AI & Machine Learning AWS Signature Version 4

AWS Bedrock REST API

Fully managed foundation model API from AWS

AWS Bedrock is a fully managed service that provides access to foundation models from leading AI companies through a unified API. Developers use Bedrock to build and scale generative AI applications with models from Anthropic, Meta, Stability AI, and Amazon without managing infrastructure. The service includes fine-tuning capabilities, model customization, and enterprise-grade security for production AI workloads.

Base URL https://bedrock-runtime.us-east-1.amazonaws.com

API Endpoints

Method	Endpoint	Description
POST	`/model/{modelId}/invoke`	Invoke a foundation model with a single prompt and get a response
POST	`/model/{modelId}/invoke-with-response-stream`	Invoke a foundation model and stream the response back in real-time
POST	`/model/{modelId}/converse`	Send messages in a conversational format with support for multi-turn dialogues
POST	`/model/{modelId}/converse-stream`	Stream conversational responses for interactive chat applications
GET	`/foundation-models`	List all available foundation models in the current region
GET	`/foundation-models/{modelId}`	Get detailed information about a specific foundation model
POST	`/model-customization-jobs`	Create a fine-tuning job to customize a foundation model
GET	`/model-customization-jobs/{jobIdentifier}`	Get the status and details of a model customization job
GET	`/custom-models`	List all custom models created through fine-tuning
DELETE	`/custom-models/{modelIdentifier}`	Delete a custom model that is no longer needed
POST	`/provisioned-model-throughput`	Purchase provisioned throughput for consistent model performance
GET	`/provisioned-model-throughput/{provisionedModelId}`	Get details about provisioned throughput allocation
POST	`/guardrails`	Create a guardrail to filter harmful content and enforce policies
POST	`/model/{modelId}/apply-guardrail`	Apply a guardrail configuration to model invocations
GET	`/model-invocation-jobs/{jobIdentifier}`	Get the status of a batch inference job

Code Examples

curl -X POST https://bedrock-runtime.us-east-1.amazonaws.com/model/anthropic.claude-3-sonnet-20240229-v1:0/invoke \
  -H 'Content-Type: application/json' \
  -H 'Authorization: AWS4-HMAC-SHA256 Credential=AKIAIOSFODNN7EXAMPLE/20240101/us-east-1/bedrock/aws4_request, SignedHeaders=content-type;host;x-amz-date, Signature=...' \
  -d '{
    "anthropic_version": "bedrock-2023-05-31",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "What are the benefits of serverless computing?"
      }
    ]
  }'

import { BedrockRuntimeClient, InvokeModelCommand } from '@aws-sdk/client-bedrock-runtime';

const client = new BedrockRuntimeClient({ region: 'us-east-1' });

const input = {
  modelId: 'anthropic.claude-3-sonnet-20240229-v1:0',
  contentType: 'application/json',
  accept: 'application/json',
  body: JSON.stringify({
    anthropic_version: 'bedrock-2023-05-31',
    max_tokens: 1024,
    messages: [
      {
        role: 'user',
        content: 'What are the benefits of serverless computing?'
      }
    ]
  })
};

const command = new InvokeModelCommand(input);
const response = await client.send(command);
const result = JSON.parse(new TextDecoder().decode(response.body));
console.log(result.content[0].text);

import boto3
import json

client = boto3.client(
    service_name='bedrock-runtime',
    region_name='us-east-1'
)

prompt_data = {
    'anthropic_version': 'bedrock-2023-05-31',
    'max_tokens': 1024,
    'messages': [
        {
            'role': 'user',
            'content': 'What are the benefits of serverless computing?'
        }
    ]
}

response = client.invoke_model(
    modelId='anthropic.claude-3-sonnet-20240229-v1:0',
    contentType='application/json',
    accept='application/json',
    body=json.dumps(prompt_data)
)

result = json.loads(response['body'].read())
print(result['content'][0]['text'])

Use AWS Bedrock from Claude / Cursor / ChatGPT

Get a hosted MCP endpoint for AWS Bedrock. Paste your AWS Bedrock API key, copy back one URL, drop it into Claude Desktop, Cursor, or any AI client that supports remote MCP. Your AI calls AWS Bedrock directly with your credentials — no local install, works on mobile.

invoke_bedrock_model Invoke any AWS Bedrock foundation model with a prompt and return the generated response

stream_bedrock_response Stream responses from Bedrock models in real-time for interactive applications

list_available_models Retrieve all available foundation models with their capabilities and pricing information

create_custom_model Start a fine-tuning job to create a custom model based on training data

apply_content_guardrails Apply guardrails to filter harmful content and enforce usage policies on model outputs

Connect in 60 seconds

Paste your AWS Bedrock key → get an MCP URL → paste into Claude/Cursor. Hosted by IOX, encrypted at rest.

Connect AWS Bedrock to your AI →

AWS Bedrock REST API

API Endpoints

Sponsor this page

Code Examples

Use AWS Bedrock from Claude / Cursor / ChatGPT

Connect in 60 seconds

Related APIs