QVeris
Connect your AI
Back to providers
Amazon Bedrock (GenAI Platform)
Provider profileAvailable in QVeris

Amazon Bedrock (GenAI Platform)

Amazon Bedrock is a fully managed service for importing and customizing foundation models via API and console.

Cloud & InfrastructureAi MlGenerative AiAi Text GenerationMl PlatformCode Generation
Official website

Continue with this provider

This provider-level handoff preserves only its public ID. No tool or business task is guessed; choose a current tool during rediscovery before setup can be treated as complete.

Selected provider
amazon_bedrock
Selected tool
Unknown — confirm during rediscovery
Business task
Unknown — confirm during rediscovery
Catalog updated
Unknown — confirm during rediscovery
Continue setupThe Plugins page keeps a safe link back to this provider profile.
Tools
7
Ready to inspect and call
Capabilities
Unknown
Covered task areas
Success
100.0%
Recent call reliability
Latency
744ms
Typical response time
From
1 credits
QVeris credits
Converse

Sends messages to a foundation model and receives a response in a conversational format.

AIConversationalLlmSample: modelId, messages
1 credit / call
100.0%
744ms
Inspect
Create Foundation Model Agreement

Creates an agreement for using a foundation model in Amazon Bedrock.

Machine LearningAIFoundation ModelsSample: modelArn, agreementType
1 credit / call
Unknown
Latency unavailable
Inspect
List Imported Models

List the imported models in Amazon Bedrock.

AIModelsAI & Machine Learning
1 credit / call
Unknown
Latency unavailable
Inspect
ApplyGuardrail

Applies a guardrail to input text or conversation history to enforce safety and compliance policies.

AISafetyLlmSample: text, guardrailVersion, guardrailIdentifier
1 credit / call
Unknown
Latency unavailable
Inspect
ConverseStream

Streams responses from a foundation model in a conversational format.

AIStreamingConversationalSample: modelId, messages
1 credit / call
Unknown
Latency unavailable
Inspect
CountTokens

Counts the number of tokens in the input text for a given foundation model.

AITokenizationLlmSample: text, modelId
1 credit / call
Unknown
Latency unavailable
Inspect
StartAsyncInvoke

Starts an asynchronous invocation of a foundation model.

AIAsyncLlm
1 credit / call
Unknown
Latency unavailable
Inspect