Amazon Bedrock Runtime
Describes the API operations for running inference using 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 running inference using Amazon Bedrock models.
Endpoints 11
Guardrail
- POSTApply guardrail
/guardrail/:guardrailIdentifier/version/:guardrailVersion/applyThe action to apply a guardrail. For troubleshooting some of the common errors you might encounter when using the ApplyGuardrail API, see Troubleshooting… - POSTInvoke guardrail checks
/guardrail-checks/invokeEvaluates messages against inline guardrail checks. You specify the check configurations directly in the request, and Amazon Bedrock returns per-check results…
Inference
- POSTConverse
/model/:modelId/converseSends messages to the specified Amazon Bedrock model. Converse provides a consistent interface that works with all models that support messages. This allows… - POSTConverse stream
/model/:modelId/converse-streamSends messages to the specified Amazon Bedrock model and returns the response in a stream. ConverseStream provides a consistent API that works with all Amazon… - POSTInvoke model
/model/:modelId/invokeInvokes the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. You use model inference to… - POSTInvoke model with bidirectional stream
/model/:modelId/invoke-with-bidirectional-streamInvoke the specified Amazon Bedrock model to run inference using the bidirectional stream. The response is returned in a stream that remains open for 8… - POSTInvoke model with response stream
/model/:modelId/invoke-with-response-streamInvoke the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. The response is returned in…
Tokenizer
- POSTCount tokens
/model/:modelId/count-tokensReturns the token count for a given inference request. This operation helps you estimate token usage before sending requests to foundation models by returning…
Async invoke
- GETGet async invoke
/async-invoke/:invocationArnRetrieve information about an asynchronous invocation. - GETList async invokes
/async-invoke?submitTimeAfter=string&submitTimeBefore=string&statusEquals=string&maxResults=0&nextToken=string&sortBy=string&sortOrder=stringLists asynchronous invocations. - POSTStart async invoke
/async-invokeStarts an asynchronous invocation. This operation requires permission for the bedrock:InvokeModel action. To deny all inference access to resources that you…
API details
- Base URL
https://bedrock-runtime.{region}.amazonaws.com- Authentication
- AWS Signature Version 4 (requests signed with your AWS access key)
- Operations
- 11 operations on 10 pathsPOST 9GET 2
- Main resources
- Inference 5Async invoke 3Guardrail 2Tokenizer 1
- Description format
- AWS Smithy model, API version
2023-09-30 - Links
- Documentation · OpenAPI document
- Listed from
- AWS Smithy API model (aws/api-models-aws) (Apache-2.0)
How to test the Amazon Bedrock Runtime 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 Runtime 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 “Apply guardrail” (POST /guardrail/:guardrailIdentifier/version/:guardrailVersion/apply), and press Send. Check the response, add tests and run the whole collection with the runner.
Frequently asked questions
What is the Amazon Bedrock Runtime?
Describes the API operations for running inference using Amazon Bedrock models. It is listed under AI & machine learning and has 11 endpoints.
Who publishes the Amazon Bedrock Runtime?
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 Runtime?
Requests go to https://bedrock-runtime.{region}.amazonaws.com. Endpoint paths are added to this base URL.
How do I authenticate with the Amazon Bedrock Runtime?
With AWS Signature Version 4 (requests signed with your AWS access key).
How many endpoints does the Amazon Bedrock Runtime have?
11 operations on 10 paths (9 POST, 2 GET). The largest groups are Inference, Async invoke, Guardrail, Tokenizer.
Is forking the Amazon Bedrock Runtime free?
Yes. Forking copies the collection into your workspace for free. It has been starred 0 times and forked 0 times.