Amazon Bedrock
Describes the API operations for creating, managing, fine-turning, and evaluating Amazon Bedrock models.
Fork copies the collection into your workspace, without the publisher's secrets, so you can add your own key and send requests. Star saves it to your starred APIs (Account › Marketplace) and helps others find it.
Overview
Describes the API operations for creating, managing, fine-turning, and evaluating Amazon Bedrock models.
Endpoints 108
Advanced prompt optimization job
- POSTBatch delete advanced prompt optimization job
/advanced-prompt-optimization-job/batch-deleteDeletes one or more advanced prompt optimization jobs. - GETList advanced prompt optimization jobs
/advanced-prompt-optimization-jobs?maxResults=0&nextToken=string&sortBy=string&sortOrder=stringLists the advanced prompt optimization jobs in your account. - POSTCreate advanced prompt optimization job
/advanced-prompt-optimization-jobsCreates an advanced prompt optimization job. The job optimizes your prompt templates for specific models using your evaluation dataset and criteria. - GETGet advanced prompt optimization job
/advanced-prompt-optimization-jobs/:jobIdentifierGets information about an advanced prompt optimization job. - POSTStop advanced prompt optimization job
/advanced-prompt-optimization-jobs/:jobIdentifier/stopStops an advanced prompt optimization job that is in progress.
Evaluation job
- POSTBatch delete evaluation job
/evaluation-jobs/batch-deleteDeletes a batch of evaluation jobs. An evaluation job can only be deleted if it has following status FAILED , COMPLETED , and STOPPED . You can request up to… - GETList evaluation jobs
/evaluation-jobs?creationTimeAfter=string&creationTimeBefore=string&statusEquals=string&applicationTypeEquals=string&nameContains=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=stringLists all existing evaluation jobs. - POSTCreate evaluation job
/evaluation-jobsCreates an evaluation job. - GETGet evaluation job
/evaluation-jobs/:jobIdentifierGets information about an evaluation job, such as the status of the job. - POSTStop evaluation job
/evaluation-job/:jobIdentifier/stopStops an evaluation job that is current being created or running.
Automated reasoning policy
- POSTCancel automated reasoning policy build workflow
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowId/cancelCancels a running Automated Reasoning policy build workflow. This stops the policy generation process and prevents further processing of the source documents. - GETList automated reasoning policies
/automated-reasoning-policies?policyArn=string&nextToken=string&maxResults=0Lists all Automated Reasoning policies in your account, with optional filtering by policy ARN. This helps you manage and discover existing policies. - POSTCreate automated reasoning policy
/automated-reasoning-policiesCreates an Automated Reasoning policy for Amazon Bedrock Guardrails. Automated Reasoning policies use mathematical techniques to detect hallucinations,… - GETList automated reasoning policy test cases
/automated-reasoning-policies/:policyArn/test-cases?nextToken=string&maxResults=0Lists tests for an Automated Reasoning policy. We recommend using pagination to ensure that the operation returns quickly and successfully. - POSTCreate automated reasoning policy test case
/automated-reasoning-policies/:policyArn/test-casesCreates a test for an Automated Reasoning policy. Tests validate that your policy works as expected by providing sample inputs and expected outcomes. Use… - POSTCreate automated reasoning policy version
/automated-reasoning-policies/:policyArn/versionsCreates a new version of an existing Automated Reasoning policy. This allows you to iterate on your policy rules while maintaining previous versions for… - GETGet automated reasoning policy
/automated-reasoning-policies/:policyArnRetrieves details about an Automated Reasoning policy or policy version. Returns information including the policy definition, metadata, and timestamps. - DELETEDelete automated reasoning policy
/automated-reasoning-policies/:policyArn?force=trueDeletes an Automated Reasoning policy or policy version. This operation is idempotent. If you delete a policy more than once, each call succeeds. Deleting a… - PATCHUpdate automated reasoning policy
/automated-reasoning-policies/:policyArnUpdates an existing Automated Reasoning policy with new rules, variables, or configuration. This creates a new version of the policy while preserving the… - GETGet automated reasoning policy build workflow
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowIdRetrieves detailed information about an Automated Reasoning policy build workflow, including its status, configuration, and metadata. - DELETEDelete automated reasoning policy build workflow
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowId?updatedAt=stringDeletes an Automated Reasoning policy build workflow and its associated artifacts. This permanently removes the workflow history and any generated assets. - GETGet automated reasoning policy test case
/automated-reasoning-policies/:policyArn/test-cases/:testCaseIdRetrieves details about a specific Automated Reasoning policy test. - DELETEDelete automated reasoning policy test case
/automated-reasoning-policies/:policyArn/test-cases/:testCaseId?updatedAt=stringDeletes an Automated Reasoning policy test. This operation is idempotent; if you delete a test more than once, each call succeeds. - PATCHUpdate automated reasoning policy test case
/automated-reasoning-policies/:policyArn/test-cases/:testCaseIdUpdates an existing Automated Reasoning policy test. You can modify the content, query, expected result, and confidence threshold. - GETExport automated reasoning policy version
/automated-reasoning-policies/:policyArn/exportExports the policy definition for an Automated Reasoning policy version. Returns the complete policy definition including rules, variables, and custom… - GETGet automated reasoning policy annotations
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowId/annotationsRetrieves the current annotations for an Automated Reasoning policy build workflow. Annotations contain corrections to the rules, variables and types to be… - PATCHUpdate automated reasoning policy annotations
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowId/annotationsUpdates the annotations for an Automated Reasoning policy build workflow. This allows you to modify extracted rules, variables, and types before finalizing… - GETGet automated reasoning policy build workflow result assets
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowId/result-assets?assetType=string&assetId=stringRetrieves the resulting assets from a completed Automated Reasoning policy build workflow, including build logs, quality reports, and generated policy… - GETGet automated reasoning policy next scenario
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowId/scenariosRetrieves the next test scenario for validating an Automated Reasoning policy. This is used during the interactive policy refinement process to test policy… - GETGet automated reasoning policy test result
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowId/test-cases/:testCaseId/test-resultsRetrieves the test result for a specific Automated Reasoning policy test. Returns detailed validation findings and execution status. - GETList automated reasoning policy build workflows
/automated-reasoning-policies/:policyArn/build-workflows?nextToken=string&maxResults=0Lists all build workflows for an Automated Reasoning policy, showing the history of policy creation and modification attempts. - GETList automated reasoning policy test results
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowId/test-results?nextToken=string&maxResults=0Lists test results for an Automated Reasoning policy, showing how the policy performed against various test scenarios and validation checks. - POSTStart automated reasoning policy build workflow
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowType/startStarts a new build workflow for an Automated Reasoning policy. This initiates the process of analyzing source documents and generating policy rules,… - POSTStart automated reasoning policy test workflow
/automated-reasoning-policies/:policyArn/build-workflows/:buildWorkflowId/test-workflowsInitiates a test workflow to validate Automated Reasoning policy tests. The workflow executes the specified tests against the policy and generates validation…
Custom model
- POSTCreate custom model
/custom-models/create-custom-modelCreates a new custom model in Amazon Bedrock. After the model is active, you can use it for inference. You can provide the model data source in one of the… - GETGet custom model
/custom-models/:modelIdentifierGet the properties associated with a Amazon Bedrock custom model that you have created. For more information, see Custom models in the Amazon Bedrock User… - DELETEDelete custom model
/custom-models/:modelIdentifierDeletes a custom model that you created earlier. For more information, see Custom models in the Amazon Bedrock User Guide . - GETList custom models
/custom-models?creationTimeBefore=string&creationTimeAfter=string&nameContains=string&baseModelArnEquals=string&foundationModelArnEquals=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=string&isOwned=true&modelStatus=stringReturns a list of the custom models that you have created with the CreateModelCustomizationJob operation. For more information, see Custom models in the…
Custom model deployment
- GETList custom model deployments
/model-customization/custom-model-deployments?createdBefore=string&createdAfter=string&nameContains=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=string&statusEquals=string&modelArnEquals=stringLists custom model deployments in your account. You can filter the results by creation time, name, status, and associated model. Use this operation to manage… - POSTCreate custom model deployment
/model-customization/custom-model-deploymentsDeploys a custom model for on-demand inference in Amazon Bedrock. After you deploy your custom model, you use the deployment's Amazon Resource Name (ARN) as… - GETGet custom model deployment
/model-customization/custom-model-deployments/:customModelDeploymentIdentifierRetrieves information about a custom model deployment, including its status, configuration, and metadata. Use this operation to monitor the deployment status… - DELETEDelete custom model deployment
/model-customization/custom-model-deployments/:customModelDeploymentIdentifierDeletes a custom model deployment. This operation stops the deployment and removes it from your account. After deletion, the deployment ARN can no longer be… - PATCHUpdate custom model deployment
/model-customization/custom-model-deployments/:customModelDeploymentIdentifierUpdates a custom model deployment with a new custom model. This allows you to deploy updated models without creating new deployment endpoints.
Subscription
- POSTCreate foundation model agreement
/create-foundation-model-agreementRequest a model access agreement for the specified model. - POSTDelete foundation model agreement
/delete-foundation-model-agreementDelete the model access agreement for the specified model. - GETGet foundation model availability
/foundation-model-availability/:modelIdGet information about the Foundation model availability. - GETList foundation model agreement offers
/list-foundation-model-agreement-offers/:modelId?offerType=stringGet the offers associated with the specified model.
Guardrails
- GETList guardrails
/guardrails?guardrailIdentifier=string&maxResults=0&nextToken=stringLists details about all the guardrails in an account. To list the DRAFT version of all your guardrails, don't specify the guardrailIdentifier field. To list… - POSTCreate guardrail
/guardrailsCreates a guardrail to block topics and to implement safeguards for your generative AI applications. You can configure the following policies in a guardrail… - GETGet guardrail
/guardrails/:guardrailIdentifier?guardrailVersion=stringGets details about a guardrail. If you don't specify a version, the response returns details for the DRAFT version. - PUTUpdate guardrail
/guardrails/:guardrailIdentifierUpdates a guardrail with the values you specify. Specify a name and optional description . Specify messages for when the guardrail successfully blocks a… - POSTCreate guardrail version
/guardrails/:guardrailIdentifierCreates a version of the guardrail. Use this API to create a snapshot of the guardrail when you are satisfied with a configuration, or to compare the… - DELETEDelete guardrail
/guardrails/:guardrailIdentifier?guardrailVersion=stringDeletes a guardrail. To delete a guardrail, only specify the ARN of the guardrail in the guardrailIdentifier field. If you delete a guardrail, all of its…
Inference profile
- GETList inference profiles
/inference-profiles?maxResults=0&nextToken=string&type=stringReturns a list of inference profiles that you can use. For more information, see Increase throughput and resilience with cross-region inference in Amazon… - POSTCreate inference profile
/inference-profilesCreates an application inference profile to track metrics and costs when invoking a model. To create an application inference profile for a foundation model… - GETGet inference profile
/inference-profiles/:inferenceProfileIdentifierGets information about an inference profile. For more information, see Increase throughput and resilience with cross-region inference in Amazon Bedrock . in… - DELETEDelete inference profile
/inference-profiles/:inferenceProfileIdentifierDeletes an application inference profile. For more information, see Increase throughput and resilience with cross-region inference in Amazon Bedrock . in the…
Bedrock marketplace
- GETList marketplace model endpoints
/marketplace-model/endpoints?maxResults=0&nextToken=string&modelSourceIdentifier=stringLists the endpoints for models from Amazon Bedrock Marketplace in your Amazon Web Services account. - POSTCreate marketplace model endpoint
/marketplace-model/endpointsCreates an endpoint for a model from Amazon Bedrock Marketplace. The endpoint is hosted by Amazon SageMaker. - GETGet marketplace model endpoint
/marketplace-model/endpoints/:endpointArnRetrieves details about a specific endpoint for a model from Amazon Bedrock Marketplace. - DELETEDelete marketplace model endpoint
/marketplace-model/endpoints/:endpointArnDeletes an endpoint for a model from Amazon Bedrock Marketplace. - PATCHUpdate marketplace model endpoint
/marketplace-model/endpoints/:endpointArnUpdates the configuration of an existing endpoint for a model from Amazon Bedrock Marketplace. - DELETEDeregister marketplace model endpoint
/marketplace-model/endpoints/:endpointArn/registrationDeregisters an endpoint for a model from Amazon Bedrock Marketplace. This operation removes the endpoint's association with Amazon Bedrock but does not delete… - POSTRegister marketplace model endpoint
/marketplace-model/endpoints/:endpointIdentifier/registrationRegisters an existing Amazon SageMaker endpoint with Amazon Bedrock Marketplace, allowing it to be used with Amazon Bedrock APIs.
Model copy
- GETList model copy jobs
/model-copy-jobs?creationTimeAfter=string&creationTimeBefore=string&statusEquals=string&sourceAccountEquals=string&sourceModelArnEquals=string&outputModelNameContains=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=stringReturns a list of model copy jobs that you have submitted. You can filter the jobs to return based on one or more criteria. For more information, see Copy… - POSTCreate model copy job
/model-copy-jobsCopies a model to another region so that it can be used there. For more information, see Copy models to be used in other regions in the Amazon Bedrock User… - GETGet model copy job
/model-copy-jobs/:jobArnRetrieves information about a model copy job. For more information, see Copy models to be used in other regions in the Amazon Bedrock User Guide .
Training
- GETList model customization jobs
/model-customization-jobs?creationTimeAfter=string&creationTimeBefore=string&statusEquals=string&nameContains=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=stringReturns a list of model customization jobs that you have submitted. You can filter the jobs to return based on one or more criteria. For more information, see… - POSTCreate model customization job
/model-customization-jobsCreates a fine-tuning job to customize a base model. You specify the base foundation model and the location of the training data. After the… - GETGet model customization job
/model-customization-jobs/:jobIdentifierRetrieves the properties associated with a model-customization job, including the status of the job. For more information, see Custom models in the Amazon… - POSTStop model customization job
/model-customization-jobs/:jobIdentifier/stopStops an active model customization job. For more information, see Custom models in the Amazon Bedrock User Guide .
Model import
- GETList model import jobs
/model-import-jobs?creationTimeAfter=string&creationTimeBefore=string&statusEquals=string&nameContains=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=stringReturns a list of import jobs you've submitted. You can filter the results to return based on one or more criteria. For more information, see Import a… - POSTCreate model import job
/model-import-jobsCreates a model import job to import model that you have customized in other environments, such as Amazon SageMaker. For more information, see Import a… - GETGet imported model
/imported-models/:modelIdentifierGets properties associated with a customized model you imported. - DELETEDelete imported model
/imported-models/:modelIdentifierDeletes a custom model that you imported earlier. For more information, see Import a customized model in the Amazon Bedrock User Guide . - GETGet model import job
/model-import-jobs/:jobIdentifierRetrieves the properties associated with import model job, including the status of the job. For more information, see Import a customized model in the Amazon… - GETList imported models
/imported-models?creationTimeBefore=string&creationTimeAfter=string&nameContains=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=stringReturns a list of models you've imported. You can filter the results to return based on one or more criteria. For more information, see Import a customized…
Model invocation job
- POSTCreate model invocation job
/model-invocation-jobCreates a batch inference job to invoke a model on multiple prompts. Format your data according to Format your inference data and upload it to an Amazon S3… - GETGet model invocation job
/model-invocation-job/:jobIdentifierGets details about a batch inference job. For more information, see Monitor batch inference jobs - GETList model invocation jobs
/model-invocation-jobs?submitTimeAfter=string&submitTimeBefore=string&statusEquals=string&nameContains=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=stringLists all batch inference jobs in the account. For more information, see View details about a batch inference job . - POSTStop model invocation job
/model-invocation-job/:jobIdentifier/stopStops a batch inference job. You're only charged for tokens that were already processed. For more information, see Stop a batch inference job .
Prompt router
- GETList prompt routers
/prompt-routers?maxResults=0&nextToken=string&type=stringRetrieves a list of prompt routers. - POSTCreate prompt router
/prompt-routersCreates a prompt router that manages the routing of requests between multiple foundation models based on the routing criteria. - GETGet prompt router
/prompt-routers/:promptRouterArnRetrieves details about a prompt router. - DELETEDelete prompt router
/prompt-routers/:promptRouterArnDeletes a specified prompt router. This action cannot be undone.
Provisioned model throughput
- POSTCreate provisioned model throughput
/provisioned-model-throughputCreates dedicated throughput for a base or custom model with the model units and for the duration that you specify. For pricing details, see Amazon Bedrock… - GETGet provisioned model throughput
/provisioned-model-throughput/:provisionedModelIdReturns details for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide . - DELETEDelete provisioned model throughput
/provisioned-model-throughput/:provisionedModelIdDeletes a Provisioned Throughput. You can't delete a Provisioned Throughput before the commitment term is over. For more information, see Provisioned… - PATCHUpdate provisioned model throughput
/provisioned-model-throughput/:provisionedModelIdUpdates the name or associated model for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide . - GETList provisioned model throughputs
/provisioned-model-throughputs?creationTimeAfter=string&creationTimeBefore=string&statusEquals=string&modelArnEquals=string&nameContains=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=stringLists the Provisioned Throughputs in the account. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide .
Enforced guardrail configuration
- DELETEDelete enforced guardrail configuration
/enforcedGuardrailsConfiguration/:configIdDeletes the account-level enforced guardrail configuration. - GETList enforced guardrails configuration
/enforcedGuardrailsConfiguration?nextToken=stringLists the account-level enforced guardrail configurations. - PUTPut enforced guardrail configuration
/enforcedGuardrailsConfigurationSets the account-level enforced guardrail configuration.
Logging
- GETGet model invocation logging configuration
/logging/modelinvocationsGet the current configuration values for model invocation logging. - PUTPut model invocation logging configuration
/logging/modelinvocationsSet the configuration values for model invocation logging. - DELETEDelete model invocation logging configuration
/logging/modelinvocationsDelete the invocation logging.
Resource policy
- GETGet resource policy
/resource-policy/:resourceArnGets the resource policy document for a Bedrock resource - DELETEDelete resource policy
/resource-policy/:resourceArnDeletes a previously created Bedrock resource policy. - POSTPut resource policy
/resource-policyAdds a resource policy for a Bedrock resource.
Data retention
- GETGet account data retention
/data-retentionReturns the account-wide data retention mode for Amazon Bedrock. - PUTPut account data retention
/data-retentionSets the account-wide data retention mode for Amazon Bedrock.
Model
- GETGet foundation model
/foundation-models/:modelIdentifierGet details about a Amazon Bedrock foundation model. - GETList foundation models
/foundation-models?byProvider=string&byCustomizationType=string&byOutputModality=string&byInferenceType=stringLists Amazon Bedrock foundation models that you can use. You can filter the results with the request parameters. For more information, see Foundation models…
Allowlist
- GETGet use case for model access
/use-case-for-model-accessGet usecase for model access. - POSTPut use case for model access
/use-case-for-model-accessPut usecase for model access.
Tagging
- POSTList tags for resource
/listTagsForResourceList the tags associated with the specified resource. For more information, see Tagging resources in the Amazon Bedrock User Guide . - POSTTag resource
/tagResourceAssociate tags with a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide . - POSTUntag resource
/untagResourceRemove one or more tags from a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide .
API details
- Base URL
https://bedrock.{region}.amazonaws.com- Authentication
- AWS Signature Version 4 (requests signed with your AWS access key)
- Operations
- 108 operations on 71 pathsGET 49POST 34DELETE 15PATCH 6PUT 4
- Main resources
- Automated reasoning policy 24Bedrock marketplace 7Guardrails 6Model import 6Advanced prompt optimization job 5Custom model deployment 5Evaluation job 5Provisioned model throughput 5Custom model 4Inference profile 4
- Description format
- AWS Smithy model, API version
2023-04-20 - Links
- Documentation · OpenAPI document
- Listed from
- AWS Smithy API model (aws/api-models-aws) (Apache-2.0)
How to test the Amazon Bedrock in Swastik Codes
- Open the APISelect “Fork & run in Swastik Codes” on this page. Sign in or create a free account if asked.
- Fork it into your workspaceChoose a workspace. You get your own copy of the Amazon Bedrock collection, without the publisher's secrets.
- Add your credentialsThis API uses AWS Signature Version 4 (requests signed with your AWS access key). Add yours in the collection's variables or an environment; the requests already reference it.
- Send a requestPick an endpoint, for example “Batch delete advanced prompt optimization job” (POST /advanced-prompt-optimization-job/batch-delete), and press Send. Check the response, add tests and run the whole collection with the runner.
Frequently asked questions
What is the Amazon Bedrock?
Describes the API operations for creating, managing, fine-turning, and evaluating Amazon Bedrock models. It is listed under AI & machine learning and has 108 endpoints.
Who publishes the Amazon Bedrock?
It is listed from Amazon Web Services, Inc.'s public API description (an OpenAPI document), not published by Amazon Web Services, Inc. on Swastik Codes. Anyone who controls amazonaws.com can claim the profile by adding a DNS TXT record.
What is the base URL of the Amazon Bedrock?
Requests go to https://bedrock.{region}.amazonaws.com. Endpoint paths are added to this base URL.
How do I authenticate with the Amazon Bedrock?
With AWS Signature Version 4 (requests signed with your AWS access key).
How many endpoints does the Amazon Bedrock have?
108 operations on 71 paths (49 GET, 34 POST, 15 DELETE, 6 PATCH, 4 PUT). The largest groups are Automated reasoning policy, Bedrock marketplace, Guardrails, Model import.
Is forking the Amazon Bedrock free?
Yes. Forking copies the collection into your workspace for free. It has been starred 0 times and forked 0 times.