Claude Academy
Loading

Making a request

Lesson 310 min

Making your first API request to AWS Bedrock requires three essential components: a Bedrock Runtime Client to connect to the service, a Model ID to specify which model you want to run, and a User Message containing the text you want to feed into the model.

Setting Up the Bedrock Client

Start by creating a client using boto3 to connect to the Bedrock runtime service:

python
import boto3

client = boto3.client("bedrock-runtime", region_name="us-west-2")

Understanding Model IDs and Regional Availability

Here's where things get tricky. Not every model is available in every AWS region. If you try to run a model that doesn't exist in your chosen region, you'll get a cryptic error message saying the model doesn't exist.

Request to run model ID "anthropic.claude-v1" arriving at the AWS region us-west-2, where that model is named Claude Sonnet.

For example, if Claude Sonnet is available in us-west-2 but you're making requests from us-east-1, your request will fail.

A request to run model ID "anthropic.claude-v1" returns an error in us-east-1, which has no model, but it is in us-west-2.

Using Inference Profiles

Inference profiles solve the regional availability problem by automatically routing your requests to a region where your chosen model is actually hosted.

Example inference profile named US Anthropic Claude Sonnet: profile ID us.profile.claude-v1, model ID anthropic.claude-v1.

Instead of tracking which models are in which regions, you can use an inference profile that knows the model is available in multiple regions like us-west-2 and us-east-2.

A request to run inference profile "us.profile.claude-v1" in us-east-1 is routed to anthropic.claude-v1 in us-west-2.

When you make a request using an inference profile, AWS automatically routes it to the correct region where your model exists, even if you're connecting from a different region.

To find inference profile IDs, go to the AWS Bedrock console and look under "Cross-region inference" rather than using the model ID from the main model catalog page.

AWS Bedrock console, Cross-region inference page, listing inference profiles with a copy button beside each profile ID.

Copy the inference profile ID for your chosen model. The examples in this course use Claude Haiku 4.5, whose inference profile ID is us.anthropic.claude-haiku-4-5-20251001-v1:0.

Creating User Messages

User messages have a specific structure that might look overly complex at first, but there's a good reason for it:

python
user_message = {
    "role": "user",
    "content": [
        {"text": "What's 1+1?"}
    ]
}

The content is a list because a single message can contain different types of content - text, images, or other media types. This structure allows you to send multimodal requests.

A user message whose content list holds an image block, format png with source bytes, then the text "What's in this image?".

Making the Request

Now you can make your API call using the converse method:

python
response = client.converse(
    modelId=model_id,
    messages=[user_message]
)

The response contains a lot of metadata, but to get just the generated text, you need to navigate through the response structure:

python
response["output"]["message"]["content"][0]["text"]

Understanding Message Types

There are two main message types you'll work with:

  • User messages - Content you want to feed into the model (role: "user")
  • Assistant messages - Content the model has produced (role: "assistant")

Chat window labeling the message "Define quantum computing" as the user message and the AI reply as the assistant message.

Both message types follow the same structure with a role and content list. This consistency makes it easy to build conversations by alternating between user and assistant messages.

The assistant message you get back from Bedrock follows the exact same format as your user message, just with a different role. This standardized structure makes it straightforward to chain multiple requests together for longer conversations.