> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# AWS Bedrock Claude

> Configuration reference for the Bedrock Claude model class, Agno's wrapper for Anthropic Claude models hosted on AWS Bedrock.

The AWS Bedrock Claude model provides access to Anthropic's Claude models hosted on AWS Bedrock.

## Parameters

| Parameter               | Type                       | Default                                              | Description                                                                                                                                                   |
| ----------------------- | -------------------------- | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `id`                    | `str`                      | `"global.anthropic.claude-sonnet-4-5-20250929-v1:0"` | The ID of the AWS Bedrock Claude model to use                                                                                                                 |
| `name`                  | `str`                      | `"AwsBedrockAnthropicClaude"`                        | The name of the model                                                                                                                                         |
| `provider`              | `str`                      | `"AwsBedrock"`                                       | The provider of the model                                                                                                                                     |
| `aws_access_key`        | `Optional[str]`            | `None`                                               | AWS access key (defaults to AWS\_ACCESS\_KEY\_ID or AWS\_ACCESS\_KEY env var)                                                                                 |
| `aws_secret_key`        | `Optional[str]`            | `None`                                               | AWS secret key (defaults to AWS\_SECRET\_ACCESS\_KEY or AWS\_SECRET\_KEY env var)                                                                             |
| `aws_session_token`     | `Optional[str]`            | `None`                                               | AWS session token (defaults to AWS\_SESSION\_TOKEN env var)                                                                                                   |
| `aws_region`            | `Optional[str]`            | `None`                                               | The AWS region to use (defaults to AWS\_REGION env var)                                                                                                       |
| `session`               | `Optional[Session]`        | `None`                                               | boto3 session for credential resolution. Credentials are re-resolved on each request, so rotated credentials (IAM roles, instance profiles, STS) keep working |
| `max_tokens`            | `Optional[int]`            | `8192`                                               | Maximum number of tokens to generate in the chat completion                                                                                                   |
| `thinking`              | `Optional[Dict[str, Any]]` | `None`                                               | Configuration for the thinking (reasoning) process                                                                                                            |
| `temperature`           | `Optional[float]`          | `None`                                               | Controls randomness in the model's output                                                                                                                     |
| `stop_sequences`        | `Optional[List[str]]`      | `None`                                               | A list of strings that the model should stop generating text at                                                                                               |
| `top_p`                 | `Optional[float]`          | `None`                                               | Controls diversity via nucleus sampling                                                                                                                       |
| `top_k`                 | `Optional[int]`            | `None`                                               | Controls diversity via top-k sampling                                                                                                                         |
| `cache_system_prompt`   | `Optional[bool]`           | `False`                                              | Whether to cache the system prompt for improved performance                                                                                                   |
| `extended_cache_time`   | `Optional[bool]`           | `False`                                              | Whether to use extended cache time (1 hour instead of default)                                                                                                |
| `request_params`        | `Optional[Dict[str, Any]]` | `None`                                               | Additional parameters to include in the request                                                                                                               |
| `client_params`         | `Optional[Dict[str, Any]]` | `None`                                               | Additional parameters for client configuration                                                                                                                |
| `retries`               | `int`                      | `0`                                                  | Number of retries to attempt before raising a ModelProviderError                                                                                              |
| `delay_between_retries` | `int`                      | `1`                                                  | Delay between retries, in seconds                                                                                                                             |
| `exponential_backoff`   | `bool`                     | `False`                                              | If True, the delay between retries is doubled each time                                                                                                       |

AWS Bedrock Claude extends the Anthropic [Claude](/reference/models/anthropic) model and accepts all of its parameters. Native structured outputs and JSON schema outputs are disabled on Bedrock.

<Warning>
  The inherited `api_key` parameter is not supported for Bedrock authentication. Setting it (directly or via `AWS_BEDROCK_API_KEY`) without a `session` raises a `ValueError`. Authenticate with `aws_access_key`/`aws_secret_key`, the AWS environment variables, or a boto3 `session` instead.
</Warning>