Claude in Amazon Bedrock

Access Claude models through Amazon Bedrock with AWS-native authentication, billing, and security boundaries.

This guide walks you through setting up and making API calls to Claude in Amazon Bedrock. Claude in Amazon Bedrock runs on AWS-managed infrastructure with zero operator access (Anthropic personnel have no access to the inference infrastructure), letting you build sensitive applications entirely inside the AWS security boundary while using the same Messages API shape you use with Anthropic's first-party API.

Access

Claude Opus 4.7 and Claude Haiku 4.5 are open to all Amazon Bedrock customers. Claude Mythos Preview requires an invitation; see Project Glasswing. For region availability, see Regions.

Prerequisites

Before you begin, ensure you have:

• An AWS account with Amazon Bedrock model access enabled for the Claude models you intend to use.
• The AWS CLI installed and configured (optional, for credential management).

Claude Mythos Preview additionally requires a dedicated AWS account that has been allowlisted by the Bedrock Marketplace team. Your Anthropic account executive can submit your account ID for allowlisting (typically processed within 24 hours), and AWS sends a welcome email once it's complete.

Authentication

Claude in Amazon Bedrock supports three authentication paths. Choose the one that best fits your security requirements.

Bedrock service role (recommended)

Use a Bedrock service role with AWS-managed keys for the most secure, long-lived access:

1. Admin: provision the service role

   An AWS administrator provisions a Bedrock service role and grants developers iam:PassRole permission on the service role ARN.

2. Developer: pass the role

   When calling the API, Bedrock assumes the service role on your behalf. See the Amazon Bedrock documentation for how to associate the role with your requests.

IAM assumed roles

For identity-federated access with a 12-hour maximum session:

1. Admin: configure the IAM role

   Create an IAM role scoped to your Claude models. The trust policy names your identity provider (SAML, OIDC, or AWS Identity Center). The permissions policy grants bedrock-mantle:CreateInference only on the allowed model ARNs.

2. Developer: authenticate and assume

   Authenticate through your corporate identity provider, then assume the IAM role. AWS STS issues temporary credentials that the SDK or CLI uses to sign requests.

Bearer tokens

For short-term access without IAM roles (12-hour maximum, least preferred):

1. Admin: restrict token types

   Block long-term keys by attaching a policy that denies bedrock:CallWithBearerToken unless the bedrock:BearerTokenType condition matches a short-term token.

2. Developer: mint a token

   Use the aws-bedrock-token-generator CLI to mint a bearer token. Pass it in the x-api-key header on each request.

Install an SDK

Anthropic's client SDKs support Claude in Amazon Bedrock through a Bedrock-specific package or module.

pip install -U "anthropic[bedrock]"

npm install @anthropic-ai/bedrock-sdk

dotnet add package Anthropic.Bedrock

go get github.com/anthropics/anthropic-sdk-go/bedrock

implementation("com.anthropic:anthropic-java-bedrock:2.33.0")

<dependency>
    <groupId>com.anthropic</groupId>
    <artifactId>anthropic-java-bedrock</artifactId>
    <version>2.33.0</version>
</dependency>

composer require anthropic-ai/sdk aws/aws-sdk-php

# Gemfile
gem "anthropic"
gem "aws-sdk-core"

Making your first request

The endpoint follows the pattern https://bedrock-mantle.{region}.api.aws/anthropic/v1/messages. Unlike the InvokeModel-based integration, this endpoint uses standard SSE streaming and the same request body shape as Anthropic's first-party API.

The SDK resolves credentials and region using the standard AWS precedence: constructor arguments, then environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN, AWS_REGION), then the AWS config file and credential chain (SSO, assumed roles, ECS task role, IMDS).

curl https://bedrock-mantle.us-east-1.api.aws/anthropic/v1/messages \
  --aws-sigv4 "aws:amz:us-east-1:bedrock-mantle" \
  --user "$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY" \
  -H "x-amz-security-token: $AWS_SESSION_TOKEN" \
  -H "content-type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "anthropic.claude-opus-4-7",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello, Claude"}
    ]
  }'

from anthropic import AnthropicBedrockMantle

client = AnthropicBedrockMantle(aws_region="us-east-1")

message = client.messages.create(
    model="anthropic.claude-opus-4-7",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello, Claude"}],
)

print(message.content[0].text)

import { AnthropicBedrockMantle } from "@anthropic-ai/bedrock-sdk";

const client = new AnthropicBedrockMantle({
  awsRegion: "us-east-1"
});

const message = await client.messages.create({
  model: "anthropic.claude-opus-4-7",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello, Claude" }]
});

const block = message.content[0];
if (block.type === "text") {
  console.log(block.text);
}

using Anthropic.Bedrock;
using Anthropic.Models.Messages;

var client = new AnthropicBedrockMantleClient(new() { AwsRegion = "us-east-1" });

var message = await client.Messages.Create(new()
{
    Model = "anthropic.claude-opus-4-7",
    MaxTokens = 1024,
    Messages = [new() { Role = Role.User, Content = "Hello, Claude" }],
});

if (message.Content[0].Value is TextBlock block)
    Console.WriteLine(block.Text);

package main

import (
	"context"
	"fmt"

	"github.com/anthropics/anthropic-sdk-go"
	"github.com/anthropics/anthropic-sdk-go/bedrock"
)

func main() {
	client, err := bedrock.NewMantleClient(context.Background(), bedrock.MantleClientConfig{
		AWSRegion: "us-east-1",
	})
	if err != nil {
		panic(err)
	}

	message, err := client.Messages.New(context.Background(), anthropic.MessageNewParams{
		Model:     "anthropic.claude-opus-4-7",
		MaxTokens: 1024,
		Messages: []anthropic.MessageParam{
			anthropic.NewUserMessage(anthropic.NewTextBlock("Hello, Claude")),
		},
	})
	if err != nil {
		panic(err)
	}

	fmt.Println(message.Content[0].Text)
}

import com.anthropic.bedrock.backends.BedrockMantleBackend;
import com.anthropic.client.AnthropicClient;
import com.anthropic.client.okhttp.AnthropicOkHttpClient;
import com.anthropic.models.messages.Message;
import com.anthropic.models.messages.MessageCreateParams;

void main() {
    AnthropicClient client = AnthropicOkHttpClient.builder()
        .backend(BedrockMantleBackend.fromEnv())
        .build();

    Message message = client.messages().create(
        MessageCreateParams.builder()
            .model("anthropic.claude-opus-4-7")
            .maxTokens(1024)
            .addUserMessage("Hello, Claude")
            .build()
    );

    IO.println(message.content().getFirst().asText().text());
}

<?php

use Anthropic\Bedrock\MantleClient;

$client = new MantleClient(awsRegion: 'us-east-1');

$message = $client->messages->create(
    model: 'anthropic.claude-opus-4-7',
    maxTokens: 1024,
    messages: [
        ['role' => 'user', 'content' => 'Hello, Claude'],
    ],
);

echo $message->content[0]->text;

require "anthropic"

client = Anthropic::BedrockMantleClient.new(aws_region: "us-east-1")

message = client.messages.create(
  model: "anthropic.claude-opus-4-7",
  max_tokens: 1024,
  messages: [{role: "user", content: "Hello, Claude"}]
)

puts message.content[0].text

Supported models

Model IDs in Claude in Amazon Bedrock carry an anthropic. provider prefix. Model capabilities and behaviors are documented on the Models overview page.

Feature support

For the full feature list with Amazon Bedrock availability, see Features overview.

Supported feature highlights

• Messages API (/anthropic/v1/messages)
• Prompt caching
• Extended thinking
• Tool use, including the Bash tool, Computer use tool, Memory tool, and Text editor tool
• Citations
• Structured outputs

Features not supported

• Input sources (URL sources for images and documents, Files API)
• Server-side tools (code execution, web search, web fetch, advisor)
• Agent infrastructure (Agent Skills, MCP connector, programmatic tool calling)
• API endpoints (Message Batches, Models, Admin, Compliance, Usage and Cost)
• Claude Managed Agents

Regions

Claude in Amazon Bedrock is available in the following AWS regions. Amazon Bedrock offers two endpoint types:

• Global: dynamic routing across all available regions for maximum availability. No pricing premium.
• Regional: the endpoint resolves to the single AWS region you specify, for data-residency requirements. Regional endpoints carry a 10% pricing premium over global endpoints. To route across multiple regions within a geography, use an inference profile (US, EU, JP, or AU). Regions marked In-region only in the table support direct single-region routing without an inference profile.

The global endpoint is available for Claude Opus 4.7 and Claude Haiku 4.5. Claude Mythos Preview is regional only and is available in us-east-1.

Quotas

Default quota is 2 million input tokens per minute (TPM). You can request up to 4 million input TPM without additional Anthropic approval. AWS enforces requests-per-minute (RPM) limits on the Bedrock side; contact AWS support for RPM adjustments.

Data retention

Data handling for this offering is governed by Amazon Bedrock. For details, see Data protection in Amazon Bedrock.

Monitoring and logging

Claude in Amazon Bedrock emits logs to both CloudWatch and CloudTrail. Anthropic recommends retaining activity logs on at least a 30-day rolling basis to understand usage patterns and investigate potential issues.

Support

For support, contact bedrock-ant-eap@amazon.com. Include your AWS account ID and the request-id from any failed API responses.