How to beginner · 3 min read

How to get started with AWS Bedrock

Q: How to get started with AWS Bedrock

To get started with AWS Bedrock, use the boto3 Python client with the bedrock-runtime service. Initialize the client, then call converse or invoke_model with your chosen Bedrock model ID and chat messages to generate AI completions.

Quick answer

To get started with AWS Bedrock, use the boto3 Python client with the bedrock-runtime service. Initialize the client, then call converse or invoke_model with your chosen Bedrock model ID and chat messages to generate AI completions.

PREREQUISITES

Python 3.8+
AWS account with Bedrock access
AWS CLI configured or environment variables for AWS credentials
pip install boto3

Setup

Install the boto3 library to interact with AWS Bedrock. Ensure your AWS credentials are configured via ~/.aws/credentials or environment variables AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY. You also need Bedrock access enabled in your AWS account.

bash

pip install boto3

Step by step

This example shows how to create a boto3 client for Bedrock and send a chat completion request using the converse method with a Claude model. Replace modelId with your Bedrock model identifier.

python

import os
import boto3

# Initialize Bedrock client
client = boto3.client('bedrock-runtime', region_name='us-east-1')

# Define model ID and messages
model_id = 'anthropic.claude-3-5-sonnet-20241022-v2:0'
messages = [
    {"role": "user", "content": [{"type": "text", "text": "Hello, AWS Bedrock!"}]}
]

# Call converse API
response = client.converse(
    modelId=model_id,
    messages=messages,
    maxTokens=100
)

# Extract and print the AI response
print(response['message']['content'][0]['text'])

output

Hello, AWS Bedrock! How can I assist you today?

Common variations

Use invoke_model for raw JSON payloads instead of converse.
Change modelId to other Bedrock models like amazon.titan-text-express-v1 or meta.llama3-1-70b-instruct-v1:0.
Adjust maxTokens and other parameters for response length and temperature.
Use AWS SDK async clients or other languages as needed.

Troubleshooting

If you get AccessDeniedException, verify your AWS IAM permissions include Bedrock access.
For ModelNotFoundException, confirm the modelId is correct and available in your region.
Ensure your AWS credentials are properly configured and environment variables are set.
Check your AWS region matches the Bedrock service availability.

✅

Key Takeaways

Use the boto3 client with service name 'bedrock-runtime' to access AWS Bedrock.
Call the 'converse' method with modelId and messages for chat completions.
Configure AWS credentials and region properly to avoid access errors.

Verified 2026-04 · anthropic.claude-3-5-sonnet-20241022-v2:0, amazon.titan-text-express-v1, meta.llama3-1-70b-instruct-v1:0

Verify ↗