Request Syntax URI Request Parameters Request Body Response Syntax Response Elements Errors Examples See Also

InvokeModelWithResponseStream

Invoke the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. The response is returned in a stream.

To see if a model supports streaming, call GetFoundationModel and check the responseStreamingSupported field in the response.

Note

The AWS CLI doesn't support InvokeModelWithResponseStream.

For example code, see Invoke model with streaming code example.

This operation requires permissions to perform the bedrock:InvokeModelWithResponseStream action.

Request Syntax


POST /model/modelId/invoke-with-response-stream HTTP/1.1
X-Amzn-Bedrock-Accept: accept
Content-Type: contentType
X-Amzn-Bedrock-GuardrailIdentifier: guardrailIdentifier
X-Amzn-Bedrock-GuardrailVersion: guardrailVersion
X-Amzn-Bedrock-Trace: trace

body

URI Request Parameters

The request uses the following URI parameters.

accept

The desired MIME type of the inference body in the response. The default value is application/json.

contentType

The MIME type of the input data in the request. The default value is application/json.

guardrailIdentifier

The unique identifier of the guardrail that you want to use. If you don't provide a value, no guardrail is applied to the invocation.

An error is thrown in the following situations.

You don't provide a guardrail identifier but you specify the amazon-bedrock-guardrailConfig field in the request body.
You enable the guardrail but the contentType isn't application/json.
You provide a guardrail identifier, but guardrailVersion isn't specified.

Length Constraints: Minimum length of 0. Maximum length of 2048.

Pattern: ^(([a-z0-9]+)|(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:guardrail/[a-z0-9]+))$

guardrailVersion

The version number for the guardrail. The value can also be DRAFT.

Pattern: ^(([1-9][0-9]{0,7})|(DRAFT))$

modelId

The unique identifier of the model to invoke to run inference.

The modelId to provide depends on the type of model that you use:

If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see Amazon Bedrock base model IDs (on-demand throughput) in the Amazon Bedrock User Guide.
If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see Run inference using a Provisioned Throughput in the Amazon Bedrock User Guide.
If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see Use a custom model in Amazon Bedrock in the Amazon Bedrock User Guide.

Length Constraints: Minimum length of 1. Maximum length of 2048.

Pattern: ^(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|([0-9]{12}:provisioned-model/[a-z0-9]{12})))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|(([0-9a-zA-Z][_-]?)+)$

Required: Yes

trace

Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.

Valid Values: ENABLED | DISABLED

Request Body

The request accepts the following binary data.

body

The prompt and inference parameters in the format specified in the contentType in the header. To see the format and content of the request and response bodies for different models, refer to Inference parameters. For more information, see Run inference in the Bedrock User Guide.

Length Constraints: Minimum length of 0. Maximum length of 25000000.

Required: Yes

Response Syntax


HTTP/1.1 200
X-Amzn-Bedrock-Content-Type: contentType
Content-type: application/json

{
   "chunk": { 
      "bytes": blob
   },
   "internalServerException": { 
   },
   "modelStreamErrorException": { 
   },
   "modelTimeoutException": { 
   },
   "throttlingException": { 
   },
   "validationException": { 
   }
}

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The response returns the following HTTP headers.

contentType: The MIME type of the inference result.

The following data is returned in JSON format by the service.

chunk

Content included in the response.

Type: PayloadPart object

internalServerException

An internal server error occurred. Retry your request.

Type: Exception

HTTP Status Code: 500

modelStreamErrorException

An error occurred while streaming the response. Retry your request.

Type: Exception

HTTP Status Code: 424

modelTimeoutException

The request took too long to process. Processing time exceeded the model timeout length.

Type: Exception

HTTP Status Code: 408

throttlingException

The number or frequency of requests exceeds the limit. Resubmit your request later.

Type: Exception

HTTP Status Code: 429

validationException

Input validation failed. Check your request parameters and retry the request.

Type: Exception

HTTP Status Code: 400

Errors

For information about the errors that are common to all actions, see Common Errors.

AccessDeniedException

The request is denied because of missing access permissions.

HTTP Status Code: 403

InternalServerException

An internal server error occurred. Retry your request.

HTTP Status Code: 500

ModelErrorException

The request failed due to an error while processing the model.

HTTP Status Code: 424

ModelNotReadyException

The model specified in the request is not ready to serve inference requests.

HTTP Status Code: 429

ModelStreamErrorException

An error occurred while streaming the response. Retry your request.

HTTP Status Code: 424

ModelTimeoutException

The request took too long to process. Processing time exceeded the model timeout length.

HTTP Status Code: 408

ResourceNotFoundException

The specified resource ARN was not found. Check the ARN and try your request again.

HTTP Status Code: 404

ServiceQuotaExceededException

The number of requests exceeds the service quota. Resubmit your request later.

HTTP Status Code: 400

ThrottlingException

The number of requests exceeds the limit. Resubmit your request later.

HTTP Status Code: 429

ValidationException

Input validation failed. Check your request parameters and retry the request.

HTTP Status Code: 400

Examples

Run inference with streaming on a text model

For streaming, you can set x-amzn-bedrock-accept-type in the header to contain the desired content type of the response. In this example, we set it to accept any content type. The default value is application/json.


POST https://bedrock-runtime.us-east-1.amazonaws.com/model/amazon.titan-text-express-v1/invoke-with-response-stream

-H accept: application/vnd.amazon.eventstream
-H content-type: application/json
-H x-amzn-bedrock-accept: */*

Payload
{"inputText": "Hello world"}

Example response

For streaming, the content type in the response is always set to application/vnd.amazon.eventstream. The response includes an additional header (x-amzn-bedrock-content-type), which contains the actual content type of the response.


-H content-type: application/vnd.amazon.eventstream
-H x-amzn-bedrock-content-type: application/json

Payload (stream events)
<response chunk>

Use a guardrail

This examples show how to use a guardrail with InvokeModelWithResponseStream.


POST /model/modelId/invoke-with-response-stream HTTP/1.1
X-Amzn-Bedrock-Accept: accept
Content-Type: contentType
X-Amzn-Bedrock-GuardrailIdentifier: guardrailIdentifier
X-Amzn-Bedrock-GuardrailVersion: guardrailVersion
X-Amzn-Bedrock-GuardrailTrace: guardrailTrace
X-Amzn-Bedrock-Trace: trace

body

// body
{
    "amazon-bedrock-guardrailConfig": {
        "tagSuffix": "string",
        "streamProcessingMode": "string"
    }
}

Example response

This examples shows the response from a call to InvokeModelWithResponseStream when using a guardrail.


HTTP/1.1 200
X-Amzn-Bedrock-Content-Type: contentType
Content-type: application/json

// chunk 1
{
  "completion": "...",
   "amazon-bedrock-guardrailAction": "INTERVENED | NONE"
}

// chunk 2
{
  "completion": "...",
  "amazon-bedrock-guardrailAction": "INTERVENED | NONE"
}

// last chunk
{
  "completion": "...",
   "amazon-bedrock-guardrailAction": "INTERVENED | NONE",
  "amazon-bedrock-trace": {
    "guardrail": {
    ... // Detailed guardrail trace
    }
  }
}