions

Defined in: src/models/bedrock.ts:344

Options for creating a BedrockModel instance.

optional maxTokens?: number;

Defined in: src/models/bedrock.ts:243

Maximum number of tokens to generate in the response.

https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InferenceConfiguration.html

BedrockModelConfig.maxTokens


optional temperature?: number;

Defined in: src/models/bedrock.ts:250

Controls randomness in generation.

https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InferenceConfiguration.html

BedrockModelConfig.temperature


optional topP?: number;

Defined in: src/models/bedrock.ts:257

Controls diversity via nucleus sampling.

https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InferenceConfiguration.html

BedrockModelConfig.topP


optional stopSequences?: string[];

Defined in: src/models/bedrock.ts:262

Array of sequences that will stop generation when encountered.

BedrockModelConfig.stopSequences


optional cacheConfig?: CacheConfig;

Defined in: src/models/bedrock.ts:269

Configuration for prompt caching.

https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html

BedrockModelConfig.cacheConfig


optional additionalRequestFields?: JSONValue;

Defined in: src/models/bedrock.ts:274

Additional fields to include in the Bedrock request.

BedrockModelConfig.additionalRequestFields


optional additionalResponseFieldPaths?: string[];

Defined in: src/models/bedrock.ts:279

Additional response field paths to extract from the Bedrock response.

BedrockModelConfig.additionalResponseFieldPaths


optional additionalArgs?: JSONValue;

Defined in: src/models/bedrock.ts:285

Additional arguments to pass through to the Bedrock Converse API.

https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/client/bedrock-runtime/command/ConverseStreamCommand/

BedrockModelConfig.additionalArgs


optional stream?: boolean;

Defined in: src/models/bedrock.ts:295

Whether or not to stream responses from the model.

This will use the ConverseStream API instead of the Converse API.

BedrockModelConfig.stream


optional includeToolResultStatus?: boolean | "auto";

Defined in: src/models/bedrock.ts:303

Flag to include status field in tool results.

  • true: Always include status field
  • false: Never include status field
  • 'auto': Automatically determine based on model ID (default)

BedrockModelConfig.includeToolResultStatus


optional guardrailConfig?: BedrockGuardrailConfig;

Defined in: src/models/bedrock.ts:309

Guardrail configuration for content filtering and safety controls.

https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html

BedrockModelConfig.guardrailConfig


optional useNativeTokenCount?: boolean;

Defined in: src/models/bedrock.ts:320

Whether to use the native Bedrock CountTokens API.

When true, countTokens() calls the Bedrock CountTokens API for accurate counts. When false or not set (default), skips the API call and uses the character-based heuristic estimator.

false

BedrockModelConfig.useNativeTokenCount


optional strictTools?: boolean;

Defined in: src/models/bedrock.ts:338

Constrain the model to emit tool names and inputs that conform to each tool’s schema.

When true, every tool is sent with strict: true and a copy of its inputSchema with additionalProperties: false added to each object type, so a free-form { type: 'object' } parameter becomes one the model can only fill with {}. Bedrock rejects schemas that use features outside its strict subset (recursive or external $ref, minimum/maximum/ multipleOf, minLength/maxLength, additionalProperties other than false) with a 400 at request time, and compiles each new schema on first use, which can take minutes. Incompatible with citations for Anthropic models.

false

BedrockModelConfig.strictTools


optional region?: string;

Defined in: src/models/bedrock.ts:348

AWS region to use for the Bedrock service.


optional clientConfig?: BedrockRuntimeClientConfig;

Defined in: src/models/bedrock.ts:353

Configuration for the Bedrock Runtime client.


optional requestTimeout?: number;

Defined in: src/models/bedrock.ts:364

Milliseconds of stream inactivity before a Bedrock request is aborted.

Applies to the default request handler and takes precedence over clientConfig.requestHandler.requestTimeout. Ignored when clientConfig.requestHandler is a constructed handler instance, whose own timeouts apply.

120000

optional apiKey?: string;

Defined in: src/models/bedrock.ts:371

Amazon Bedrock API key for bearer token authentication. When provided, requests use the API key instead of SigV4 signing.

https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys.html


optional modelId?: string;

Defined in: src/models/model.ts:183

The model identifier. This typically specifies which model to use from the provider’s catalog.

BedrockModelConfig.modelId


optional contextWindowLimit?: number;

Defined in: src/models/model.ts:216

Maximum context window size in tokens for the model.

This value represents the total token capacity shared between input and output. When not provided, it is automatically resolved from a built-in lookup table based on the configured model ID. An explicit value always takes precedence.

When modelId is changed via updateConfig(), this value is automatically re-resolved if it was initially auto-populated. Explicitly set values are preserved.

BedrockModelConfig.contextWindowLimit