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

# bedrock()

> Create an AWS Bedrock language model

Factory function to create an AWS Bedrock model instance using the Converse API.

<Note>
  Requires optional dependency: `pip install ai-query[bedrock]`
</Note>

## Signature

```python theme={null}
def bedrock(
    model_id: str,
    *,
    region: str | None = None,
    credentials: dict | Callable | None = None,
) -> LanguageModel
```

## Parameters

<ParamField path="model_id" type="str" required>
  The Bedrock model ID (e.g., "anthropic.claude-3-5-sonnet-20241022-v2:0").
</ParamField>

<ParamField path="region" type="str" optional>
  AWS region. Falls back to `AWS_REGION` or `AWS_DEFAULT_REGION` environment variable.
</ParamField>

<ParamField path="credentials" type="dict | Callable" optional>
  AWS credentials. Can be:

  * `None`: Use default AWS credential chain
  * `dict`: `{"access_key": "...", "secret_key": "...", "session_token": "..."}`
  * `Callable`: A credentials provider function
</ParamField>

## Returns

A `LanguageModel` instance configured for AWS Bedrock.

## Environment

Uses the standard AWS credential chain. Optionally set:

```bash theme={null}
export AWS_REGION="us-east-1"
export AWS_ACCESS_KEY_ID="AKIA..."
export AWS_SECRET_ACCESS_KEY="..."
```

## Available Models

| Model ID                                    | Description          |
| ------------------------------------------- | -------------------- |
| `anthropic.claude-3-5-sonnet-20241022-v2:0` | Claude 3.5 Sonnet v2 |
| `anthropic.claude-3-haiku-20240307-v1:0`    | Claude 3 Haiku       |
| `meta.llama3-1-70b-instruct-v1:0`           | Llama 3.1 70B        |
| `amazon.nova-pro-v1:0`                      | Amazon Nova Pro      |

## Example

```python theme={null}
from ai_query import generate_text
from ai_query.providers.bedrock import bedrock

result = await generate_text(
    model=bedrock("anthropic.claude-3-5-sonnet-20241022-v2:0"),
    prompt="Hello, world!"
)
```

## With Credentials

```python theme={null}
result = await generate_text(
    model=bedrock(
        "anthropic.claude-3-5-sonnet-20241022-v2:0",
        region="us-west-2",
        credentials={
            "access_key": "AKIA...",
            "secret_key": "..."
        }
    ),
    prompt="Hello!"
)
```