What Is Amazon Bedrock? Your First AI Agent API Call

Let's get acquainted with Amazon Bedrock. Instead of managing servers, you get a single API endpoint that connects to hundreds of foundation models, like Claude, Llama, Nova, Mistral, and more.

Series: GenAI and AI agents on AWS (2 articles)

1
GenAI and AI agents on AWS: set up the account before you write any code
2
What Is Amazon Bedrock? Your First AI Agent API Call This article

Olha Piliaieva

Published Oct 27, 2026

Last modified Oct 28, 2026

If you’ve ever tried adding an AI feature to an app, you know that you should set up a server, figure out GPU hosting, and spend half your week reading infrastructure docs. Cloud providers finally realized nobody wants to do that.
Let's get acquainted with Amazon Bedrock. Instead of managing servers, you get a single API endpoint that connects to hundreds of foundation models, like Claude, Llama, Nova, Mistral, and more.
No infrastructure: No servers or GPUs to configure.
﻿
Pay-per-token. You pay only for what you use.
Prompts and responses are not used to train models and are not shared with providers.
Inside you can find lists of over 200 serverless and marketplace models. You can filter by provider (Amazon Nova, Anthropic Claude, Meta Llama, etc.) to check parameters and capabilities.
Playground lets you test prompts in your browser before writing code. Pick a lightweight option like Amazon Nova 2 Light, give it a system prompt, and run a quick test.
Some models (like Meta Llama) have regional restrictions or licensing limits. Providers like Anthropic require a one-time use-case form per account (company name, website, industry, and use-case description) before granting model access.
Bedrock uses the Converse API, providing a uniform request structure across all models. The payload requires three main fields:  modelId ,  messages ,  inferenceConfig .
Python
import boto3
from config import REGION, MODEL_ID
﻿
bedrock = boto3.client("bedrock-runtime", region_name=REGION)
﻿
start = time.time()
response = bedrock.converse(
    modelId=MODEL_ID,
    messages=[{"role": "user", "content": [{"text": "Write a one-line welcome message for BrightCart, an online electronics store."}]}],
    inferenceConfig={"maxTokens": 200, "temperature": 0.5},
)
seconds = time.time() - start
﻿
print("Model:", MODEL_ID)
print("Answer:", response["output"]["message"]["content"][0]["text"])
usage = response["usage"]
print(f"Tokens: {usage['inputTokens']} in, {usage['outputTokens']} out · {seconds:.1f} s")
﻿
In  config.py 
Plain text
REGION = "us-east-1"
﻿
# Model IDs (copy the newest ones from Bedrock console > Model catalog > model card > "Inference profile ID")
NOVA = "us.amazon.nova-2-lite-v1:0"
CLAUDE = "global.anthropic.claude-sonnet-4-5-20250929-v1:0"
﻿
MODEL_ID = os.getenv("MODEL_ID", NOVA)
﻿
Two Metrics we have to monitor
Token Breakdown: Models process fragments of words called tokens, not raw text. You pay for both input tokens (your prompt) and output tokens (the generated response). Different models split text differently-the same prompt might cost 60 tokens on one model and 25 on another. Keep an eye on the usage stats returned in the API payload.
Temperature Setting: Controls randomness.
Low (0.1–0.3): Keeps outputs deterministic and grounded. Perfect for customer support, document parsing, or factual Q&A.
High (0.7–1.0): Adds variety and creative range. Great for marketing copy or creative brainstorming.
By using AWS Bedrock in combination with Python and Boto3, you gain a convenient and scalable way to run advanced large language models (LLMs) within your own infrastructure-without the need to configure servers or lose control over costs.
You can watch the full practical walkthrough in these videos:
 What is Amazon Bedrock  
 Amazon Bedrock Python Tutorial | Your First Bedrock API Call 
﻿
﻿
I’ll be sharing plenty of hands-on videos about AWS, AI and deployment on my YouTube channel,   @CodeAiFlow   every week. This article follows the second episode of the series, if you'd rather watch the setup step by step.
Source code for all upcoming hands-on episodes:   GitHub repository 