# Amazon Bedrock (/en/ai/models/llm/amazon)

> For AI agents: see the complete documentation index at [llms.txt](/llms.txt).

Amazon Bedrock provides access to a variety of foundation models (FMs) from leading AI providers through a fully managed AWS service.

### Sample configuration [#sample-configuration]

The following example shows how to configure Amazon Bedrock LLM when starting a conversational AI agent.

<Tabs defaultValue="python" groupId="ai-sdk-language">
  <TabsList>
    <TabsTrigger value="python">
      Python SDK
    </TabsTrigger>

    <TabsTrigger value="typescript">
      TypeScript SDK
    </TabsTrigger>

    <TabsTrigger value="go">
      Go SDK
    </TabsTrigger>

    <TabsTrigger value="rest-api">
      REST API
    </TabsTrigger>
  </TabsList>

  <TabsContent value="python">
    ```python
    from agora_agent import Agent, AmazonBedrock

    # client is your configured Agora client
    agent = (
        Agent(client)
        .with_stt(...)  # configure your STT vendor
        .with_llm(AmazonBedrock(
            access_key='your-aws-access-key-id',
            secret_key='your-aws-secret-access-key',
            region='us-east-1',
            model='us.anthropic.claude-sonnet-4-20250514-v1:0',
            system_messages=[{'role': 'system', 'content': 'You are a helpful chatbot.'}],
        ))
        .with_tts(...)  # configure your TTS vendor
    )
    ```
  </TabsContent>

  <TabsContent value="typescript">
    ```typescript
    import { Agent, AmazonBedrock } from 'agora-agents';

    // client is your configured Agora client
    const agent = new Agent({ client })
      .withStt(/* configure your STT vendor */)
      .withLlm(new AmazonBedrock({
        accessKey: 'your-aws-access-key-id',
        secretKey: 'your-aws-secret-access-key',
        region: 'us-east-1',
        model: 'us.anthropic.claude-sonnet-4-20250514-v1:0',
        systemMessages: [{ role: 'system', content: 'You are a helpful chatbot.' }],
      }))
      .withTts(/* configure your TTS vendor */);
    ```
  </TabsContent>

  <TabsContent value="go">
    ```go
    import "github.com/AgoraIO/agora-agents-go/v2/agentkit/vendors"

    // client is your configured Agora client
    agent := agentkit.NewAgent(client).WithStt(/* configure your STT vendor */).
      WithLlm(
        vendors.NewAmazonBedrock(vendors.AmazonBedrockOptions{
            AccessKey: "your-aws-access-key-id",
            SecretKey: "your-aws-secret-access-key",
            Region:    "us-east-1",
            Model:     "us.anthropic.claude-sonnet-4-20250514-v1:0",
            SystemMessages: []map[string]interface{}{
                {"role": "system", "content": "You are a helpful chatbot."},
            },
        }),
    ).WithTts(/* configure your TTS vendor */)
    ```
  </TabsContent>

  <TabsContent value="rest-api">
    Use the following `llm` configuration in your request:

    ```json
    "llm": {
        "url": "https://bedrock-runtime.us-east-1.amazonaws.com/model/us.anthropic.claude-sonnet-4-20250514-v1:0/converse-stream",
        "api_key": "<your_bedrock_api_key>",
        "access_key": "<your_aws_access_key_id>",
        "secret_key": "<your_aws_secret_access_key>",
        "region": "us-east-1",
        "model": "us.anthropic.claude-sonnet-4-20250514-v1:0",
        "system_messages": [
            {
                "role": "system",
                "content": "You are a helpful chatbot."
            }
        ],
        "style": "bedrock"
    }
    ```
  </TabsContent>
</Tabs>

### Key parameters [#key-parameters]

<ParameterList title="llm" required="true">
  <Parameter name="url" type="string" required="true">
    The Amazon Bedrock runtime endpoint for the target region and model. See [Amazon Bedrock endpoints and quotas](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bedrock_region) for the correct endpoint format.
  </Parameter>

  <Parameter name="api_key" type="string" required="false">
    Your Bedrock API key for authentication. Use either `api_key` alone, or both `access_key` and `secret_key` together for authentication.
  </Parameter>

  <Parameter name="access_key" type="string" required="false">
    Your AWS Access Key ID for authenticating Bedrock API calls. Required if not using `api_key`. Must be used together with `secret_key`. Get your access key from the [AWS IAM Console](https://console.aws.amazon.com/iam/).
  </Parameter>

  <Parameter name="secret_key" type="string" required="false">
    Your AWS Secret Access Key for authenticating Bedrock API calls. Required if not using `api_key`. Must be used together with `access_key`. Get your secret key from the [AWS IAM Console](https://console.aws.amazon.com/iam/).
  </Parameter>

  <Parameter name="region" type="string" required="true">
    The AWS region hosting the Bedrock model, for example, `us-east-1` or `us-west-2`. See [Supported Regions and models](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html) for available regions.
  </Parameter>

  <Parameter name="style" type="string" required="true">
    The API style to use. Set to `bedrock` for Amazon Bedrock models.
  </Parameter>
</ParameterList>

For advanced configuration options, model capabilities, and detailed parameter descriptions, see the [Amazon Bedrock documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html).