GET

/v1/schemas/amazon-bedrock/chat/model/{modelId}/converse-stream?kind=output

Accept:

kind outputactivity chathash 4a1376c7…extracted Nov 10, 2026version currentsource upstream spec ↗

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

Response body

11 properties · 0 required · 176 $defs

property	type	description
messageStart	MessageStartEvent	Message start information.
contentBlockStart	ContentBlockStartEvent	Start information for a content block.
contentBlockDelta	ContentBlockDeltaEvent	The messages output content block delta.
contentBlockStop	ContentBlockStopEvent	Stop information for a content block.
messageStop	MessageStopEvent	Message stop information.
metadata	ConverseStreamMetadataEvent	Metadata for the converse output stream.
internalServerException	InternalServerException	An internal server error occurred. Retry your request.
modelStreamErrorException	ModelStreamErrorException	A streaming error occurred. Retry your request.
validationException	ValidationException	The input fails to satisfy the constraints specified by Amazon Bedrock . For troubleshooting this error, see ValidationError in the Amazon Bedrock User Guide.
throttlingException	ThrottlingException	Your request was denied due to exceeding the account quotas for Amazon Bedrock . For troubleshooting this error, see ThrottlingException in the Amazon Bedrock User Guide.
serviceUnavailableException	ServiceUnavailableException	The service isn't currently available. For troubleshooting this error, see ServiceUnavailable in the Amazon Bedrock User Guide

Types

176 $defs

AppliedGuardrailDetailsobject

Details about the specific guardrail that was applied during this assessment, including its identifier, version, ARN, origin, and ownership information.

guardrailId	string	The unique ID of the guardrail that was applied.	length ≥ 0 · length ≤ 2048
guardrailVersion	string	The version of the guardrail that was applied.
guardrailArn	string	The ARN of the guardrail that was applied.	length ≥ 0 · length ≤ 2048
guardrailOrigin	GuardrailOrigin[]	The origin of how the guardrail was applied. This can be either requested at the API level or enforced at the account or organization level as a default guardrail.
guardrailOwnership	enum	The ownership type of the guardrail, indicating whether it is owned by the requesting account or is a cross-account guardrail shared from another AWS account.	SELF \| CROSS_ACCOUNT

AutomatedReasoningRuleIdentifierstring

length ≥ 0 · length ≤ 12

Blobstring

CacheDetailobject

Cache creation metrics for a specific TTL duration

ttl*	enum	TTL duration for these cached tokens	5m \| 1h
inputTokens*	integer	Number of tokens written to cache with this TTL (cache creation tokens)	n ≥ 0

CacheDetailInputTokensIntegerinteger

n ≥ 0

CacheDetailsListCacheDetail[]

List of cache details by TTL

ttl*	enum	TTL duration for these cached tokens	5m \| 1h
inputTokens*	integer	Number of tokens written to cache with this TTL (cache creation tokens)	n ≥ 0

CacheTTLenum

Time-to-live duration for ephemeral cache entries

5m | 1h

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.

CitationsDeltaobject

Contains incremental updates to citation information during streaming responses. This allows clients to build up citation data progressively as the response is generated.

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	CitationSourceContentDelta[]	The specific content from the source document that was referenced or cited in the generated response.
location	CitationLocation	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.

CitationSourceContentDeltaobject

Contains incremental updates to the source content text during streaming responses, allowing clients to build up the cited content progressively.

text

string

An incremental update to the text content from the source document that is being cited.

CitationSourceContentListDeltaCitationSourceContentDelta[]

text

string

An incremental update to the text content from the source document that is being cited.

ContentBlockDeltaobject

A block of content in a streaming response.

text	string	The content text.
toolUse	ToolUseBlockDelta	Information about a tool that the model is requesting to use.
toolResult	ToolResultBlockDelta[]	An incremental update that contains the results from a tool call.
reasoningContent	ReasoningContentBlockDelta	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.
citation	CitationsDelta	Incremental citation information that is streamed as part of the response generation process.
image	ImageBlockDelta	A streaming delta event containing incremental image data.

ContentBlockDeltaEventobject

The content block delta event.

delta*	ContentBlockDelta	The delta for a content block delta event.
contentBlockIndex*	integer	The block index for a content block delta event.	n ≥ 0

ContentBlockStartobject

Content block start information.

toolUse	ToolUseBlockStart	Information about a tool that the model is requesting to use.
toolResult	ToolResultBlockStart	The
image	ImageBlockStart	The initial event indicating the start of a streaming image block.

ContentBlockStartEventobject

Content block start event.

start*	ContentBlockStart	Start information about a content block start event.
contentBlockIndex*	integer	The index for a content block start event.	n ≥ 0

ContentBlockStopEventobject

A content block stop event.

contentBlockIndex*

integer

The index for a content block.

n ≥ 0

ConversationRoleenum

user | assistant | system

ConverseStreamMetadataEventobject

A conversation stream metadata event.

usage*	TokenUsage	Usage information for the conversation stream event.
metrics*	ConverseStreamMetrics	The metrics for the conversation stream metadata event.
trace	ConverseStreamTrace	The trace object in the response from ConverseStream that contains information about the guardrail behavior.
performanceConfig	PerformanceConfiguration	Model performance configuration metadata for the conversation stream event.
serviceTier	ServiceTier	Specifies the processing tier configuration used for serving the request.

ConverseStreamMetricsobject

Metrics for the stream.

latencyMs*

integer

The latency for the streaming request, in milliseconds.

ConverseStreamTraceobject

The trace object in a response from ConverseStream .

guardrail	GuardrailTraceAssessment	The guardrail trace object.
promptRouter	PromptRouterTrace	The request's prompt router.

Documentany

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

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

ErrorBlockobject

A block containing error information when content processing fails.

message

string

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

GuardrailArnstring

length ≥ 0 · length ≤ 2048

GuardrailAssessmentobject

A behavior assessment of the guardrail policies used in a call to the Converse API.

topicPolicy	GuardrailTopicPolicyAssessment	The topic policy.
contentPolicy	GuardrailContentPolicyAssessment	The content policy.
wordPolicy	GuardrailWordPolicyAssessment	The word policy.
sensitiveInformationPolicy	GuardrailSensitiveInformationPolicyAssessment	The sensitive information policy.
contextualGroundingPolicy	GuardrailContextualGroundingPolicyAssessment	The contextual grounding policy used for the guardrail assessment.
automatedReasoningPolicy	GuardrailAutomatedReasoningPolicyAssessment	The automated reasoning policy assessment results, including logical validation findings for the input content.
invocationMetrics	GuardrailInvocationMetrics	The invocation metrics for the guardrail assessment.
appliedGuardrailDetails	AppliedGuardrailDetails	Details about the specific guardrail that was applied during this assessment, including its identifier, version, ARN, origin, and ownership information.

GuardrailAssessmentListGuardrailAssessment[]

topicPolicy	GuardrailTopicPolicyAssessment	The topic policy.
contentPolicy	GuardrailContentPolicyAssessment	The content policy.
wordPolicy	GuardrailWordPolicyAssessment	The word policy.
sensitiveInformationPolicy	GuardrailSensitiveInformationPolicyAssessment	The sensitive information policy.
contextualGroundingPolicy	GuardrailContextualGroundingPolicyAssessment	The contextual grounding policy used for the guardrail assessment.
automatedReasoningPolicy	GuardrailAutomatedReasoningPolicyAssessment	The automated reasoning policy assessment results, including logical validation findings for the input content.
invocationMetrics	GuardrailInvocationMetrics	The invocation metrics for the guardrail assessment.
appliedGuardrailDetails	AppliedGuardrailDetails	Details about the specific guardrail that was applied during this assessment, including its identifier, version, ARN, origin, and ownership information.

GuardrailAssessmentListMapobject

GuardrailAssessmentMapobject

GuardrailAutomatedReasoningDifferenceScenarioListGuardrailAutomatedReasoningScenario[]

statements

GuardrailAutomatedReasoningStatement[]

List of logical assignments and statements that define this scenario.

GuardrailAutomatedReasoningFindingobject

Represents a logical validation result from automated reasoning policy evaluation. The finding indicates whether claims in the input are logically valid, invalid, satisfiable, impossible, or have other logical issues.

valid	GuardrailAutomatedReasoningValidFinding	Contains the result when the automated reasoning evaluation determines that the claims in the input are logically valid and definitively true based on the provided premises and policy rules.
invalid	GuardrailAutomatedReasoningInvalidFinding	Contains the result when the automated reasoning evaluation determines that the claims in the input are logically invalid and contradict the established premises or policy rules.
satisfiable	GuardrailAutomatedReasoningSatisfiableFinding	Contains the result when the automated reasoning evaluation determines that the claims in the input could be either true or false depending on additional assumptions not provided in the input context.
impossible	GuardrailAutomatedReasoningImpossibleFinding	Contains the result when the automated reasoning evaluation determines that no valid logical conclusions can be drawn due to contradictions in the premises or policy rules themselves.
translationAmbiguous	GuardrailAutomatedReasoningTranslationAmbiguousFinding	Contains the result when the automated reasoning evaluation detects that the input has multiple valid logical interpretations, requiring additional context or clarification to proceed with validation.
tooComplex	GuardrailAutomatedReasoningTooComplexFinding	Contains the result when the automated reasoning evaluation cannot process the input due to its complexity or volume exceeding the system's processing capacity for logical analysis.
noTranslations	GuardrailAutomatedReasoningNoTranslationsFinding	Contains the result when the automated reasoning evaluation cannot extract any relevant logical information from the input that can be validated against the policy rules.

GuardrailAutomatedReasoningFindingListGuardrailAutomatedReasoningFinding[]

valid	GuardrailAutomatedReasoningValidFinding	Contains the result when the automated reasoning evaluation determines that the claims in the input are logically valid and definitively true based on the provided premises and policy rules.
invalid	GuardrailAutomatedReasoningInvalidFinding	Contains the result when the automated reasoning evaluation determines that the claims in the input are logically invalid and contradict the established premises or policy rules.
satisfiable	GuardrailAutomatedReasoningSatisfiableFinding	Contains the result when the automated reasoning evaluation determines that the claims in the input could be either true or false depending on additional assumptions not provided in the input context.
impossible	GuardrailAutomatedReasoningImpossibleFinding	Contains the result when the automated reasoning evaluation determines that no valid logical conclusions can be drawn due to contradictions in the premises or policy rules themselves.
translationAmbiguous	GuardrailAutomatedReasoningTranslationAmbiguousFinding	Contains the result when the automated reasoning evaluation detects that the input has multiple valid logical interpretations, requiring additional context or clarification to proceed with validation.
tooComplex	GuardrailAutomatedReasoningTooComplexFinding	Contains the result when the automated reasoning evaluation cannot process the input due to its complexity or volume exceeding the system's processing capacity for logical analysis.
noTranslations	GuardrailAutomatedReasoningNoTranslationsFinding	Contains the result when the automated reasoning evaluation cannot extract any relevant logical information from the input that can be validated against the policy rules.

GuardrailAutomatedReasoningImpossibleFindingobject

Indicates that no valid claims can be made due to logical contradictions in the premises or rules.

translation	GuardrailAutomatedReasoningTranslation	The logical translation of the input that this finding evaluates.
contradictingRules	GuardrailAutomatedReasoningRule[]	The automated reasoning policy rules that contradict the claims and/or premises in the input.
logicWarning	GuardrailAutomatedReasoningLogicWarning	Indication of a logic issue with the translation without needing to consider the automated reasoning policy rules.

GuardrailAutomatedReasoningInputTextReferenceobject

References a portion of the original input text that corresponds to logical elements.

text

string

The specific text from the original input that this reference points to.

length ≥ 0 · length ≤ 1000

GuardrailAutomatedReasoningInputTextReferenceListGuardrailAutomatedReasoningInputTextReference[]

text

string

The specific text from the original input that this reference points to.

length ≥ 0 · length ≤ 1000

GuardrailAutomatedReasoningInvalidFindingobject

Indicates that the claims are logically false and contradictory to the established rules or premises.

translation	GuardrailAutomatedReasoningTranslation	The logical translation of the input that this finding invalidates.
contradictingRules	GuardrailAutomatedReasoningRule[]	The automated reasoning policy rules that contradict the claims in the input.
logicWarning	GuardrailAutomatedReasoningLogicWarning	Indication of a logic issue with the translation without needing to consider the automated reasoning policy rules.

GuardrailAutomatedReasoningLogicWarningobject

Identifies logical issues in the translated statements that exist independent of any policy rules, such as statements that are always true or always false.

type	enum	The category of the detected logical issue, such as statements that are always true or always false.	ALWAYS_FALSE \| ALWAYS_TRUE
premises	GuardrailAutomatedReasoningStatement[]	The logical statements that serve as premises under which the claims are validated.
claims	GuardrailAutomatedReasoningStatement[]	The logical statements that are validated while assuming the policy and premises.

GuardrailAutomatedReasoningLogicWarningTypeenum

ALWAYS_FALSE | ALWAYS_TRUE

GuardrailAutomatedReasoningNoTranslationsFindingobject

Indicates that no relevant logical information could be extracted from the input for validation.

GuardrailAutomatedReasoningPoliciesProcessedinteger

GuardrailAutomatedReasoningPolicyAssessmentobject

Contains the results of automated reasoning policy evaluation, including logical findings about the validity of claims made in the input content.

findings

GuardrailAutomatedReasoningFinding[]

List of logical validation results produced by evaluating the input content against automated reasoning policies.

GuardrailAutomatedReasoningPolicyUnitsProcessedinteger

GuardrailAutomatedReasoningPolicyVersionArnstring

length ≥ 0 · length ≤ 2048

GuardrailAutomatedReasoningRuleobject

References a specific automated reasoning policy rule that was applied during evaluation.

identifier	string	The unique identifier of the automated reasoning rule.	length ≥ 0 · length ≤ 12
policyVersionArn	string	The ARN of the automated reasoning policy version that contains this rule.	length ≥ 0 · length ≤ 2048

GuardrailAutomatedReasoningRuleListGuardrailAutomatedReasoningRule[]

identifier	string	The unique identifier of the automated reasoning rule.	length ≥ 0 · length ≤ 12
policyVersionArn	string	The ARN of the automated reasoning policy version that contains this rule.	length ≥ 0 · length ≤ 2048

GuardrailAutomatedReasoningSatisfiableFindingobject

Indicates that the claims could be either true or false depending on additional assumptions not provided in the input.

translation	GuardrailAutomatedReasoningTranslation	The logical translation of the input that this finding evaluates.
claimsTrueScenario	GuardrailAutomatedReasoningScenario	An example scenario demonstrating how the claims could be logically true.
claimsFalseScenario	GuardrailAutomatedReasoningScenario	An example scenario demonstrating how the claims could be logically false.
logicWarning	GuardrailAutomatedReasoningLogicWarning	Indication of a logic issue with the translation without needing to consider the automated reasoning policy rules.

GuardrailAutomatedReasoningScenarioobject

Represents a logical scenario where claims can be evaluated as true or false, containing specific logical assignments.

statements

GuardrailAutomatedReasoningStatement[]

List of logical assignments and statements that define this scenario.

GuardrailAutomatedReasoningStatementobject

A logical statement that includes both formal logic representation and natural language explanation.

logic	string	The formal logical representation of the statement.	length ≥ 0 · length ≤ 1000
naturalLanguage	string	The natural language explanation of the logical statement.	length ≥ 0 · length ≤ 1000

GuardrailAutomatedReasoningStatementListGuardrailAutomatedReasoningStatement[]

logic	string	The formal logical representation of the statement.	length ≥ 0 · length ≤ 1000
naturalLanguage	string	The natural language explanation of the logical statement.	length ≥ 0 · length ≤ 1000

GuardrailAutomatedReasoningStatementLogicContentstring

length ≥ 0 · length ≤ 1000

GuardrailAutomatedReasoningStatementNaturalLanguageContentstring

length ≥ 0 · length ≤ 1000

GuardrailAutomatedReasoningTooComplexFindingobject

Indicates that the input exceeds the processing capacity due to the volume or complexity of the logical information.

GuardrailAutomatedReasoningTranslationobject

Contains the logical translation of natural language input into formal logical statements, including premises, claims, and confidence scores.

premises	GuardrailAutomatedReasoningStatement[]	The logical statements that serve as the foundation or assumptions for the claims.
claims	GuardrailAutomatedReasoningStatement[]	The logical statements that are being validated against the premises and policy rules.
untranslatedPremises	GuardrailAutomatedReasoningInputTextReference[]	References to portions of the original input text that correspond to the premises but could not be fully translated.
untranslatedClaims	GuardrailAutomatedReasoningInputTextReference[]	References to portions of the original input text that correspond to the claims but could not be fully translated.
confidence	number	A confidence score between 0 and 1 indicating how certain the system is about the logical translation.	0 ≤ n ≤ 1

GuardrailAutomatedReasoningTranslationAmbiguousFindingobject

Indicates that the input has multiple valid logical interpretations, requiring additional context or clarification.

options	GuardrailAutomatedReasoningTranslationOption[]	Different logical interpretations that were detected during translation of the input.	items ≥ 0 · items ≤ 2
differenceScenarios	GuardrailAutomatedReasoningScenario[]	Scenarios showing how the different translation options differ in meaning.	items ≥ 0 · items ≤ 2

GuardrailAutomatedReasoningTranslationConfidencenumber

0 ≤ n ≤ 1

GuardrailAutomatedReasoningTranslationListGuardrailAutomatedReasoningTranslation[]

premises	GuardrailAutomatedReasoningStatement[]	The logical statements that serve as the foundation or assumptions for the claims.
claims	GuardrailAutomatedReasoningStatement[]	The logical statements that are being validated against the premises and policy rules.
untranslatedPremises	GuardrailAutomatedReasoningInputTextReference[]	References to portions of the original input text that correspond to the premises but could not be fully translated.
untranslatedClaims	GuardrailAutomatedReasoningInputTextReference[]	References to portions of the original input text that correspond to the claims but could not be fully translated.
confidence	number	A confidence score between 0 and 1 indicating how certain the system is about the logical translation.	0 ≤ n ≤ 1

GuardrailAutomatedReasoningTranslationOptionobject

Represents one possible logical interpretation of ambiguous input content.

translations

GuardrailAutomatedReasoningTranslation[]

Example translations that provide this possible interpretation of the input.

GuardrailAutomatedReasoningTranslationOptionListGuardrailAutomatedReasoningTranslationOption[]

translations

GuardrailAutomatedReasoningTranslation[]

Example translations that provide this possible interpretation of the input.

GuardrailAutomatedReasoningValidFindingobject

Indicates that the claims are definitively true and logically implied by the premises, with no possible alternative interpretations.

translation	GuardrailAutomatedReasoningTranslation	The logical translation of the input that this finding validates.
claimsTrueScenario	GuardrailAutomatedReasoningScenario	An example scenario demonstrating how the claims are logically true.
supportingRules	GuardrailAutomatedReasoningRule[]	The automated reasoning policy rules that support why this result is considered valid.
logicWarning	GuardrailAutomatedReasoningLogicWarning	Indication of a logic issue with the translation without needing to consider the automated reasoning policy rules.

GuardrailContentFilterobject

The content filter for a guardrail.

type*	enum	The guardrail type.	INSULTS \| HATE \| SEXUAL \| VIOLENCE \| MISCONDUCT \| PROMPT_ATTACK
confidence*	enum	The guardrail confidence.	NONE \| LOW \| MEDIUM \| HIGH
filterStrength	enum	The filter strength setting for the guardrail content filter.	NONE \| LOW \| MEDIUM \| HIGH
action*	enum	The guardrail action.	BLOCKED \| NONE
detected	boolean	Indicates whether content that breaches the guardrail configuration is detected.

GuardrailContentFilterConfidenceenum

NONE | LOW | MEDIUM | HIGH

GuardrailContentFilterListGuardrailContentFilter[]

type*	enum	The guardrail type.	INSULTS \| HATE \| SEXUAL \| VIOLENCE \| MISCONDUCT \| PROMPT_ATTACK
confidence*	enum	The guardrail confidence.	NONE \| LOW \| MEDIUM \| HIGH
filterStrength	enum	The filter strength setting for the guardrail content filter.	NONE \| LOW \| MEDIUM \| HIGH
action*	enum	The guardrail action.	BLOCKED \| NONE
detected	boolean	Indicates whether content that breaches the guardrail configuration is detected.

GuardrailContentFilterStrengthenum

NONE | LOW | MEDIUM | HIGH

GuardrailContentFilterTypeenum

GuardrailContentPolicyActionenum

BLOCKED | NONE

GuardrailContentPolicyAssessmentobject

An assessment of a content policy for a guardrail.

filters*

GuardrailContentFilter[]

The content policy filters.

GuardrailContentPolicyImageUnitsProcessedinteger

GuardrailContentPolicyUnitsProcessedinteger

GuardrailContextualGroundingFilterobject

The details for the guardrails contextual grounding filter.

type*	enum	The contextual grounding filter type.	GROUNDING \| RELEVANCE
threshold*	number	The threshold used by contextual grounding filter to determine whether the content is grounded or not.	0 ≤ n ≤ 1
score*	number	The score generated by contextual grounding filter.	0 ≤ n ≤ 1
action*	enum	The action performed by the guardrails contextual grounding filter.	BLOCKED \| NONE
detected	boolean	Indicates whether content that fails the contextual grounding evaluation (grounding or relevance score less than the corresponding threshold) was detected.

GuardrailContextualGroundingFiltersGuardrailContextualGroundingFilter[]

type*	enum	The contextual grounding filter type.	GROUNDING \| RELEVANCE
threshold*	number	The threshold used by contextual grounding filter to determine whether the content is grounded or not.	0 ≤ n ≤ 1
score*	number	The score generated by contextual grounding filter.	0 ≤ n ≤ 1
action*	enum	The action performed by the guardrails contextual grounding filter.	BLOCKED \| NONE
detected	boolean	Indicates whether content that fails the contextual grounding evaluation (grounding or relevance score less than the corresponding threshold) was detected.

GuardrailContextualGroundingFilterScoreDoublenumber

0 ≤ n ≤ 1

GuardrailContextualGroundingFilterThresholdDoublenumber

0 ≤ n ≤ 1

GuardrailContextualGroundingFilterTypeenum

GROUNDING | RELEVANCE

GuardrailContextualGroundingPolicyActionenum

BLOCKED | NONE

GuardrailContextualGroundingPolicyAssessmentobject

The policy assessment details for the guardrails contextual grounding filter.

filters

GuardrailContextualGroundingFilter[]

The filter details for the guardrails contextual grounding filter.

GuardrailContextualGroundingPolicyUnitsProcessedinteger

GuardrailCoverageobject

The action of the guardrail coverage details.

textCharacters	GuardrailTextCharactersCoverage	The text characters of the guardrail coverage details.
images	GuardrailImageCoverage	The guardrail coverage for images (the number of images that guardrails guarded).

GuardrailCustomWordobject

A custom word configured in a guardrail.

match*	string	The match for the custom word.
action*	enum	The action for the custom word.	BLOCKED \| NONE
detected	boolean	Indicates whether custom word content that breaches the guardrail configuration is detected.

GuardrailCustomWordListGuardrailCustomWord[]

match*	string	The match for the custom word.
action*	enum	The action for the custom word.	BLOCKED \| NONE
detected	boolean	Indicates whether custom word content that breaches the guardrail configuration is detected.

GuardrailIdstring

length ≥ 0 · length ≤ 2048

GuardrailImageCoverageobject

The details of the guardrail image coverage.

guarded	integer	The count (integer) of images guardrails guarded.
total	integer	Represents the total number of images (integer) that were in the request (guarded and unguarded).

GuardrailInvocationMetricsobject

The invocation metrics for the guardrail.

guardrailProcessingLatency	integer	The processing latency details for the guardrail invocation metrics.
usage	GuardrailUsage	The usage details for the guardrail invocation metrics.
guardrailCoverage	GuardrailCoverage	The coverage details for the guardrail invocation metrics.

GuardrailManagedWordobject

A managed word configured in a guardrail.

match*	string	The match for the managed word.
type*	enum	The type for the managed word.	PROFANITY
action*	enum	The action for the managed word.	BLOCKED \| NONE
detected	boolean	Indicates whether managed word content that breaches the guardrail configuration is detected.

GuardrailManagedWordListGuardrailManagedWord[]

match*	string	The match for the managed word.
type*	enum	The type for the managed word.	PROFANITY
action*	enum	The action for the managed word.	BLOCKED \| NONE
detected	boolean	Indicates whether managed word content that breaches the guardrail configuration is detected.

GuardrailManagedWordTypeenum

PROFANITY

GuardrailOriginenum

REQUEST | ACCOUNT_ENFORCED | ORGANIZATION_ENFORCED

GuardrailOriginListGuardrailOrigin[]

GuardrailOutputTextstring

GuardrailOwnershipenum

SELF | CROSS_ACCOUNT

GuardrailPiiEntityFilterobject

A Personally Identifiable Information (PII) entity configured in a guardrail.

match*	string	The PII entity filter match.
type*	enum	The PII entity filter type.	ADDRESS \| AGE \| AWS_ACCESS_KEY \| AWS_SECRET_KEY \| CA_HEALTH_NUMBER \| CA_SOCIAL_INSURANCE_NUMBER · +25 more
action*	enum	The PII entity filter action.	ANONYMIZED \| BLOCKED \| NONE
detected	boolean	Indicates whether personally identifiable information (PII) that breaches the guardrail configuration is detected.

GuardrailPiiEntityFilterListGuardrailPiiEntityFilter[]

match*	string	The PII entity filter match.
type*	enum	The PII entity filter type.	ADDRESS \| AGE \| AWS_ACCESS_KEY \| AWS_SECRET_KEY \| CA_HEALTH_NUMBER \| CA_SOCIAL_INSURANCE_NUMBER · +25 more
action*	enum	The PII entity filter action.	ANONYMIZED \| BLOCKED \| NONE
detected	boolean	Indicates whether personally identifiable information (PII) that breaches the guardrail configuration is detected.

GuardrailPiiEntityTypeenum

GuardrailProcessingLatencyinteger

GuardrailRegexFilterobject

A Regex filter configured in a guardrail.

name	string	The regex filter name.
match	string	The regesx filter match.
regex	string	The regex query.
action*	enum	The region filter action.	ANONYMIZED \| BLOCKED \| NONE
detected	boolean	Indicates whether custom regex entities that breach the guardrail configuration are detected.

GuardrailRegexFilterListGuardrailRegexFilter[]

name	string	The regex filter name.
match	string	The regesx filter match.
regex	string	The regex query.
action*	enum	The region filter action.	ANONYMIZED \| BLOCKED \| NONE
detected	boolean	Indicates whether custom regex entities that breach the guardrail configuration are detected.

GuardrailSensitiveInformationPolicyActionenum

ANONYMIZED | BLOCKED | NONE

GuardrailSensitiveInformationPolicyAssessmentobject

The assessment for a Personally Identifiable Information (PII) policy.

piiEntities*	GuardrailPiiEntityFilter[]	The PII entities in the assessment.
regexes*	GuardrailRegexFilter[]	The regex queries in the assessment.

GuardrailSensitiveInformationPolicyFreeUnitsProcessedinteger

GuardrailSensitiveInformationPolicyUnitsProcessedinteger

GuardrailTextCharactersCoverageobject

The guardrail coverage for the text characters.

guarded	integer	The text characters that were guarded by the guardrail coverage.
total	integer	The total text characters by the guardrail coverage.

GuardrailTopicobject

Information about a topic guardrail.

name*	string	The name for the guardrail.
type*	enum	The type behavior that the guardrail should perform when the model detects the topic.	DENY
action*	enum	The action the guardrail should take when it intervenes on a topic.	BLOCKED \| NONE
detected	boolean	Indicates whether topic content that breaches the guardrail configuration is detected.

GuardrailTopicListGuardrailTopic[]

name*	string	The name for the guardrail.
type*	enum	The type behavior that the guardrail should perform when the model detects the topic.	DENY
action*	enum	The action the guardrail should take when it intervenes on a topic.	BLOCKED \| NONE
detected	boolean	Indicates whether topic content that breaches the guardrail configuration is detected.

GuardrailTopicPolicyActionenum

BLOCKED | NONE

GuardrailTopicPolicyAssessmentobject

A behavior assessment of a topic policy.

topics*

GuardrailTopic[]

The topics in the assessment.

GuardrailTopicPolicyUnitsProcessedinteger

GuardrailTopicTypeenum

DENY

GuardrailTraceAssessmentobject

A Top level guardrail trace object. For more information, see ConverseTrace .

modelOutput	GuardrailOutputText[]	The output from the model.
inputAssessment	GuardrailAssessmentMap	The input assessment.
outputAssessments	GuardrailAssessmentListMap	the output assessments.
actionReason	string	Provides the reason for the action taken when harmful content is detected.

GuardrailUsageobject

The details on the use of the guardrail.

topicPolicyUnits*	integer	The topic policy units processed by the guardrail.
contentPolicyUnits*	integer	The content policy units processed by the guardrail.
wordPolicyUnits*	integer	The word policy units processed by the guardrail.
sensitiveInformationPolicyUnits*	integer	The sensitive information policy units processed by the guardrail.
sensitiveInformationPolicyFreeUnits*	integer	The sensitive information policy free units processed by the guardrail.
contextualGroundingPolicyUnits*	integer	The contextual grounding policy units processed by the guardrail.
contentPolicyImageUnits	integer	The content policy image units processed by the guardrail.
automatedReasoningPolicyUnits	integer	The number of text units processed by the automated reasoning policy.
automatedReasoningPolicies	integer	The number of automated reasoning policies that were processed during the guardrail evaluation.

GuardrailVersionstring

GuardrailWordPolicyActionenum

BLOCKED | NONE

GuardrailWordPolicyAssessmentobject

The word policy assessment.

customWords*	GuardrailCustomWord[]	Custom words in the assessment.
managedWordLists*	GuardrailManagedWord[]	Managed word lists in the assessment.

GuardrailWordPolicyUnitsProcessedinteger

ImageBlockDeltaobject

A streaming delta event that contains incremental image data during streaming responses.

source	ImageSource	The incremental image source data for this delta event.
error	ErrorBlock	Error information if this image delta could not be processed.

ImageBlockStartobject

The initial event in a streaming image block that indicates the start of image content.

format*

enum

The format of the image data that will be streamed in subsequent delta events.

png | jpeg | gif | webp

ImageFormatenum

png | jpeg | gif | webp

ImagesGuardedinteger

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

ImagesTotalinteger

InternalServerExceptionobject

An internal server error occurred. For troubleshooting this error, see InternalFailure in the Amazon Bedrock User Guide

message

string

InvokedModelIdstring

Longinteger

MessageStartEventobject

The start of a message.

role*

enum

The role for the message.

user | assistant | system

MessageStopEventobject

The stop event for a message.

stopReason*	enum	The reason why the model stopped generating output.	end_turn \| tool_use \| max_tokens \| stop_sequence \| guardrail_intervened \| content_filtered · +3 more
additionalModelResponseFields	Document	The additional model response fields.

ModelOutputsGuardrailOutputText[]

ModelStreamErrorExceptionobject

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

message	string
originalStatusCode	integer	The original status code.	100 ≤ n ≤ 599
originalMessage	string	The original message.

NonBlankStringstring

NonNegativeIntegerinteger

n ≥ 0

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

PromptRouterTraceobject

A prompt router trace.

invokedModelId

string

The ID of the invoked model.

ReasoningContentBlockDeltaobject

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.

text	string	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.
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.

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

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

ServiceUnavailableExceptionobject

The service isn't currently available. For troubleshooting this error, see ServiceUnavailable in the Amazon Bedrock User Guide

message

string

StatusCodeinteger

100 ≤ n ≤ 599

StopReasonenum

Stringstring

TextCharactersGuardedinteger

TextCharactersTotalinteger

ThrottlingExceptionobject

Your request was denied due to exceeding the account quotas for Amazon Bedrock . For troubleshooting this error, see ThrottlingException in the Amazon Bedrock User Guide

message

string

TokenUsageobject

The tokens used in a message API inference call.

inputTokens*	integer	The number of tokens sent in the request to the model.	n ≥ 0
outputTokens*	integer	The number of tokens that the model generated for the request.	n ≥ 0
totalTokens*	integer	The total of input tokens and tokens generated by the model.	n ≥ 0
cacheReadInputTokens	integer	The number of input tokens read from the cache for the request.	n ≥ 0
cacheWriteInputTokens	integer	The number of input tokens written to the cache for the request.	n ≥ 0
cacheDetails	CacheDetail[]	Detailed breakdown of cache writes by TTL. Empty if no cache creation occurred. Sorted by TTL duration (1h before 5m).

TokenUsageCacheReadInputTokensIntegerinteger

n ≥ 0

TokenUsageCacheWriteInputTokensIntegerinteger

n ≥ 0

TokenUsageInputTokensIntegerinteger

n ≥ 0

TokenUsageOutputTokensIntegerinteger

n ≥ 0

TokenUsageTotalTokensIntegerinteger

n ≥ 0

ToolNamestring

length ≥ 1 · length ≤ 64

ToolResultBlockDeltaobject

Contains incremental updates to tool results information during streaming responses. This allows clients to build up tool results data progressively as the response is generated.

text	string	The reasoning the model used to return the output.
json	Document	The JSON schema for the tool result content block. see JSON Schema Reference .

ToolResultBlocksDeltaToolResultBlockDelta[]

text	string	The reasoning the model used to return the output.
json	Document	The JSON schema for the tool result content block. see JSON Schema Reference .

ToolResultBlockStartobject

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

toolUseId*	string	The ID of the tool that was used to generate this tool result block.	length ≥ 1 · length ≤ 64
type	string	The type for the tool that was used to generate this tool result block.
status	enum	The status of the tool result block.	success \| error

ToolResultStatusenum

success | error

ToolUseBlockDeltaobject

The delta for a tool use block.

input*

string

The input for a requested tool.

ToolUseBlockStartobject

The start of a tool use block. 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 is requesting to use.	length ≥ 1 · length ≤ 64
type	enum	The type for the tool request.	server_tool_use

ToolUseIdstring

length ≥ 1 · length ≤ 64

ToolUseTypeenum

server_tool_use

ValidationExceptionobject

The input fails to satisfy the constraints specified by Amazon Bedrock . For troubleshooting this error, see ValidationError in the Amazon Bedrock User Guide

message

string

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?kind=output

Response body

Types

AccountIdstring

AppliedGuardrailDetailsobject

AutomatedReasoningRuleIdentifierstring

Blobstring

Booleanboolean

CacheDetailobject

CacheDetailInputTokensIntegerinteger

CacheDetailsListCacheDetail[]

CacheTTLenum

CitationLocationobject

CitationsDeltaobject

CitationSourceContentDeltaobject

CitationSourceContentListDeltaCitationSourceContentDelta[]

ContentBlockDeltaobject

ContentBlockDeltaEventobject

ContentBlockStartobject

ContentBlockStartEventobject

ContentBlockStopEventobject

ConversationRoleenum

ConverseStreamMetadataEventobject

ConverseStreamMetricsobject

ConverseStreamTraceobject

Documentany

DocumentCharLocationobject

DocumentCharLocationDocumentIndexIntegerinteger

DocumentCharLocationEndIntegerinteger

DocumentCharLocationStartIntegerinteger

DocumentChunkLocationobject

DocumentChunkLocationDocumentIndexIntegerinteger

DocumentChunkLocationEndIntegerinteger

DocumentChunkLocationStartIntegerinteger

DocumentPageLocationobject

DocumentPageLocationDocumentIndexIntegerinteger

DocumentPageLocationEndIntegerinteger

DocumentPageLocationStartIntegerinteger

ErrorBlockobject

GuardrailArnstring

GuardrailAssessmentobject

GuardrailAssessmentListGuardrailAssessment[]

GuardrailAssessmentListMapobject

GuardrailAssessmentMapobject

GuardrailAutomatedReasoningDifferenceScenarioListGuardrailAutomatedReasoningScenario[]

GuardrailAutomatedReasoningFindingobject

GuardrailAutomatedReasoningFindingListGuardrailAutomatedReasoningFinding[]

GuardrailAutomatedReasoningImpossibleFindingobject

GuardrailAutomatedReasoningInputTextReferenceobject

GuardrailAutomatedReasoningInputTextReferenceListGuardrailAutomatedReasoningInputTextReference[]

GuardrailAutomatedReasoningInvalidFindingobject

GuardrailAutomatedReasoningLogicWarningobject

GuardrailAutomatedReasoningLogicWarningTypeenum

GuardrailAutomatedReasoningNoTranslationsFindingobject

GuardrailAutomatedReasoningPoliciesProcessedinteger

GuardrailAutomatedReasoningPolicyAssessmentobject

GuardrailAutomatedReasoningPolicyUnitsProcessedinteger

GuardrailAutomatedReasoningPolicyVersionArnstring

GuardrailAutomatedReasoningRuleobject

GuardrailAutomatedReasoningRuleListGuardrailAutomatedReasoningRule[]

GuardrailAutomatedReasoningSatisfiableFindingobject

GuardrailAutomatedReasoningScenarioobject

GuardrailAutomatedReasoningStatementobject

GuardrailAutomatedReasoningStatementListGuardrailAutomatedReasoningStatement[]

GuardrailAutomatedReasoningStatementLogicContentstring

GuardrailAutomatedReasoningStatementNaturalLanguageContentstring

GuardrailAutomatedReasoningTooComplexFindingobject

GuardrailAutomatedReasoningTranslationobject

GuardrailAutomatedReasoningTranslationAmbiguousFindingobject

GuardrailAutomatedReasoningTranslationConfidencenumber

GuardrailAutomatedReasoningTranslationListGuardrailAutomatedReasoningTranslation[]

GuardrailAutomatedReasoningTranslationOptionobject

GuardrailAutomatedReasoningTranslationOptionListGuardrailAutomatedReasoningTranslationOption[]

GuardrailAutomatedReasoningValidFindingobject

GuardrailContentFilterobject

GuardrailContentFilterConfidenceenum

GuardrailContentFilterListGuardrailContentFilter[]

GuardrailContentFilterStrengthenum

GuardrailContentFilterTypeenum

GuardrailContentPolicyActionenum