create_provisioned_model_throughput ¶

def create_provisioned_model_throughput(
    self,
    model_units: "capo_bedrock.types.positive_integer.PositiveInteger",
    provisioned_model_name: "capo_bedrock.types.provisioned_model_name.ProvisionedModelName",
    model_id: "capo_bedrock.types.model_identifier.ModelIdentifier",
    *,
    config_overrides: Optional[BedrockClientConfig] = None,
    client_request_token: Optional[
        "capo_bedrock.types.idempotency_token.IdempotencyToken"
    ] = None,
    commitment_duration: Optional[
        "capo_bedrock.types.commitment_duration.CommitmentDuration"
    ] = None,
    tags: Optional["capo_bedrock.types.tag_list.TagList"] = None,
) -> "capo_bedrock.types.create_provisioned_model_throughput_response.CreateProvisionedModelThroughputResponse":
    """<p>Creates dedicated throughput for a base or custom model with the model units and for the duration that you specify. For pricing details, see <a href="http://aws.amazon.com/bedrock/pricing/">Amazon Bedrock Pricing</a>. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-throughput.html">Provisioned Throughput</a> in the <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-service.html">Amazon Bedrock User Guide</a>.</p>

    Args:
        client_request_token: <p>A unique, case-sensitive identifier to ensure that the API request 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/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html">Ensuring idempotency</a> in the Amazon S3 User Guide.</p>
        model_units: <p>Number of model units to allocate. A model unit delivers a specific throughput level for the specified model. The throughput level of a model unit specifies the total number of input and output tokens that it can process and generate within a span of one minute. By default, your account has no model units for purchasing Provisioned Throughputs with commitment. You must first visit the <a href="https://console.aws.amazon.com/support/home#/case/create?issueType=service-limit-increase">Amazon Web Services support center</a> to request MUs.</p> <p>For model unit quotas, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/quotas.html#prov-thru-quotas">Provisioned Throughput quotas</a> in the <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-service.html">Amazon Bedrock User Guide</a>.</p> <p>For more information about what an MU specifies, contact your Amazon Web Services account manager.</p>
        provisioned_model_name: <p>The name for this Provisioned Throughput.</p>
        model_id: <p>The Amazon Resource Name (ARN) or name of the model to associate with this Provisioned Throughput. For a list of models for which you can purchase Provisioned Throughput, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#prov-throughput-models">Amazon Bedrock model IDs for purchasing Provisioned Throughput</a> in the <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-service.html">Amazon Bedrock User Guide</a>.</p>
        commitment_duration: <p>The commitment duration requested for the Provisioned Throughput. Billing occurs hourly and is discounted for longer commitment terms. To request a no-commit Provisioned Throughput, omit this field.</p> <p>Custom models support all levels of commitment. To see which base models support no commitment, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/pt-supported.html">Supported regions and models for Provisioned Throughput</a> in the <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-service.html">Amazon Bedrock User Guide</a> </p>
        tags: <p>Tags to associate with this Provisioned Throughput.</p>

    Raises:
        capo_bedrock.errors.access_denied_exception.AccessDeniedException: <p>The request is denied because of missing access permissions.</p>
        capo_bedrock.errors.internal_server_exception.InternalServerException: <p>An internal server error occurred. Retry your request.</p>
        capo_bedrock.errors.resource_not_found_exception.ResourceNotFoundException: <p>The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.</p>
        capo_bedrock.errors.service_quota_exceeded_exception.ServiceQuotaExceededException: <p>The number of requests exceeds the service quota. Resubmit your request later.</p>
        capo_bedrock.errors.throttling_exception.ThrottlingException: <p>The number of requests exceeds the limit. Resubmit your request later.</p>
        capo_bedrock.errors.too_many_tags_exception.TooManyTagsException: <p>The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request. </p>
        capo_bedrock.errors.validation_exception.ValidationException: <p>Input validation failed. Check your request parameters and retry the request.</p>
        capo_bedrock.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_bedrock.types.create_provisioned_model_throughput_request.CreateProvisionedModelThroughputRequest]",
    ) -> OperationResponse[
        "capo_bedrock.types.create_provisioned_model_throughput_response.CreateProvisionedModelThroughputResponse"
    ]:
        import capo_bedrock._operations.amazon_bedrock_control_plane_service.create_provisioned_model_throughput

        output, http_response = (
            capo_bedrock._operations.amazon_bedrock_control_plane_service.create_provisioned_model_throughput.create_provisioned_model_throughput(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("CreateProvisionedModelThroughput")
    )
    input_: capo_bedrock.types.create_provisioned_model_throughput_request.CreateProvisionedModelThroughputRequest = {
        "model_units": model_units,
        "provisioned_model_name": provisioned_model_name,
        "model_id": model_id,
    }
    if client_request_token is None:
        client_request_token = str(uuid.uuid4())
    input_["client_request_token"] = client_request_token
    if commitment_duration is not None:
        input_["commitment_duration"] = commitment_duration
    if tags is not None:
        input_["tags"] = tags

    response = execute_pipeline(
        OperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    response.response.close()
    return response.output