Skip to main content

AWS Bedrock

Integrate AWS Bedrock foundation models through the Adaline Proxy to automatically capture telemetry — requests, responses, token usage, latency, and costs — with minimal code changes.

Supported Models

Chat Models
ModelDescription
anthropic.claude-opus-4-6-v1Latest Claude Opus
anthropic.claude-opus-4-5-20251101-v1:0Claude Opus 4.5
anthropic.claude-opus-4-20250514-v1:0Claude Opus 4
anthropic.claude-sonnet-4-6-v1Latest Claude Sonnet
anthropic.claude-sonnet-4-5-20250929-v1:0Claude Sonnet 4.5
anthropic.claude-sonnet-4-20250514-v1:0Claude Sonnet 4
anthropic.claude-haiku-4-5-20251001-v1:0Claude Haiku 4.5
anthropic.claude-3-7-sonnet-20250219-v1:0Claude 3.7 Sonnet
anthropic.claude-3-5-sonnet-20241022-v2:0Claude 3.5 Sonnet v2
anthropic.claude-3-5-sonnet-20240620-v1:0Claude 3.5 Sonnet v1
anthropic.claude-3-5-haiku-20241022-v1:0Claude 3.5 Haiku
anthropic.claude-3-opus-20240229-v1:0Claude 3 Opus
anthropic.claude-3-sonnet-20240229-v1:0Claude 3 Sonnet
anthropic.claude-3-haiku-20240307-v1:0Claude 3 Haiku

Proxy Base URL

https://gateway.adaline.ai/v1/bedrock/

Prerequisites

  1. An AWS account with Bedrock model access enabled
  2. AWS access key and secret key with Bedrock permissions
  3. An Adaline API key, project ID, and prompt ID

Chat Completions

Complete Chat

import boto3
import json

# Point the Bedrock runtime client at the Adaline Proxy
client = boto3.client(
    "bedrock-runtime",
    region_name="us-east-1",
    aws_access_key_id="your-aws-access-key",
    aws_secret_access_key="your-aws-secret-key",
    endpoint_url="https://gateway.adaline.ai/v1/bedrock/"
)

response = client.invoke_model(
    modelId="anthropic.claude-3-5-sonnet-20241022-v2:0",
    contentType="application/json",
    accept="application/json",
    body=json.dumps({
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 1000,
        "messages": [
            {"role": "user", "content": "What is cloud computing?"}
        ]
    }),
    # Adaline headers passed as custom headers
    # Note: Header passing mechanism depends on your AWS SDK configuration
)

result = json.loads(response["body"].read())
print(result["content"][0]["text"])
AWS Bedrock integration through the proxy requires additional configuration depending on your AWS SDK version. Contact support@adaline.ai for setup assistance.

Features

Access models from Anthropic, Meta, Mistral, and Amazon through a single AWS service.
Data stays within your AWS environment with VPC support and IAM-based access control.
Custom model fine-tuning on your own data through Bedrock’s managed service.

Next Steps


Back to Integrations

Browse all integrations