OptionalmaxMaximum number of tokens to generate in the response.
OptionaltemperatureControls randomness in generation.
OptionaltopControls diversity via nucleus sampling.
OptionalstopArray of sequences that will stop generation when encountered.
OptionalcacheCache point type for the system prompt.
OptionalcacheCache point type for tools.
OptionaladditionalAdditional fields to include in the Bedrock request.
OptionaladditionalAdditional response field paths to extract from the Bedrock response.
OptionaladditionalAdditional arguments to pass through to the Bedrock Converse API.
OptionalstreamWhether or not to stream responses from the model.
This will use the ConverseStream API instead of the Converse API.
OptionalincludeFlag to include status field in tool results.
true: Always include status fieldfalse: Never include status field'auto': Automatically determine based on model ID (default)OptionalmodelThe model identifier. This typically specifies which model to use from the provider's catalog.
Configuration interface for AWS Bedrock model provider.
Extends BaseModelConfig with Bedrock-specific configuration options for model parameters, caching, and additional request/response fields.
Example