rboto-bedrock

rboto is an independent project maintained by Ferrumio. It is not affiliated with, sponsored by, or endorsed by Amazon Web Services (AWS).

Preview (Alpha). rboto is under active development. APIs may change between releases.

rboto provides an async-only, typed Python client for Amazon Bedrock, powered by Rust. This package contains BedrockClient and 108 operations.

Installation

Requires Python 3.12 or newer and a native wheel for your Python version and platform.

python -m pip install "rboto[bedrock]"

You can also install rboto-bedrock directly; it installs the matching rboto package. Only the selected service is installed.

These are the package names to use when a release is available on your package index. If your index has no release yet, follow the source installation instructions.

Usage

Configure credentials through your environment, shared profile, or workload role. The example uses us-east-1; select a region where your service and resources are available. Resource names, identifiers, input files, and model IDs in the example are placeholders to replace with your own.

import asyncio

from rboto import BedrockClient


async def main() -> None:
    client = BedrockClient(region="us-east-1")
    response = await client.list_foundation_models(by_output_modality="TEXT")
    for model in response.model_summaries or []:
        print(model.model_id, model.model_name)


if __name__ == "__main__":
    asyncio.run(main())

In an application with an event loop, call await main() instead of asyncio.run(main()). Reuse the client across calls. Constructing a client does not send a request.

API conventions

• Import the client with from rboto import BedrockClient.

• Every operation is asynchronous: use await client.method(...).

• Operation arguments are keyword-only and use the Python names listed below.

• Structured inputs use typed dictionaries and tagged unions from rboto_bedrock.types.

• Regular responses expose typed attributes; response.to_dict() converts them to a dictionary.

• Event-stream responses may be typed dictionaries containing async iterators. Follow the declared return type; consume event streams with async for.

• Byte streams are consumed asynchronously. await stream.read() buffers the complete body; iterate the stream when processing a large response.

• Direct operation calls return one page.

• Use async for page in client.paginators.method(...) for supported paginated operations. Paginators accept the same typed arguments as the corresponding client method.

• Catch modeled exceptions from rboto_bedrock.exceptions. Their error_code, message, and operation_name identify service failures.

Clients also accept profile, endpoint_url, or shared Session settings. See configuration, errors, and streaming.

Operations

This is the complete operation catalog for this generated package. “Required arguments” lists arguments without defaults in the Python signature. Service-side conditions may require additional arguments. Each method links to its complete signature, including optional arguments. Nested input definitions are in rboto_bedrock.types; native response definitions are in the package's _native.pyi.

Method	Required arguments	Return type
batch_delete_advanced_prompt_optimization_job	job_identifiers: Sequence[str]	BatchDeleteAdvancedPromptOptimizationJobOutput
batch_delete_evaluation_job	job_identifiers: Sequence[str]	BatchDeleteEvaluationJobOutput
cancel_automated_reasoning_policy_build_workflow	policy_arn: str, build_workflow_id: str	CancelAutomatedReasoningPolicyBuildWorkflowOutput
create_advanced_prompt_optimization_job	job_name: str, input_config: AdvancedPromptOptimizationInputConfig, output_config: AdvancedPromptOptimizationOutputConfig, model_configurations: Sequence[ModelConfiguration]	CreateAdvancedPromptOptimizationJobOutput
create_automated_reasoning_policy	name: str	CreateAutomatedReasoningPolicyOutput
create_automated_reasoning_policy_test_case	policy_arn: str, guard_content: str, expected_aggregated_findings_result: AutomatedReasoningCheckResult	CreateAutomatedReasoningPolicyTestCaseOutput
create_automated_reasoning_policy_version	policy_arn: str, last_updated_definition_hash: str	CreateAutomatedReasoningPolicyVersionOutput
create_custom_model	model_name: str	CreateCustomModelOutput
create_custom_model_deployment	model_deployment_name: str, model_arn: str	CreateCustomModelDeploymentOutput
create_evaluation_job	job_name: str, role_arn: str, evaluation_config: EvaluationConfig, inference_config: EvaluationInferenceConfig, output_data_config: EvaluationOutputDataConfig	CreateEvaluationJobOutput
create_foundation_model_agreement	offer_token: str, model_id: str	CreateFoundationModelAgreementOutput
create_guardrail	name: str, blocked_input_messaging: str, blocked_outputs_messaging: str	CreateGuardrailOutput
create_guardrail_version	guardrail_identifier: str	CreateGuardrailVersionOutput
create_inference_profile	inference_profile_name: str, model_source: InferenceProfileModelSource	CreateInferenceProfileOutput
create_marketplace_model_endpoint	model_source_identifier: str, endpoint_config: EndpointConfig, endpoint_name: str	CreateMarketplaceModelEndpointOutput
create_model_copy_job	source_model_arn: str, target_model_name: str	CreateModelCopyJobOutput
create_model_customization_job	job_name: str, custom_model_name: str, role_arn: str, base_model_identifier: str, training_data_config: TrainingDataConfig, output_data_config: OutputDataConfig	CreateModelCustomizationJobOutput
create_model_import_job	job_name: str, imported_model_name: str, role_arn: str, model_data_source: ModelDataSource	CreateModelImportJobOutput
create_model_invocation_job	job_name: str, role_arn: str, model_id: str, input_data_config: ModelInvocationJobInputDataConfig, output_data_config: ModelInvocationJobOutputDataConfig	CreateModelInvocationJobOutput
create_prompt_router	prompt_router_name: str, models: Sequence[PromptRouterTargetModel], routing_criteria: RoutingCriteria, fallback_model: PromptRouterTargetModel	CreatePromptRouterOutput
create_provisioned_model_throughput	model_units: int, provisioned_model_name: str, model_id: str	CreateProvisionedModelThroughputOutput
delete_automated_reasoning_policy	policy_arn: str	DeleteAutomatedReasoningPolicyOutput
delete_automated_reasoning_policy_build_workflow	policy_arn: str, build_workflow_id: str, last_updated_at: str	DeleteAutomatedReasoningPolicyBuildWorkflowOutput
delete_automated_reasoning_policy_test_case	policy_arn: str, test_case_id: str, last_updated_at: str	DeleteAutomatedReasoningPolicyTestCaseOutput
delete_custom_model	model_identifier: str	DeleteCustomModelOutput
delete_custom_model_deployment	custom_model_deployment_identifier: str	DeleteCustomModelDeploymentOutput
delete_enforced_guardrail_configuration	config_id: str	DeleteEnforcedGuardrailConfigurationOutput
delete_foundation_model_agreement	model_id: str	DeleteFoundationModelAgreementOutput
delete_guardrail	guardrail_identifier: str	DeleteGuardrailOutput
delete_imported_model	model_identifier: str	DeleteImportedModelOutput
delete_inference_profile	inference_profile_identifier: str	DeleteInferenceProfileOutput
delete_marketplace_model_endpoint	endpoint_arn: str	DeleteMarketplaceModelEndpointOutput
delete_model_invocation_logging_configuration	None	DeleteModelInvocationLoggingConfigurationOutput
delete_prompt_router	prompt_router_arn: str	DeletePromptRouterOutput
delete_provisioned_model_throughput	provisioned_model_id: str	DeleteProvisionedModelThroughputOutput
delete_resource_policy	resource_arn: str	DeleteResourcePolicyOutput
deregister_marketplace_model_endpoint	endpoint_arn: str	DeregisterMarketplaceModelEndpointOutput
export_automated_reasoning_policy_version	policy_arn: str	ExportAutomatedReasoningPolicyVersionOutput
get_account_data_retention	None	GetAccountDataRetentionOutput
get_advanced_prompt_optimization_job	job_identifier: str	GetAdvancedPromptOptimizationJobOutput
get_automated_reasoning_policy	policy_arn: str	GetAutomatedReasoningPolicyOutput
get_automated_reasoning_policy_annotations	policy_arn: str, build_workflow_id: str	GetAutomatedReasoningPolicyAnnotationsOutput
get_automated_reasoning_policy_build_workflow	policy_arn: str, build_workflow_id: str	GetAutomatedReasoningPolicyBuildWorkflowOutput
get_automated_reasoning_policy_build_workflow_result_assets	policy_arn: str, build_workflow_id: str, asset_type: AutomatedReasoningPolicyBuildResultAssetType	GetAutomatedReasoningPolicyBuildWorkflowResultAssetsOutput
get_automated_reasoning_policy_next_scenario	policy_arn: str, build_workflow_id: str	GetAutomatedReasoningPolicyNextScenarioOutput
get_automated_reasoning_policy_test_case	policy_arn: str, test_case_id: str	GetAutomatedReasoningPolicyTestCaseOutput
get_automated_reasoning_policy_test_result	policy_arn: str, build_workflow_id: str, test_case_id: str	GetAutomatedReasoningPolicyTestResultOutput
get_custom_model	model_identifier: str	GetCustomModelOutput
get_custom_model_deployment	custom_model_deployment_identifier: str	GetCustomModelDeploymentOutput
get_evaluation_job	job_identifier: str	GetEvaluationJobOutput
get_foundation_model	model_identifier: str	GetFoundationModelOutput
get_foundation_model_availability	model_id: str	GetFoundationModelAvailabilityOutput
get_guardrail	guardrail_identifier: str	GetGuardrailOutput
get_imported_model	model_identifier: str	GetImportedModelOutput
get_inference_profile	inference_profile_identifier: str	GetInferenceProfileOutput
get_marketplace_model_endpoint	endpoint_arn: str	GetMarketplaceModelEndpointOutput
get_model_copy_job	job_arn: str	GetModelCopyJobOutput
get_model_customization_job	job_identifier: str	GetModelCustomizationJobOutput
get_model_import_job	job_identifier: str	GetModelImportJobOutput
get_model_invocation_job	job_identifier: str	GetModelInvocationJobOutput
get_model_invocation_logging_configuration	None	GetModelInvocationLoggingConfigurationOutput
get_prompt_router	prompt_router_arn: str	GetPromptRouterOutput
get_provisioned_model_throughput	provisioned_model_id: str	GetProvisionedModelThroughputOutput
get_resource_policy	resource_arn: str	GetResourcePolicyOutput
get_use_case_for_model_access	None	GetUseCaseForModelAccessOutput
list_advanced_prompt_optimization_jobs	None	ListAdvancedPromptOptimizationJobsOutput
list_automated_reasoning_policies	None	ListAutomatedReasoningPoliciesOutput
list_automated_reasoning_policy_build_workflows	policy_arn: str	ListAutomatedReasoningPolicyBuildWorkflowsOutput
list_automated_reasoning_policy_test_cases	policy_arn: str	ListAutomatedReasoningPolicyTestCasesOutput
list_automated_reasoning_policy_test_results	policy_arn: str, build_workflow_id: str	ListAutomatedReasoningPolicyTestResultsOutput
list_custom_model_deployments	None	ListCustomModelDeploymentsOutput
list_custom_models	None	ListCustomModelsOutput
list_enforced_guardrails_configuration	None	ListEnforcedGuardrailsConfigurationOutput
list_evaluation_jobs	None	ListEvaluationJobsOutput
list_foundation_model_agreement_offers	model_id: str	ListFoundationModelAgreementOffersOutput
list_foundation_models	None	ListFoundationModelsOutput
list_guardrails	None	ListGuardrailsOutput
list_imported_models	None	ListImportedModelsOutput
list_inference_profiles	None	ListInferenceProfilesOutput
list_marketplace_model_endpoints	None	ListMarketplaceModelEndpointsOutput
list_model_copy_jobs	None	ListModelCopyJobsOutput
list_model_customization_jobs	None	ListModelCustomizationJobsOutput
list_model_import_jobs	None	ListModelImportJobsOutput
list_model_invocation_jobs	None	ListModelInvocationJobsOutput
list_prompt_routers	None	ListPromptRoutersOutput
list_provisioned_model_throughputs	None	ListProvisionedModelThroughputsOutput
list_tags_for_resource	resource_arn: str	ListTagsForResourceOutput
put_account_data_retention	mode: DataRetentionMode	PutAccountDataRetentionOutput
put_enforced_guardrail_configuration	guardrail_inference_config: AccountEnforcedGuardrailInferenceInputConfiguration	PutEnforcedGuardrailConfigurationOutput
put_model_invocation_logging_configuration	logging_config: LoggingConfig	PutModelInvocationLoggingConfigurationOutput
put_resource_policy	resource_arn: str, resource_policy: str	PutResourcePolicyOutput
put_use_case_for_model_access	form_data: bytes	PutUseCaseForModelAccessOutput
register_marketplace_model_endpoint	endpoint_identifier: str, model_source_identifier: str	RegisterMarketplaceModelEndpointOutput
start_automated_reasoning_policy_build_workflow	policy_arn: str, build_workflow_type: AutomatedReasoningPolicyBuildWorkflowType, source_content: AutomatedReasoningPolicyBuildWorkflowSource	StartAutomatedReasoningPolicyBuildWorkflowOutput
start_automated_reasoning_policy_test_workflow	policy_arn: str, build_workflow_id: str	StartAutomatedReasoningPolicyTestWorkflowOutput
stop_advanced_prompt_optimization_job	job_identifier: str	StopAdvancedPromptOptimizationJobOutput
stop_evaluation_job	job_identifier: str	StopEvaluationJobOutput
stop_model_customization_job	job_identifier: str	StopModelCustomizationJobOutput
stop_model_invocation_job	job_identifier: str	StopModelInvocationJobOutput
tag_resource	resource_arn: str, tags: Sequence[Tag]	TagResourceOutput
untag_resource	resource_arn: str, tag_keys: Sequence[str]	UntagResourceOutput
update_automated_reasoning_policy	policy_arn: str, policy_definition: AutomatedReasoningPolicyDefinition	UpdateAutomatedReasoningPolicyOutput
update_automated_reasoning_policy_annotations	policy_arn: str, build_workflow_id: str, annotations: Sequence[AutomatedReasoningPolicyAnnotation], last_updated_annotation_set_hash: str	UpdateAutomatedReasoningPolicyAnnotationsOutput
update_automated_reasoning_policy_test_case	policy_arn: str, test_case_id: str, guard_content: str, last_updated_at: str, expected_aggregated_findings_result: AutomatedReasoningCheckResult	UpdateAutomatedReasoningPolicyTestCaseOutput
update_custom_model_deployment	model_arn: str, custom_model_deployment_identifier: str	UpdateCustomModelDeploymentOutput
update_guardrail	guardrail_identifier: str, name: str, blocked_input_messaging: str, blocked_outputs_messaging: str	UpdateGuardrailOutput
update_marketplace_model_endpoint	endpoint_arn: str, endpoint_config: EndpointConfig	UpdateMarketplaceModelEndpointOutput
update_provisioned_model_throughput	provisioned_model_id: str	UpdateProvisionedModelThroughputOutput

Complete signatures

batch_delete_advanced_prompt_optimization_job

async def batch_delete_advanced_prompt_optimization_job(
    *,
    job_identifiers: Sequence[str],
) -> BatchDeleteAdvancedPromptOptimizationJobOutput: ...

batch_delete_evaluation_job

async def batch_delete_evaluation_job(
    *,
    job_identifiers: Sequence[str],
) -> BatchDeleteEvaluationJobOutput: ...

cancel_automated_reasoning_policy_build_workflow

async def cancel_automated_reasoning_policy_build_workflow(
    *,
    policy_arn: str,
    build_workflow_id: str,
) -> CancelAutomatedReasoningPolicyBuildWorkflowOutput: ...

create_advanced_prompt_optimization_job

async def create_advanced_prompt_optimization_job(
    *,
    job_name: str,
    input_config: AdvancedPromptOptimizationInputConfig,
    output_config: AdvancedPromptOptimizationOutputConfig,
    model_configurations: Sequence[ModelConfiguration],
    job_description: str | None = None,
    client_token: str | None = None,
    encryption_key_arn: str | None = None,
    tags: Sequence[Tag] | None = None,
) -> CreateAdvancedPromptOptimizationJobOutput: ...

create_automated_reasoning_policy

async def create_automated_reasoning_policy(
    *,
    name: str,
    description: str | None = None,
    client_request_token: str | None = None,
    policy_definition: AutomatedReasoningPolicyDefinition | None = None,
    kms_key_id: str | None = None,
    tags: Sequence[Tag] | None = None,
) -> CreateAutomatedReasoningPolicyOutput: ...

create_automated_reasoning_policy_test_case

async def create_automated_reasoning_policy_test_case(
    *,
    policy_arn: str,
    guard_content: str,
    expected_aggregated_findings_result: AutomatedReasoningCheckResult,
    query_content: str | None = None,
    client_request_token: str | None = None,
    confidence_threshold: float | None = None,
) -> CreateAutomatedReasoningPolicyTestCaseOutput: ...

create_automated_reasoning_policy_version

async def create_automated_reasoning_policy_version(
    *,
    policy_arn: str,
    last_updated_definition_hash: str,
    client_request_token: str | None = None,
    tags: Sequence[Tag] | None = None,
) -> CreateAutomatedReasoningPolicyVersionOutput: ...

create_custom_model

async def create_custom_model(
    *,
    model_name: str,
    model_source_config: ModelDataSource | None = None,
    custom_model_data_source: CustomModelDataSource | None = None,
    model_kms_key_arn: str | None = None,
    role_arn: str | None = None,
    model_tags: Sequence[Tag] | None = None,
    client_request_token: str | None = None,
) -> CreateCustomModelOutput: ...

create_custom_model_deployment

async def create_custom_model_deployment(
    *,
    model_deployment_name: str,
    model_arn: str,
    description: str | None = None,
    tags: Sequence[Tag] | None = None,
    client_request_token: str | None = None,
) -> CreateCustomModelDeploymentOutput: ...

create_evaluation_job

async def create_evaluation_job(
    *,
    job_name: str,
    role_arn: str,
    evaluation_config: EvaluationConfig,
    inference_config: EvaluationInferenceConfig,
    output_data_config: EvaluationOutputDataConfig,
    job_description: str | None = None,
    client_request_token: str | None = None,
    customer_encryption_key_id: str | None = None,
    job_tags: Sequence[Tag] | None = None,
    application_type: ApplicationType | None = None,
) -> CreateEvaluationJobOutput: ...

create_foundation_model_agreement

async def create_foundation_model_agreement(
    *,
    offer_token: str,
    model_id: str,
) -> CreateFoundationModelAgreementOutput: ...

create_guardrail

async def create_guardrail(
    *,
    name: str,
    blocked_input_messaging: str,
    blocked_outputs_messaging: str,
    description: str | None = None,
    topic_policy_config: GuardrailTopicPolicyConfig | None = None,
    content_policy_config: GuardrailContentPolicyConfig | None = None,
    word_policy_config: GuardrailWordPolicyConfig | None = None,
    sensitive_information_policy_config: GuardrailSensitiveInformationPolicyConfig | None = None,
    contextual_grounding_policy_config: GuardrailContextualGroundingPolicyConfig | None = None,
    automated_reasoning_policy_config: GuardrailAutomatedReasoningPolicyConfig | None = None,
    cross_region_config: GuardrailCrossRegionConfig | None = None,
    kms_key_id: str | None = None,
    tags: Sequence[Tag] | None = None,
    client_request_token: str | None = None,
) -> CreateGuardrailOutput: ...

create_guardrail_version

async def create_guardrail_version(
    *,
    guardrail_identifier: str,
    description: str | None = None,
    client_request_token: str | None = None,
) -> CreateGuardrailVersionOutput: ...

create_inference_profile

async def create_inference_profile(
    *,
    inference_profile_name: str,
    model_source: InferenceProfileModelSource,
    description: str | None = None,
    client_request_token: str | None = None,
    tags: Sequence[Tag] | None = None,
) -> CreateInferenceProfileOutput: ...

create_marketplace_model_endpoint

async def create_marketplace_model_endpoint(
    *,
    model_source_identifier: str,
    endpoint_config: EndpointConfig,
    endpoint_name: str,
    accept_eula: bool | None = None,
    client_request_token: str | None = None,
    tags: Sequence[Tag] | None = None,
) -> CreateMarketplaceModelEndpointOutput: ...

create_model_copy_job

async def create_model_copy_job(
    *,
    source_model_arn: str,
    target_model_name: str,
    model_kms_key_id: str | None = None,
    target_model_tags: Sequence[Tag] | None = None,
    client_request_token: str | None = None,
) -> CreateModelCopyJobOutput: ...

create_model_customization_job

async def create_model_customization_job(
    *,
    job_name: str,
    custom_model_name: str,
    role_arn: str,
    base_model_identifier: str,
    training_data_config: TrainingDataConfig,
    output_data_config: OutputDataConfig,
    client_request_token: str | None = None,
    customization_type: CustomizationType | None = None,
    custom_model_kms_key_id: str | None = None,
    job_tags: Sequence[Tag] | None = None,
    custom_model_tags: Sequence[Tag] | None = None,
    validation_data_config: ValidationDataConfig | None = None,
    hyper_parameters: dict[str, str] | None = None,
    vpc_config: VpcConfig | None = None,
    customization_config: CustomizationConfig | None = None,
) -> CreateModelCustomizationJobOutput: ...

create_model_import_job

async def create_model_import_job(
    *,
    job_name: str,
    imported_model_name: str,
    role_arn: str,
    model_data_source: ModelDataSource,
    job_tags: Sequence[Tag] | None = None,
    imported_model_tags: Sequence[Tag] | None = None,
    client_request_token: str | None = None,
    vpc_config: VpcConfig | None = None,
    imported_model_kms_key_id: str | None = None,
) -> CreateModelImportJobOutput: ...

create_model_invocation_job

async def create_model_invocation_job(
    *,
    job_name: str,
    role_arn: str,
    model_id: str,
    input_data_config: ModelInvocationJobInputDataConfig,
    output_data_config: ModelInvocationJobOutputDataConfig,
    client_request_token: str | None = None,
    vpc_config: VpcConfig | None = None,
    timeout_duration_in_hours: int | None = None,
    tags: Sequence[Tag] | None = None,
    model_invocation_type: ModelInvocationType | None = None,
) -> CreateModelInvocationJobOutput: ...

create_prompt_router

async def create_prompt_router(
    *,
    prompt_router_name: str,
    models: Sequence[PromptRouterTargetModel],
    routing_criteria: RoutingCriteria,
    fallback_model: PromptRouterTargetModel,
    client_request_token: str | None = None,
    description: str | None = None,
    tags: Sequence[Tag] | None = None,
) -> CreatePromptRouterOutput: ...

create_provisioned_model_throughput

async def create_provisioned_model_throughput(
    *,
    model_units: int,
    provisioned_model_name: str,
    model_id: str,
    client_request_token: str | None = None,
    commitment_duration: CommitmentDuration | None = None,
    tags: Sequence[Tag] | None = None,
) -> CreateProvisionedModelThroughputOutput: ...

delete_automated_reasoning_policy

async def delete_automated_reasoning_policy(
    *,
    policy_arn: str,
    force: bool | None = None,
) -> DeleteAutomatedReasoningPolicyOutput: ...

delete_automated_reasoning_policy_build_workflow

async def delete_automated_reasoning_policy_build_workflow(
    *,
    policy_arn: str,
    build_workflow_id: str,
    last_updated_at: str,
) -> DeleteAutomatedReasoningPolicyBuildWorkflowOutput: ...

delete_automated_reasoning_policy_test_case

async def delete_automated_reasoning_policy_test_case(
    *,
    policy_arn: str,
    test_case_id: str,
    last_updated_at: str,
) -> DeleteAutomatedReasoningPolicyTestCaseOutput: ...

delete_custom_model

async def delete_custom_model(
    *,
    model_identifier: str,
) -> DeleteCustomModelOutput: ...

delete_custom_model_deployment

async def delete_custom_model_deployment(
    *,
    custom_model_deployment_identifier: str,
) -> DeleteCustomModelDeploymentOutput: ...

delete_enforced_guardrail_configuration

async def delete_enforced_guardrail_configuration(
    *,
    config_id: str,
) -> DeleteEnforcedGuardrailConfigurationOutput: ...

delete_foundation_model_agreement

async def delete_foundation_model_agreement(
    *,
    model_id: str,
) -> DeleteFoundationModelAgreementOutput: ...

delete_guardrail

async def delete_guardrail(
    *,
    guardrail_identifier: str,
    guardrail_version: str | None = None,
) -> DeleteGuardrailOutput: ...

delete_imported_model

async def delete_imported_model(
    *,
    model_identifier: str,
) -> DeleteImportedModelOutput: ...

delete_inference_profile

async def delete_inference_profile(
    *,
    inference_profile_identifier: str,
) -> DeleteInferenceProfileOutput: ...

delete_marketplace_model_endpoint

async def delete_marketplace_model_endpoint(
    *,
    endpoint_arn: str,
) -> DeleteMarketplaceModelEndpointOutput: ...

delete_model_invocation_logging_configuration

async def delete_model_invocation_logging_configuration() -> DeleteModelInvocationLoggingConfigurationOutput: ...

delete_prompt_router

async def delete_prompt_router(
    *,
    prompt_router_arn: str,
) -> DeletePromptRouterOutput: ...

delete_provisioned_model_throughput

async def delete_provisioned_model_throughput(
    *,
    provisioned_model_id: str,
) -> DeleteProvisionedModelThroughputOutput: ...

delete_resource_policy

async def delete_resource_policy(
    *,
    resource_arn: str,
) -> DeleteResourcePolicyOutput: ...

deregister_marketplace_model_endpoint

async def deregister_marketplace_model_endpoint(
    *,
    endpoint_arn: str,
) -> DeregisterMarketplaceModelEndpointOutput: ...

export_automated_reasoning_policy_version

async def export_automated_reasoning_policy_version(
    *,
    policy_arn: str,
) -> ExportAutomatedReasoningPolicyVersionOutput: ...

get_account_data_retention

async def get_account_data_retention() -> GetAccountDataRetentionOutput: ...

get_advanced_prompt_optimization_job

async def get_advanced_prompt_optimization_job(
    *,
    job_identifier: str,
) -> GetAdvancedPromptOptimizationJobOutput: ...

get_automated_reasoning_policy

async def get_automated_reasoning_policy(
    *,
    policy_arn: str,
) -> GetAutomatedReasoningPolicyOutput: ...

get_automated_reasoning_policy_annotations

async def get_automated_reasoning_policy_annotations(
    *,
    policy_arn: str,
    build_workflow_id: str,
) -> GetAutomatedReasoningPolicyAnnotationsOutput: ...

get_automated_reasoning_policy_build_workflow

async def get_automated_reasoning_policy_build_workflow(
    *,
    policy_arn: str,
    build_workflow_id: str,
) -> GetAutomatedReasoningPolicyBuildWorkflowOutput: ...

get_automated_reasoning_policy_build_workflow_result_assets

async def get_automated_reasoning_policy_build_workflow_result_assets(
    *,
    policy_arn: str,
    build_workflow_id: str,
    asset_type: AutomatedReasoningPolicyBuildResultAssetType,
    asset_id: str | None = None,
) -> GetAutomatedReasoningPolicyBuildWorkflowResultAssetsOutput: ...

get_automated_reasoning_policy_next_scenario

async def get_automated_reasoning_policy_next_scenario(
    *,
    policy_arn: str,
    build_workflow_id: str,
) -> GetAutomatedReasoningPolicyNextScenarioOutput: ...

get_automated_reasoning_policy_test_case

async def get_automated_reasoning_policy_test_case(
    *,
    policy_arn: str,
    test_case_id: str,
) -> GetAutomatedReasoningPolicyTestCaseOutput: ...

get_automated_reasoning_policy_test_result

async def get_automated_reasoning_policy_test_result(
    *,
    policy_arn: str,
    build_workflow_id: str,
    test_case_id: str,
) -> GetAutomatedReasoningPolicyTestResultOutput: ...

get_custom_model

async def get_custom_model(
    *,
    model_identifier: str,
) -> GetCustomModelOutput: ...

get_custom_model_deployment

async def get_custom_model_deployment(
    *,
    custom_model_deployment_identifier: str,
) -> GetCustomModelDeploymentOutput: ...

get_evaluation_job

async def get_evaluation_job(
    *,
    job_identifier: str,
) -> GetEvaluationJobOutput: ...

get_foundation_model

async def get_foundation_model(
    *,
    model_identifier: str,
) -> GetFoundationModelOutput: ...

get_foundation_model_availability

async def get_foundation_model_availability(
    *,
    model_id: str,
) -> GetFoundationModelAvailabilityOutput: ...

get_guardrail

async def get_guardrail(
    *,
    guardrail_identifier: str,
    guardrail_version: str | None = None,
) -> GetGuardrailOutput: ...

get_imported_model

async def get_imported_model(
    *,
    model_identifier: str,
) -> GetImportedModelOutput: ...

get_inference_profile

async def get_inference_profile(
    *,
    inference_profile_identifier: str,
) -> GetInferenceProfileOutput: ...

get_marketplace_model_endpoint

async def get_marketplace_model_endpoint(
    *,
    endpoint_arn: str,
) -> GetMarketplaceModelEndpointOutput: ...

get_model_copy_job

async def get_model_copy_job(
    *,
    job_arn: str,
) -> GetModelCopyJobOutput: ...

get_model_customization_job

async def get_model_customization_job(
    *,
    job_identifier: str,
) -> GetModelCustomizationJobOutput: ...

get_model_import_job

async def get_model_import_job(
    *,
    job_identifier: str,
) -> GetModelImportJobOutput: ...

get_model_invocation_job

async def get_model_invocation_job(
    *,
    job_identifier: str,
) -> GetModelInvocationJobOutput: ...

get_model_invocation_logging_configuration

async def get_model_invocation_logging_configuration() -> GetModelInvocationLoggingConfigurationOutput: ...

get_prompt_router

async def get_prompt_router(
    *,
    prompt_router_arn: str,
) -> GetPromptRouterOutput: ...

get_provisioned_model_throughput

async def get_provisioned_model_throughput(
    *,
    provisioned_model_id: str,
) -> GetProvisionedModelThroughputOutput: ...

get_resource_policy

async def get_resource_policy(
    *,
    resource_arn: str,
) -> GetResourcePolicyOutput: ...

get_use_case_for_model_access

async def get_use_case_for_model_access() -> GetUseCaseForModelAccessOutput: ...

list_advanced_prompt_optimization_jobs

async def list_advanced_prompt_optimization_jobs(
    *,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortJobsBy | None = None,
    sort_order: SortOrder | None = None,
) -> ListAdvancedPromptOptimizationJobsOutput: ...

Also available as client.paginators.list_advanced_prompt_optimization_jobs(...), returning an async iterator of the response type above.

list_automated_reasoning_policies

async def list_automated_reasoning_policies(
    *,
    policy_arn: str | None = None,
    next_token: str | None = None,
    max_results: int | None = None,
) -> ListAutomatedReasoningPoliciesOutput: ...

Also available as client.paginators.list_automated_reasoning_policies(...), returning an async iterator of the response type above.

list_automated_reasoning_policy_build_workflows

async def list_automated_reasoning_policy_build_workflows(
    *,
    policy_arn: str,
    next_token: str | None = None,
    max_results: int | None = None,
) -> ListAutomatedReasoningPolicyBuildWorkflowsOutput: ...

Also available as client.paginators.list_automated_reasoning_policy_build_workflows(...), returning an async iterator of the response type above.

list_automated_reasoning_policy_test_cases

async def list_automated_reasoning_policy_test_cases(
    *,
    policy_arn: str,
    next_token: str | None = None,
    max_results: int | None = None,
) -> ListAutomatedReasoningPolicyTestCasesOutput: ...

Also available as client.paginators.list_automated_reasoning_policy_test_cases(...), returning an async iterator of the response type above.

list_automated_reasoning_policy_test_results

async def list_automated_reasoning_policy_test_results(
    *,
    policy_arn: str,
    build_workflow_id: str,
    next_token: str | None = None,
    max_results: int | None = None,
) -> ListAutomatedReasoningPolicyTestResultsOutput: ...

Also available as client.paginators.list_automated_reasoning_policy_test_results(...), returning an async iterator of the response type above.

list_custom_model_deployments

async def list_custom_model_deployments(
    *,
    created_before: str | None = None,
    created_after: str | None = None,
    name_contains: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortModelsBy | None = None,
    sort_order: SortOrder | None = None,
    status_equals: CustomModelDeploymentStatus | None = None,
    model_arn_equals: str | None = None,
) -> ListCustomModelDeploymentsOutput: ...

Also available as client.paginators.list_custom_model_deployments(...), returning an async iterator of the response type above.

list_custom_models

async def list_custom_models(
    *,
    creation_time_before: str | None = None,
    creation_time_after: str | None = None,
    name_contains: str | None = None,
    base_model_arn_equals: str | None = None,
    foundation_model_arn_equals: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortModelsBy | None = None,
    sort_order: SortOrder | None = None,
    is_owned: bool | None = None,
    model_status: ModelStatus | None = None,
) -> ListCustomModelsOutput: ...

Also available as client.paginators.list_custom_models(...), returning an async iterator of the response type above.

list_enforced_guardrails_configuration

async def list_enforced_guardrails_configuration(
    *,
    next_token: str | None = None,
) -> ListEnforcedGuardrailsConfigurationOutput: ...

Also available as client.paginators.list_enforced_guardrails_configuration(...), returning an async iterator of the response type above.

list_evaluation_jobs

async def list_evaluation_jobs(
    *,
    creation_time_after: str | None = None,
    creation_time_before: str | None = None,
    status_equals: EvaluationJobStatus | None = None,
    application_type_equals: ApplicationType | None = None,
    name_contains: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortJobsBy | None = None,
    sort_order: SortOrder | None = None,
) -> ListEvaluationJobsOutput: ...

Also available as client.paginators.list_evaluation_jobs(...), returning an async iterator of the response type above.

list_foundation_model_agreement_offers

async def list_foundation_model_agreement_offers(
    *,
    model_id: str,
    offer_type: OfferType | None = None,
) -> ListFoundationModelAgreementOffersOutput: ...

list_foundation_models

async def list_foundation_models(
    *,
    by_provider: str | None = None,
    by_customization_type: ModelCustomization | None = None,
    by_output_modality: ModelModality | None = None,
    by_inference_type: InferenceType | None = None,
) -> ListFoundationModelsOutput: ...

list_guardrails

async def list_guardrails(
    *,
    guardrail_identifier: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
) -> ListGuardrailsOutput: ...

Also available as client.paginators.list_guardrails(...), returning an async iterator of the response type above.

list_imported_models

async def list_imported_models(
    *,
    creation_time_before: str | None = None,
    creation_time_after: str | None = None,
    name_contains: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortModelsBy | None = None,
    sort_order: SortOrder | None = None,
) -> ListImportedModelsOutput: ...

Also available as client.paginators.list_imported_models(...), returning an async iterator of the response type above.

list_inference_profiles

async def list_inference_profiles(
    *,
    max_results: int | None = None,
    next_token: str | None = None,
    type_equals: InferenceProfileType | None = None,
) -> ListInferenceProfilesOutput: ...

Also available as client.paginators.list_inference_profiles(...), returning an async iterator of the response type above.

list_marketplace_model_endpoints

async def list_marketplace_model_endpoints(
    *,
    max_results: int | None = None,
    next_token: str | None = None,
    model_source_equals: str | None = None,
) -> ListMarketplaceModelEndpointsOutput: ...

Also available as client.paginators.list_marketplace_model_endpoints(...), returning an async iterator of the response type above.

list_model_copy_jobs

async def list_model_copy_jobs(
    *,
    creation_time_after: str | None = None,
    creation_time_before: str | None = None,
    status_equals: ModelCopyJobStatus | None = None,
    source_account_equals: str | None = None,
    source_model_arn_equals: str | None = None,
    target_model_name_contains: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortJobsBy | None = None,
    sort_order: SortOrder | None = None,
) -> ListModelCopyJobsOutput: ...

Also available as client.paginators.list_model_copy_jobs(...), returning an async iterator of the response type above.

list_model_customization_jobs

async def list_model_customization_jobs(
    *,
    creation_time_after: str | None = None,
    creation_time_before: str | None = None,
    status_equals: FineTuningJobStatus | None = None,
    name_contains: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortJobsBy | None = None,
    sort_order: SortOrder | None = None,
) -> ListModelCustomizationJobsOutput: ...

Also available as client.paginators.list_model_customization_jobs(...), returning an async iterator of the response type above.

list_model_import_jobs

async def list_model_import_jobs(
    *,
    creation_time_after: str | None = None,
    creation_time_before: str | None = None,
    status_equals: ModelImportJobStatus | None = None,
    name_contains: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortJobsBy | None = None,
    sort_order: SortOrder | None = None,
) -> ListModelImportJobsOutput: ...

Also available as client.paginators.list_model_import_jobs(...), returning an async iterator of the response type above.

list_model_invocation_jobs

async def list_model_invocation_jobs(
    *,
    submit_time_after: str | None = None,
    submit_time_before: str | None = None,
    status_equals: ModelInvocationJobStatus | None = None,
    name_contains: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortJobsBy | None = None,
    sort_order: SortOrder | None = None,
) -> ListModelInvocationJobsOutput: ...

Also available as client.paginators.list_model_invocation_jobs(...), returning an async iterator of the response type above.

list_prompt_routers

async def list_prompt_routers(
    *,
    max_results: int | None = None,
    next_token: str | None = None,
    type: PromptRouterType | None = None,
) -> ListPromptRoutersOutput: ...

Also available as client.paginators.list_prompt_routers(...), returning an async iterator of the response type above.

list_provisioned_model_throughputs

async def list_provisioned_model_throughputs(
    *,
    creation_time_after: str | None = None,
    creation_time_before: str | None = None,
    status_equals: ProvisionedModelStatus | None = None,
    model_arn_equals: str | None = None,
    name_contains: str | None = None,
    max_results: int | None = None,
    next_token: str | None = None,
    sort_by: SortByProvisionedModels | None = None,
    sort_order: SortOrder | None = None,
) -> ListProvisionedModelThroughputsOutput: ...

Also available as client.paginators.list_provisioned_model_throughputs(...), returning an async iterator of the response type above.

list_tags_for_resource

async def list_tags_for_resource(
    *,
    resource_arn: str,
) -> ListTagsForResourceOutput: ...

put_account_data_retention

async def put_account_data_retention(
    *,
    mode: DataRetentionMode,
) -> PutAccountDataRetentionOutput: ...

put_enforced_guardrail_configuration

async def put_enforced_guardrail_configuration(
    *,
    guardrail_inference_config: AccountEnforcedGuardrailInferenceInputConfiguration,
    config_id: str | None = None,
) -> PutEnforcedGuardrailConfigurationOutput: ...

put_model_invocation_logging_configuration

async def put_model_invocation_logging_configuration(
    *,
    logging_config: LoggingConfig,
) -> PutModelInvocationLoggingConfigurationOutput: ...

put_resource_policy

async def put_resource_policy(
    *,
    resource_arn: str,
    resource_policy: str,
) -> PutResourcePolicyOutput: ...

put_use_case_for_model_access

async def put_use_case_for_model_access(
    *,
    form_data: bytes,
) -> PutUseCaseForModelAccessOutput: ...

register_marketplace_model_endpoint

async def register_marketplace_model_endpoint(
    *,
    endpoint_identifier: str,
    model_source_identifier: str,
) -> RegisterMarketplaceModelEndpointOutput: ...

start_automated_reasoning_policy_build_workflow

async def start_automated_reasoning_policy_build_workflow(
    *,
    policy_arn: str,
    build_workflow_type: AutomatedReasoningPolicyBuildWorkflowType,
    source_content: AutomatedReasoningPolicyBuildWorkflowSource,
    client_request_token: str | None = None,
) -> StartAutomatedReasoningPolicyBuildWorkflowOutput: ...

start_automated_reasoning_policy_test_workflow

async def start_automated_reasoning_policy_test_workflow(
    *,
    policy_arn: str,
    build_workflow_id: str,
    test_case_ids: Sequence[str] | None = None,
    client_request_token: str | None = None,
) -> StartAutomatedReasoningPolicyTestWorkflowOutput: ...

stop_advanced_prompt_optimization_job

async def stop_advanced_prompt_optimization_job(
    *,
    job_identifier: str,
) -> StopAdvancedPromptOptimizationJobOutput: ...

stop_evaluation_job

async def stop_evaluation_job(
    *,
    job_identifier: str,
) -> StopEvaluationJobOutput: ...

stop_model_customization_job

async def stop_model_customization_job(
    *,
    job_identifier: str,
) -> StopModelCustomizationJobOutput: ...

stop_model_invocation_job

async def stop_model_invocation_job(
    *,
    job_identifier: str,
) -> StopModelInvocationJobOutput: ...

tag_resource

async def tag_resource(
    *,
    resource_arn: str,
    tags: Sequence[Tag],
) -> TagResourceOutput: ...

untag_resource

async def untag_resource(
    *,
    resource_arn: str,
    tag_keys: Sequence[str],
) -> UntagResourceOutput: ...

update_automated_reasoning_policy

async def update_automated_reasoning_policy(
    *,
    policy_arn: str,
    policy_definition: AutomatedReasoningPolicyDefinition,
    name: str | None = None,
    description: str | None = None,
) -> UpdateAutomatedReasoningPolicyOutput: ...

update_automated_reasoning_policy_annotations

async def update_automated_reasoning_policy_annotations(
    *,
    policy_arn: str,
    build_workflow_id: str,
    annotations: Sequence[AutomatedReasoningPolicyAnnotation],
    last_updated_annotation_set_hash: str,
) -> UpdateAutomatedReasoningPolicyAnnotationsOutput: ...

update_automated_reasoning_policy_test_case

async def update_automated_reasoning_policy_test_case(
    *,
    policy_arn: str,
    test_case_id: str,
    guard_content: str,
    last_updated_at: str,
    expected_aggregated_findings_result: AutomatedReasoningCheckResult,
    query_content: str | None = None,
    confidence_threshold: float | None = None,
    client_request_token: str | None = None,
) -> UpdateAutomatedReasoningPolicyTestCaseOutput: ...

update_custom_model_deployment

async def update_custom_model_deployment(
    *,
    model_arn: str,
    custom_model_deployment_identifier: str,
) -> UpdateCustomModelDeploymentOutput: ...

update_guardrail

async def update_guardrail(
    *,
    guardrail_identifier: str,
    name: str,
    blocked_input_messaging: str,
    blocked_outputs_messaging: str,
    description: str | None = None,
    topic_policy_config: GuardrailTopicPolicyConfig | None = None,
    content_policy_config: GuardrailContentPolicyConfig | None = None,
    word_policy_config: GuardrailWordPolicyConfig | None = None,
    sensitive_information_policy_config: GuardrailSensitiveInformationPolicyConfig | None = None,
    contextual_grounding_policy_config: GuardrailContextualGroundingPolicyConfig | None = None,
    automated_reasoning_policy_config: GuardrailAutomatedReasoningPolicyConfig | None = None,
    cross_region_config: GuardrailCrossRegionConfig | None = None,
    kms_key_id: str | None = None,
) -> UpdateGuardrailOutput: ...

update_marketplace_model_endpoint

async def update_marketplace_model_endpoint(
    *,
    endpoint_arn: str,
    endpoint_config: EndpointConfig,
    client_request_token: str | None = None,
) -> UpdateMarketplaceModelEndpointOutput: ...

update_provisioned_model_throughput

async def update_provisioned_model_throughput(
    *,
    provisioned_model_id: str,
    desired_provisioned_model_name: str | None = None,
    desired_model_id: str | None = None,
) -> UpdateProvisionedModelThroughputOutput: ...

Links

• Service guide
• Repository
• Issues
• Releases

Licensed under Apache-2.0.