View a markdown version of this page

Inference using Anthropic Messages API - Amazon Bedrock
Supported RegionsPrerequisitesBasic requestStream responsesSupported features

Inference using Anthropic Messages API

The Anthropic Messages API provides native access to Claude models using the Anthropic request and response format. You can use the Messages API on both the bedrock-mantle and bedrock-runtime endpoints, giving you flexibility to choose the authentication and integration style that fits your application.

Endpoint Base URL Use case
bedrock-mantle https://bedrock-mantle.{region}.api.aws/anthropic/v1/messages Recommended for new applications. Supports API key auth and Workspaces (Anthropic-compatible).
bedrock-runtime https://bedrock-runtime.{region}.amazonaws.com Use with existing AWS SDK integrations and invocation logging.

Supported Regions

The Messages API is available on the bedrock-mantle endpoint in all Regions that support bedrock-mantle (see Supported Regions and Endpoints). On the bedrock-runtime endpoint, it is available in all Regions where Claude models are available. See Regional availability for details.

Prerequisites

Before using the Messages API, ensure you have the following:

  • Model access – Request access to Claude models in the Amazon Bedrock console. See Request access to models.

  • Authentication – Depends on the endpoint:

    • bedrock-mantle – Use a Amazon Bedrock API key (see API keys) or AWS SigV4 credentials.

    • bedrock-runtime – Use AWS SigV4 credentials via the AWS SDK (boto3, etc.).

  • Anthropic version header – All requests require an API version:

    • bedrock-mantle: Set anthropic-version: 2023-06-01 as an HTTP header.

    • bedrock-runtime: Set "anthropic_version": "bedrock-2023-05-31" in the request body.

Basic request

To send a basic message to a Claude model, choose the tab for your preferred method, and then follow the steps:

bedrock-mantle (curl)
curl -X POST https://bedrock-mantle.us-east-1.api.aws/anthropic/v1/messages \
  -H "x-api-key: $BEDROCK_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic.claude-sonnet-4-6-v1",
    "max_tokens": 1024,
    "messages": [
        {"role": "user", "content": "Explain quantum computing in one sentence."}
    ]
  }'
bedrock-runtime (Python)
import boto3
import json

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

response = client.invoke_model(
    modelId="anthropic.claude-sonnet-4-6-v1",
    body=json.dumps({
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 1024,
        "messages": [
            {"role": "user", "content": "Explain quantum computing in one sentence."}
        ]
    })
)

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

Use the AWS CLI to invoke the model:

aws bedrock-runtime invoke-model \
  --model-id anthropic.claude-sonnet-4-6-v1 \
  --body '{
    "anthropic_version": "bedrock-2023-05-31",
    "max_tokens": 1024,
    "messages": [
        {"role": "user", "content": "Explain quantum computing in one sentence."}
    ]
  }' \
  --cli-binary-format raw-in-base64-out \
  output.json

Stream responses

To receive response tokens incrementally as they are generated, choose the tab for your preferred method, and then follow the steps:

bedrock-mantle (curl)
curl -X POST https://bedrock-mantle.us-east-1.api.aws/anthropic/v1/messages \
  -H "x-api-key: $BEDROCK_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic.claude-sonnet-4-6-v1",
    "max_tokens": 1024,
    "stream": true,
    "messages": [
        {"role": "user", "content": "Write a short poem about cloud computing."}
    ]
  }'
bedrock-runtime (Python)
import boto3
import json

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

response = client.invoke_model_with_response_stream(
    modelId="anthropic.claude-sonnet-4-6-v1",
    body=json.dumps({
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 1024,
        "messages": [
            {"role": "user", "content": "Write a short poem about cloud computing."}
        ]
    })
)

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

Supported features

The Messages API supports the following advanced features with Claude models:

For the full Messages API request and response format, including all parameters and features, see Anthropic Claude Messages API.