Amazon Bedrock

SideSeat automatically extracts model information, token usage, and costs from Amazon Bedrock API calls.

Prerequisites

• SideSeat running locally (sideseat)
• SDK installed (pip install sideseat / uv add sideseat or npm install @sideseat/sdk)
• AWS credentials configured for Amazon Bedrock

Usage with Boto3

from sideseat import SideSeat
SideSeat()

import boto3
import json

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

response = bedrock.invoke_model(
    modelId="anthropic.claude-sonnet-4-5-20250929-v1:0",
    body=json.dumps({
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 1024,
        "messages": [{"role": "user", "content": "Hello!"}]
    })
)

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

Usage with Strands

Strands has native Bedrock support:

from sideseat import SideSeat, Frameworks
SideSeat(framework=Frameworks.Strands)

from strands import Agent

agent = Agent()
response = agent("Hello!")
print(response)

Strands uses Amazon Bedrock by default. To specify a model explicitly:

from strands.models import BedrockModel

model = BedrockModel(model_id="anthropic.claude-sonnet-4-5-20250929-v1:0")
agent = Agent(model=model)

Extracted Attributes

Attribute	Source
gen_ai.system	bedrock
gen_ai.request.model	Model ID from request
gen_ai.response.model	Model ID from response
gen_ai.usage.input_tokens	Usage metrics
gen_ai.usage.output_tokens	Usage metrics
cloud.provider	aws
cloud.region	AWS region

Cross-Region Inference

Bedrock cross-region inference is supported:

model = BedrockModel(
    model_id="anthropic.claude-sonnet-4-5-20250929-v1:0",
    region_name="us-east-1"
)

The us. prefix indicates cross-region inference.

Streaming

Streaming responses are captured:

response = bedrock.invoke_model_with_response_stream(
    modelId="anthropic.claude-sonnet-4-5-20250929-v1:0",
    body=json.dumps({
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 1024,
        "messages": [{"role": "user", "content": "Tell me a story"}]
    })
)

for event in response["body"]:
    chunk = json.loads(event["chunk"]["bytes"])
    if chunk["type"] == "content_block_delta":
        print(chunk["delta"]["text"], end="")

Converse API

The Bedrock Converse API is also supported:

response = bedrock.converse(
    modelId="anthropic.claude-sonnet-4-5-20250929-v1:0",
    messages=[{
        "role": "user",
        "content": [{"text": "Hello!"}]
    }]
)

print(response["output"]["message"]["content"][0]["text"])

Authentication

Amazon Bedrock uses the standard AWS credential chain:

# Environment variables
export AWS_ACCESS_KEY_ID=xxx
export AWS_SECRET_ACCESS_KEY=xxx
export AWS_REGION=us-east-1

# Or AWS profile
export AWS_PROFILE=my-profile

Next Steps

• Strands — full Strands guide
• Python SDK — SDK reference