GET

/v1/schemas/amazon-bedrock/chat/model/{modelId}/converse-stream

Accept:

kind inputactivity chathash 54c0d155…extracted Nov 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. generated Source trace `618bf3a6f4cb6e4987a01bd8ea2ce1f070e854991c750c67babf03520315dead` { "fetchedAt": 1794288032, "extractorVersion": "2", "verifiedAt": null }

Request body

12 properties · 0 required · 127 $defs

property	type	description	constraints
messages	Message[]	The messages that you want to send to the model.
system	SystemContentBlock[]	A prompt that provides instructions or context to the model about the task it should perform, or the persona it should adopt during the conversation.
inferenceConfig	InferenceConfiguration	Inference parameters to pass to the model. Converse and ConverseStream support a base set of inference parameters. If you need to pass additional parameters that the model supports, use the additionalModelRequestFields request field.
toolConfig	ToolConfiguration	Configuration information for the tools that the model can use when generating a response. For information about models that support streaming tool use, see Supported models and model features .
guardrailConfig	GuardrailStreamConfiguration	Configuration information for a guardrail that you want to use in the request. If you include guardContent blocks in the content field in the messages field, the guardrail operates only on those messages. If you include no guardContent blocks, the guardrail op…
additionalModelRequestFields	Document	Additional inference parameters that the model supports, beyond the base set of inference parameters that Converse and ConverseStream support in the inferenceConfig field. For more information, see Model parameters .
promptVariables	PromptVariableMap	Contains a map of variables in a prompt from Prompt management to objects containing the values to fill in for them when running model invocation. This field is ignored if you don't specify a prompt resource in the modelId field.
additionalModelResponseFieldPaths	ConverseStreamRequestAdditionalModelResponseFieldPathsListMemberString[]	Additional model parameters field paths to return in the response. Converse and ConverseStream return the requested fields as a JSON Pointer object in the additionalModelResponseFields field. The following is example JSON for additionalModelResponseFieldPaths …	items ≥ 0 · items ≤ 10
requestMetadata	RequestMetadata	Key-value pairs that you can use to filter invocation logs.
performanceConfig	PerformanceConfiguration	Model performance settings for the request.
serviceTier	ServiceTier	Specifies the processing tier configuration used for serving the request.
outputConfig	OutputConfig	Output configuration for a model response.

Types

127 $defs

AnyToolChoiceobject

The model must request at least one tool (no text is generated). For example, {"any" : {}} . For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.

AudioBlockobject

An audio content block that contains audio data in various supported formats.

format*	enum	The format of the audio data, such as MP3, WAV, FLAC, or other supported audio formats.	mp3 \| opus \| wav \| aac \| flac \| mp4 · +9 more
source*	AudioSource	The source of the audio data, which can be provided as raw bytes or an S3 location.
error	ErrorBlock	Error information if the audio block could not be processed or contains invalid data.

AudioFormatenum

mp3 | opus | wav | aac | flac | mp4 · +9 more

AudioSourceobject

The source of audio data, which can be provided either as raw bytes or a reference to an S3 location.

bytes	string	Audio data encoded in base64.
s3Location	S3Location	A reference to audio data stored in an Amazon S3 bucket. To see which models support S3 uploads, see Supported models and features for Converse .

The Model automatically decides if a tool should be called or whether to generate text instead. For example, {"auto" : {}} . For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide

Blobstring

Booleanboolean

CachePointBlockobject

Defines a section of content to be cached for reuse in subsequent API calls.

type*	enum	Specifies the type of cache point within the CachePointBlock.	default
ttl	enum	Optional TTL duration for cache entries. When specified, enables extended TTL caching with the specified duration. When omitted, uses type value for caching behavior.	5m \| 1h

CachePointTypeenum

default

CacheTTLenum

Time-to-live duration for ephemeral cache entries

5m | 1h

Citationobject

Contains information about a citation that references a specific source document. Citations provide traceability between the model's generated response and the source documents that informed that response.

title	string	The title or identifier of the source document being cited.
source	string	The source from the original search result that provided the cited content.
sourceContent	CitationSourceContent[]	The specific content from the source document that was referenced or cited in the generated response.
location	CitationLocation	The precise location within the source document where the cited content can be found, including character positions, page numbers, or chunk identifiers.

CitationGeneratedContentobject

Contains the generated text content that corresponds to or is supported by a citation from a source document.

text

string

The text content that was generated by the model and is supported by the associated citation.

CitationGeneratedContentListCitationGeneratedContent[]

text

string

The text content that was generated by the model and is supported by the associated citation.

CitationLocationobject

Specifies the precise location within a source document where cited content can be found. This can include character-level positions, page numbers, or document chunks depending on the document type and indexing method.

web	WebLocation	The web URL that was cited for this reference.
documentChar	DocumentCharLocation	The character-level location within the document where the cited content is found.
documentPage	DocumentPageLocation	The page-level location within the document where the cited content is found.
documentChunk	DocumentChunkLocation	The chunk-level location within the document where the cited content is found, typically used for documents that have been segmented into logical chunks.
searchResultLocation	SearchResultLocation	The search result location where the cited content is found, including the search result index and block positions within the content array.

CitationsCitation[]

title	string	The title or identifier of the source document being cited.
source	string	The source from the original search result that provided the cited content.
sourceContent	CitationSourceContent[]	The specific content from the source document that was referenced or cited in the generated response.
location	CitationLocation	The precise location within the source document where the cited content can be found, including character positions, page numbers, or chunk identifiers.

CitationsConfigobject

Configuration settings for enabling and controlling document citations in Converse API responses. When enabled, the model can include citation information that links generated content back to specific source documents.

enabled*

boolean

Specifies whether citations from the selected document should be used in the model's response. When set to true, the model can generate citations that reference the source documents used to inform the response.

CitationsContentBlockobject

A content block that contains both generated text and associated citation information. This block type is returned when document citations are enabled, providing traceability between the generated content and the source documents that informed the response.

content	CitationGeneratedContent[]	The generated content that is supported by the associated citations.
citations	Citation[]	An array of citations that reference the source documents used to generate the associated content.

CitationSourceContentobject

Contains the actual text content from a source document that is being cited or referenced in the model's response.

text

string

The text content from the source document that is being cited.

CitationSourceContentListCitationSourceContent[]

text

string

The text content from the source document that is being cited.

ContentBlockobject

A block of content for a message that you pass to, or receive from, a model with the Converse or ConverseStream API operations.

text	string	Text to include in the message.
image	ImageBlock	Image to include in the message. This field is only supported by Anthropic Claude 3 models.
document	DocumentBlock	A document to include in the message.
video	VideoBlock	Video to include in the message.
audio	AudioBlock	An audio content block containing audio data in the conversation.
toolUse	ToolUseBlock	Information about a tool use request from a model.
toolResult	ToolResultBlock	The result for a tool request that a model makes.
guardContent	GuardrailConverseContentBlock	Contains the content to assess with the guardrail. If you don't specify guardContent in a call to the Converse API, the guardrail (if passed in the Converse API) assesses the entire message. For more information, see Use a guardrail with the Converse API in th…
cachePoint	CachePointBlock	CachePoint to include in the message.
reasoningContent	ReasoningContentBlock	Contains content regarding the reasoning that is carried out by the model. Reasoning refers to a Chain of Thought (CoT) that the model generates to enhance the accuracy of its final response.
citationsContent	CitationsContentBlock	A content block that contains both generated text and associated citation information, providing traceability between the response and source documents.
searchResult	SearchResultBlock	Search result to include in the message.
toolAddition	ToolAdditionBlock	A content block for adding a tool to the available tool set mid-conversation. Each block references a single tool via its tool field. Use within a system role message to make a tool available without re-sending the full tool configuration.
toolRemoval	ToolRemovalBlock	A content block for removing a tool from the available tool set mid-conversation. Each block references a single tool via its tool field. Use within a system role message to remove a tool without re-sending the full tool configuration.

ContentBlocksContentBlock[]

text	string	Text to include in the message.
image	ImageBlock	Image to include in the message. This field is only supported by Anthropic Claude 3 models.
document	DocumentBlock	A document to include in the message.
video	VideoBlock	Video to include in the message.
audio	AudioBlock	An audio content block containing audio data in the conversation.
toolUse	ToolUseBlock	Information about a tool use request from a model.
toolResult	ToolResultBlock	The result for a tool request that a model makes.
guardContent	GuardrailConverseContentBlock	Contains the content to assess with the guardrail. If you don't specify guardContent in a call to the Converse API, the guardrail (if passed in the Converse API) assesses the entire message. For more information, see Use a guardrail with the Converse API in th…
cachePoint	CachePointBlock	CachePoint to include in the message.
reasoningContent	ReasoningContentBlock	Contains content regarding the reasoning that is carried out by the model. Reasoning refers to a Chain of Thought (CoT) that the model generates to enhance the accuracy of its final response.
citationsContent	CitationsContentBlock	A content block that contains both generated text and associated citation information, providing traceability between the response and source documents.
searchResult	SearchResultBlock	Search result to include in the message.
toolAddition	ToolAdditionBlock	A content block for adding a tool to the available tool set mid-conversation. Each block references a single tool via its tool field. Use within a system role message to make a tool available without re-sending the full tool configuration.
toolRemoval	ToolRemovalBlock	A content block for removing a tool from the available tool set mid-conversation. Each block references a single tool via its tool field. Use within a system role message to remove a tool without re-sending the full tool configuration.

ConversationRoleenum

user | assistant | system

ConverseStreamRequestAdditionalModelResponseFieldPathsListConverseStreamRequestAdditionalModelResponseFieldPathsListMemberString[]

items ≥ 0 · items ≤ 10

ConverseStreamRequestAdditionalModelResponseFieldPathsListMemberStringstring

length ≥ 1 · length ≤ 256

Documentany

DocumentBlockobject

A document to include in a message.

format	enum	The format of a document, or its extension.	pdf \| csv \| doc \| docx \| xls \| xlsx · +3 more
name*	string	A name for the document. The name can only contain the following characters: Alphanumeric characters Whitespace characters (no more than one in a row) Hyphens Parentheses Square brackets This field is vulnerable to prompt injections, because the model might in…	length ≥ 1 · length ≤ 200
source*	DocumentSource	Contains the content of the document.
context	string	Contextual information about how the document should be processed or interpreted by the model when generating citations.
citations	CitationsConfig	Configuration settings that control how citations should be generated for this specific document.

DocumentBlockNameStringstring

length ≥ 1 · length ≤ 200

DocumentCharLocationobject

Specifies a character-level location within a document, providing precise positioning information for cited content using start and end character indices.

documentIndex	integer	The index of the document within the array of documents provided in the request.	n ≥ 0
start	integer	The starting character position of the cited content within the document.	n ≥ 0
end	integer	The ending character position of the cited content within the document.	n ≥ 0

DocumentCharLocationDocumentIndexIntegerinteger

n ≥ 0

DocumentCharLocationEndIntegerinteger

n ≥ 0

DocumentCharLocationStartIntegerinteger

n ≥ 0

DocumentChunkLocationobject

Specifies a chunk-level location within a document, providing positioning information for cited content using logical document segments or chunks.

documentIndex	integer	The index of the document within the array of documents provided in the request.	n ≥ 0
start	integer	The starting chunk identifier or index of the cited content within the document.	n ≥ 0
end	integer	The ending chunk identifier or index of the cited content within the document.	n ≥ 0

DocumentChunkLocationDocumentIndexIntegerinteger

n ≥ 0

DocumentChunkLocationEndIntegerinteger

n ≥ 0

DocumentChunkLocationStartIntegerinteger

n ≥ 0

DocumentContentBlockobject

Contains the actual content of a document that can be processed by the model and potentially cited in the response.

text

string

The text content of the document.

DocumentContentBlocksDocumentContentBlock[]

text

string

The text content of the document.

DocumentFormatenum

pdf | csv | doc | docx | xls | xlsx · +3 more

DocumentPageLocationobject

Specifies a page-level location within a document, providing positioning information for cited content using page numbers.

documentIndex	integer	The index of the document within the array of documents provided in the request.	n ≥ 0
start	integer	The starting page number of the cited content within the document.	n ≥ 0
end	integer	The ending page number of the cited content within the document.	n ≥ 0

DocumentPageLocationDocumentIndexIntegerinteger

n ≥ 0

DocumentPageLocationEndIntegerinteger

n ≥ 0

DocumentPageLocationStartIntegerinteger

n ≥ 0

DocumentSourceobject

Contains the content of a document.

bytes	string	The raw bytes for the document. If you use an Amazon Web Services SDK, you don't need to encode the bytes in base64.
s3Location	S3Location	The location of a document object in an Amazon S3 bucket. To see which models support S3 uploads, see Supported models and features for Converse .
text	string	The text content of the document source.
content	DocumentContentBlock[]	The structured content of the document source, which may include various content blocks such as text, images, or other document elements.

DocumentSourceBytesBlobstring

ErrorBlockobject

A block containing error information when content processing fails.

message

string

A human-readable error message describing what went wrong during content processing.

GuardrailConverseContentBlockobject

A content block for selective guarding with the Converse or ConverseStream API operations.

text	GuardrailConverseTextBlock	The text to guard.
image	GuardrailConverseImageBlock	Image within converse content block to be evaluated by the guardrail.

GuardrailConverseContentQualifierenum

grounding_source | query | guard_content

GuardrailConverseContentQualifierListGuardrailConverseContentQualifier[]

GuardrailConverseImageBlockobject

An image block that contains images that you want to assess with a guardrail.

format*	enum	The format details for the image type of the guardrail converse image block.	png \| jpeg
source*	GuardrailConverseImageSource	The image source (image bytes) of the guardrail converse image block.

GuardrailConverseImageFormatenum

png | jpeg

GuardrailConverseImageSourceobject

The image source (image bytes) of the guardrail converse image source.

bytes

string

The raw image bytes for the image.

GuardrailConverseImageSourceBytesBlobstring

GuardrailConverseTextBlockobject

A text block that contains text that you want to assess with a guardrail. For more information, see GuardrailConverseContentBlock .

text*	string	The text that you want to guard.
qualifiers	GuardrailConverseContentQualifier[]	The qualifier details for the guardrails contextual grounding filter.

GuardrailIdentifierstring

length ≥ 0 · length ≤ 2048

GuardrailStreamConfigurationobject

Configuration information for a guardrail that you use with the ConverseStream action.

guardrailIdentifier	string	The identifier for the guardrail.	length ≥ 0 · length ≤ 2048
guardrailVersion	string	The version of the guardrail.
trace	enum	The trace behavior for the guardrail.	enabled \| disabled \| enabled_full
streamProcessingMode	enum	The processing mode. The processing mode. For more information, see Configure streaming response behavior in the Amazon Bedrock User Guide .	sync \| async

GuardrailStreamProcessingModeenum

sync | async

GuardrailTraceenum

enabled | disabled | enabled_full

GuardrailVersionstring

ImageBlockobject

Image content for a message.

format*	enum	The format of the image.	png \| jpeg \| gif \| webp
source*	ImageSource	The source for the image.
error	ErrorBlock	Error information if the image block could not be processed or contains invalid data.

ImageFormatenum

png | jpeg | gif | webp

ImageSourceobject

The source for an image.

bytes	string	The raw image bytes for the image. If you use an AWS SDK, you don't need to encode the image bytes in base64.
s3Location	S3Location	The location of an image object in an Amazon S3 bucket. To see which models support S3 uploads, see Supported models and features for Converse .

ImageSourceBytesBlobstring

InferenceConfigurationobject

Base inference parameters to pass to a model in a call to Converse or ConverseStream . For more information, see Inference parameters for foundation models . If you need to pass additional parameters that the model supports, use the additionalModelRequestField…

maxTokens	integer	The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using. For more information, see Inference parameters for foundation models .	n ≥ 1
temperature	number	The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options. …	0 ≤ n ≤ 1
topP	number	The percentage of most-likely candidates that the model considers for the next token. For example, if you choose a value of 0.8 for topP , the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence. The defa…	0 ≤ n ≤ 1
stopSequences	NonEmptyString[]	A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.	items ≥ 0 · items ≤ 2500

InferenceConfigurationMaxTokensIntegerinteger

n ≥ 1

InferenceConfigurationStopSequencesListNonEmptyString[]

items ≥ 0 · items ≤ 2500

InferenceConfigurationTemperatureFloatnumber

0 ≤ n ≤ 1

InferenceConfigurationTopPFloatnumber

0 ≤ n ≤ 1

JsonSchemaDefinitionobject

JSON schema structured output format options.

schema*	string	The JSON schema to constrain the model's output. For more information, see JSON Schema Reference .
name	string	The name of the JSON schema.
description	string	A description of the JSON schema.

Messageobject

A message input, or returned from, a call to Converse or ConverseStream .

role*	enum	The role that the message plays in the message.	user \| assistant \| system
content*	ContentBlock[]	The message content. Note the following restrictions: You can include up to 20 images. Each image's size, height, and width must be no more than 3.75 MB, 8000 px, and 8000 px, respectively. You can include up to five documents. Each document's size must be no …

MessagesMessage[]

role*	enum	The role that the message plays in the message.	user \| assistant \| system
content*	ContentBlock[]	The message content. Note the following restrictions: You can include up to 20 images. Each image's size, height, and width must be no more than 3.75 MB, 8000 px, and 8000 px, respectively. You can include up to five documents. Each document's size must be no …

NonEmptyStringstring

length ≥ 1

OutputConfigobject

Output configuration for a model response in a call to Converse or ConverseStream .

textFormat	OutputFormat	Structured output parameters to control the model's text response.
effort	string	The effort level for the model to use when generating a response. Higher effort levels allow the model to spend more time reasoning before responding. Supported values are low , medium , high , xhigh , and max . When extended thinking is disabled, the effort l…	length ≥ 0 · length ≤ 16

OutputConfigEffortStringstring

length ≥ 0 · length ≤ 16

OutputFormatobject

Structured output parameters to control the model's response.

type*	enum	The type of structured output format.	json_schema
structure*	OutputFormatStructure	The structure that the model's output must adhere to.

OutputFormatStructureobject

The structure that the model's output must adhere to.

jsonSchema

JsonSchemaDefinition

A JSON schema structure that the model's output must adhere to.

OutputFormatTypeenum

The type of structured output format. Available options are: json_schema.

json_schema

PerformanceConfigLatencyenum

standard | optimized

PerformanceConfigurationobject

Performance settings for a model.

latency

enum

To use a latency-optimized version of the model, set to optimized .

standard | optimized

PromptVariableMapobject

PromptVariableValuesobject

Contains a map of variables in a prompt from Prompt management to an object containing the values to fill in for them when running model invocation. For more information, see How Prompt management works .

text

string

The text value that the variable maps to.

ReasoningContentBlockobject

Contains content regarding the reasoning that is carried out by the model with respect to the content in the content block. Reasoning refers to a Chain of Thought (CoT) that the model generates to enhance the accuracy of its final response.

reasoningText	ReasoningTextBlock	The reasoning that the model used to return the output.
redactedContent	string	The content in the reasoning that was encrypted by the model provider for safety reasons. The encryption doesn't affect the quality of responses.

ReasoningTextBlockobject

Contains the reasoning that the model used to return the output.

text*	string	The reasoning that the model used to return the output.
signature	string	A token that verifies that the reasoning text was generated by the model. If you pass a reasoning block back to the API in a multi-turn conversation, include the text and its signature unmodified.

RequestMetadataobject

RequestMetadataValueStringstring

length ≥ 0 · length ≤ 256

S3Locationobject

A storage location in an Amazon S3 bucket.

uri*	string	An object URI starting with s3:// .	length ≥ 1 · length ≤ 1024
bucketOwner	string	If the bucket belongs to another AWS account, specify that account's ID.

S3Uristring

length ≥ 1 · length ≤ 1024

SearchResultBlockobject

A search result block that enables natural citations with proper source attribution for retrieved content. This field is only supported by Anthropic Claude Opus 4.1, Opus 4, Sonnet 4.5, Sonnet 4, Sonnet 3.7, and 3.5 Haiku models.

source*	string	The source URL or identifier for the content.
title*	string	A descriptive title for the search result.
content*	SearchResultContentBlock[]	An array of search result content block.
citations	CitationsConfig	Configuration setting for citations

SearchResultContentBlockobject

A block within a search result that contains the content.

text*

string

The actual text content

SearchResultContentBlocksSearchResultContentBlock[]

text*

string

The actual text content

SearchResultLocationobject

Specifies a search result location within the content array, providing positioning information for cited content using search result index and block positions.

searchResultIndex	integer	The index of the search result content block where the cited content is found.	n ≥ 0
start	integer	The starting position in the content array where the cited content begins.	n ≥ 0
end	integer	The ending position in the content array where the cited content ends.	n ≥ 0

SearchResultLocationEndIntegerinteger

n ≥ 0

SearchResultLocationSearchResultIndexIntegerinteger

n ≥ 0

SearchResultLocationStartIntegerinteger

n ≥ 0

ServiceTierobject

Specifies the processing tier configuration used for serving the request.

type*

enum

Specifies the processing tier type used for serving the request.

priority | default | flex | reserved

ServiceTierTypeenum

priority | default | flex | reserved

SpecificToolChoiceobject

The model must request a specific tool. For example, {"tool" : {"name" : "Your tool name"}} . For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide This field is only supported by Anthropic Claude 3 models.

name*

string

The name of the tool that the model must request.

length ≥ 1 · length ≤ 64

Stringstring

SystemContentBlockobject

Contains configurations for instructions to provide the model for how to handle input. To learn more, see Using the Converse API .

text	string	A system prompt for the model.	length ≥ 1
guardContent	GuardrailConverseContentBlock	A content block to assess with the guardrail. Use with the Converse or ConverseStream API operations. For more information, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide .
cachePoint	CachePointBlock	CachePoint to include in the system prompt.

SystemContentBlocksSystemContentBlock[]

text	string	A system prompt for the model.	length ≥ 1
guardContent	GuardrailConverseContentBlock	A content block to assess with the guardrail. Use with the Converse or ConverseStream API operations. For more information, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide .
cachePoint	CachePointBlock	CachePoint to include in the system prompt.

SystemToolobject

Specifies a system-defined tool for the model to use. System-defined tools are tools that are created and provided by the model provider.

name*

string

The name of the system-defined tool that you want to call.

length ≥ 1 · length ≤ 64

Toolobject

Information about a tool that you can use with the Converse API. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.

toolSpec	ToolSpecification	The specfication for the tool.
systemTool	SystemTool	Specifies the system-defined tool that you want use.
cachePoint	CachePointBlock	CachePoint to include in the tool configuration.

ToolAdditionBlockobject

A content block for adding a tool to the available tool set mid-conversation. Each block references a single tool via its tool field. Use within a system role message to make a tool available without re-sending the full tool configuration.

tool*

ToolReference

A reference to the tool to add to the available tool set.

ToolChoiceobject

Determines which tools the model should request in a call to Converse or ConverseStream . For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.

auto	AutoToolChoice	(Default). The Model automatically decides if a tool should be called or whether to generate text instead.
any	AnyToolChoice	The model must request at least one tool (no text is generated).
tool	SpecificToolChoice	The Model must request the specified tool. Only supported by Anthropic Claude 3 and Amazon Nova models.

ToolConfigurationobject

Configuration information for the tools that you pass to a model. For more information, see Tool use (function calling) in the Amazon Bedrock User Guide.

tools*	Tool[]	An array of tools that you want to pass to a model.	items ≥ 1
toolChoice	ToolChoice	If supported by model, forces the model to request a tool.

ToolConfigurationToolsListTool[]

toolSpec	ToolSpecification	The specfication for the tool.
systemTool	SystemTool	Specifies the system-defined tool that you want use.
cachePoint	CachePointBlock	CachePoint to include in the tool configuration.

ToolInputSchemaobject

The schema for the tool. The top level schema type must be object . For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.

json

Document

The JSON schema for the tool. For more information, see JSON Schema Reference .

ToolNamestring

length ≥ 1 · length ≤ 64

ToolReferenceobject

A reference to a tool in the tool configuration. Used with ToolAdditionBlock and ToolRemovalBlock to identify which tool to add or remove mid-conversation.

type	string	The type of tool reference.	length ≥ 1 · length ≤ 64
name	string	The name of the tool. Must match the name of a tool declared in the top-level tool configuration.	length ≥ 1 · length ≤ 128
serverName	string	The name of the MCP server that provides the tool. Required when referencing an MCP tool.	length ≥ 1 · length ≤ 128

ToolReferenceNameStringstring

length ≥ 1 · length ≤ 128

ToolReferenceServerNameStringstring

length ≥ 1 · length ≤ 128

ToolReferenceTypeStringstring

length ≥ 1 · length ≤ 64

ToolRemovalBlockobject

A content block for removing a tool from the available tool set mid-conversation. Each block references a single tool via its tool field. Use within a system role message to remove a tool without re-sending the full tool configuration.

tool*

ToolReference

A reference to the tool to remove from the available tool set.

ToolResultBlockobject

A tool result block that contains the results for a tool request that the model previously made. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.

toolUseId*	string	The ID of the tool request that this is the result for.	length ≥ 1 · length ≤ 64
content*	ToolResultContentBlock[]	The content for tool result content block.
status	enum	The status for the tool result content block. This field is only supported by Amazon Nova and Anthropic Claude 3 and 4 models.	success \| error
type	string	The type for the tool result content block.

ToolResultContentBlockobject

The tool result content block. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.

json	Document	A tool result that is JSON format data.
text	string	A tool result that is text.
image	ImageBlock	A tool result that is an image. This field is only supported by Amazon Nova and Anthropic Claude 3 and 4 models.
document	DocumentBlock	A tool result that is a document.
video	VideoBlock	A tool result that is video.
searchResult	SearchResultBlock	A tool result that is a search result.

ToolResultContentBlocksToolResultContentBlock[]

json	Document	A tool result that is JSON format data.
text	string	A tool result that is text.
image	ImageBlock	A tool result that is an image. This field is only supported by Amazon Nova and Anthropic Claude 3 and 4 models.
document	DocumentBlock	A tool result that is a document.
video	VideoBlock	A tool result that is video.
searchResult	SearchResultBlock	A tool result that is a search result.

ToolResultStatusenum

success | error

ToolSpecificationobject

The specification for the tool. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.

name*	string	The name for the tool.	length ≥ 1 · length ≤ 64
description	string	The description for the tool.	length ≥ 1
inputSchema*	ToolInputSchema	The input schema for the tool in JSON format.
strict	boolean	Flag to enable structured output enforcement on a tool usage response.

ToolUseBlockobject

A tool use content block. Contains information about a tool that the model is requesting be run., The model uses the result from the tool to generate a response. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.

toolUseId*	string	The ID for the tool request.	length ≥ 1 · length ≤ 64
name*	string	The name of the tool that the model wants to use.	length ≥ 1 · length ≤ 64
input*	Document	The input to pass to the tool.
type	enum	The type for the tool request.	server_tool_use

ToolUseIdstring

length ≥ 1 · length ≤ 64

ToolUseTypeenum

server_tool_use

VideoBlockobject

A video block.

format*	enum	The block's format.	mkv \| mov \| mp4 \| webm \| flv \| mpeg · +3 more
source*	VideoSource	The block's source.

VideoFormatenum

mkv | mov | mp4 | webm | flv | mpeg · +3 more

VideoSourceobject

A video source. You can upload a smaller video as a base64-encoded string as long as the encoded file is less than 25MB. You can also transfer videos up to 1GB in size from an S3 bucket.

bytes	string	Video content encoded in base64.
s3Location	S3Location	The location of a video object in an Amazon S3 bucket. To see which models support S3 uploads, see Supported models and features for Converse .

VideoSourceBytesBlobstring

WebLocationobject

Provides the URL and domain information for the website that was cited when performing a web search.

url	string	The URL that was cited when performing a web search.
domain	string	The domain that was cited when performing a web search.

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"amazon-bedrock","endpointId":"model/{modelId}/converse-stream","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}

/v1/schemas/amazon-bedrock/chat/model/{modelId}/converse-stream

Request body

Types

AccountIdstring

AnyToolChoiceobject

AudioBlockobject

AudioFormatenum

AudioSourceobject

AudioSourceBytesBlobstring

AutoToolChoiceobject

Blobstring

Booleanboolean

CachePointBlockobject

CachePointTypeenum

CacheTTLenum

Citationobject

CitationGeneratedContentobject

CitationGeneratedContentListCitationGeneratedContent[]

CitationLocationobject

CitationsCitation[]

CitationsConfigobject

CitationsContentBlockobject

CitationSourceContentobject

CitationSourceContentListCitationSourceContent[]

ContentBlockobject

ContentBlocksContentBlock[]

ConversationRoleenum

ConverseStreamRequestAdditionalModelResponseFieldPathsListConverseStreamRequestAdditionalModelResponseFieldPathsListMemberString[]

ConverseStreamRequestAdditionalModelResponseFieldPathsListMemberStringstring

Documentany

DocumentBlockobject

DocumentBlockNameStringstring

DocumentCharLocationobject

DocumentCharLocationDocumentIndexIntegerinteger

DocumentCharLocationEndIntegerinteger

DocumentCharLocationStartIntegerinteger

DocumentChunkLocationobject

DocumentChunkLocationDocumentIndexIntegerinteger

DocumentChunkLocationEndIntegerinteger

DocumentChunkLocationStartIntegerinteger

DocumentContentBlockobject

DocumentContentBlocksDocumentContentBlock[]

DocumentFormatenum

DocumentPageLocationobject

DocumentPageLocationDocumentIndexIntegerinteger

DocumentPageLocationEndIntegerinteger

DocumentPageLocationStartIntegerinteger

DocumentSourceobject

DocumentSourceBytesBlobstring

ErrorBlockobject

GuardrailConverseContentBlockobject

GuardrailConverseContentQualifierenum

GuardrailConverseContentQualifierListGuardrailConverseContentQualifier[]

GuardrailConverseImageBlockobject

GuardrailConverseImageFormatenum

GuardrailConverseImageSourceobject

GuardrailConverseImageSourceBytesBlobstring

GuardrailConverseTextBlockobject

GuardrailIdentifierstring

GuardrailStreamConfigurationobject

GuardrailStreamProcessingModeenum

GuardrailTraceenum

GuardrailVersionstring

ImageBlockobject

ImageFormatenum

ImageSourceobject

ImageSourceBytesBlobstring

InferenceConfigurationobject

InferenceConfigurationMaxTokensIntegerinteger

InferenceConfigurationStopSequencesListNonEmptyString[]

InferenceConfigurationTemperatureFloatnumber

InferenceConfigurationTopPFloatnumber

JsonSchemaDefinitionobject

Messageobject

MessagesMessage[]

NonEmptyStringstring

OutputConfigobject

OutputConfigEffortStringstring

OutputFormatobject

OutputFormatStructureobject