How to beginner · 3 min read

How to use Bedrock invoke_model API

Q: How to use Bedrock invoke_model API

Use the boto3 client for bedrock-runtime to call invoke_model with the model ID and messages formatted as JSON. This method sends chat or text inputs to Bedrock models and returns the generated output in the response.

Quick answer

Use the boto3 client for bedrock-runtime to call invoke_model with the model ID and messages formatted as JSON. This method sends chat or text inputs to Bedrock models and returns the generated output in the response.

PREREQUISITES

Python 3.8+
AWS account with Bedrock access
AWS credentials configured (~/.aws/credentials or environment variables)
pip install boto3

Setup

Install the boto3 library and configure your AWS credentials with Bedrock permissions. Ensure you have access to Bedrock models and the bedrock-runtime client is available in your AWS SDK.

bash

pip install boto3

Step by step

This example shows how to invoke a Bedrock model using boto3 with the invoke_model API. It sends a chat message and prints the model's response.

python

import os
import json
import boto3

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

# Define the model ID for the Bedrock model you want to use
model_id = 'anthropic.claude-3-5-sonnet-20241022-v2:0'

# Prepare the chat messages payload
messages = [
    {"role": "user", "content": [{"type": "text", "text": "Hello from Bedrock!"}]}
]

# Construct the request body as JSON string
body = json.dumps({
    "anthropic_version": "bedrock-2023-05-31",
    "max_tokens": 512,
    "messages": messages
})

# Call invoke_model API
response = client.invoke_model(
    modelId=model_id,
    body=body
)

# Parse the response body
response_body = json.loads(response['body'].read())

# Extract the generated text
output_text = response_body['output']['message']['content'][0]['text']

print("Model response:", output_text)

output

Model response: Hello from Bedrock! How can I assist you today?

Common variations

Change modelId to use other Bedrock models like amazon.titan-text-express-v1 or meta.llama3-1-70b-instruct-v1:0.
Adjust max_tokens and other parameters in the JSON body to control output length and behavior.
Use client.converse() for simpler chat interactions if supported.
Set region_name in boto3.client to your Bedrock region.

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.
If response['body'] is empty or malformed, check network connectivity and AWS SDK version.
Ensure your AWS credentials are properly configured in environment variables or AWS config files.

✅

Key Takeaways

Use boto3's bedrock-runtime client with invoke_model to call Bedrock AI models.
Format the request body as a JSON string with messages and parameters.
Check AWS IAM permissions and model IDs if you encounter 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 ↗