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

# Amazon Bedrock

> Use Amazon Bedrock models with Tracia

Tracia supports Amazon Bedrock via [LiteLLM](https://docs.litellm.ai/docs/providers/bedrock). No additional provider packages are needed. LiteLLM is included as a dependency.

## Installation

```bash theme={null}
pip install tracia
```

## Environment Variables

Set your AWS credentials:

```bash theme={null}
AWS_ACCESS_KEY_ID=your-access-key-id
AWS_SECRET_ACCESS_KEY=your-secret-access-key
AWS_REGION=us-east-1
```

## Usage

Bedrock hosts models from multiple vendors. Use the full Bedrock model ID:

### Amazon Nova

```python theme={null}
result = client.run_local(
    model="amazon.nova-lite-v1:0",
    messages=[
        {"role": "user", "content": "What are the benefits of cloud computing?"}
    ],
    temperature=0.7,
    max_output_tokens=500,
)
```

### Anthropic Claude (via Bedrock)

```python theme={null}
result = client.run_local(
    model="anthropic.claude-sonnet-4-5-20250929-v1:0",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing."},
    ],
    temperature=0.7,
    max_output_tokens=1000,
)
```

### Meta Llama (via Bedrock)

```python theme={null}
result = client.run_local(
    model="meta.llama4-scout-17b-instruct-v1:0",
    messages=[
        {"role": "user", "content": "Write a haiku about programming."}
    ],
)
```

## Streaming

```python theme={null}
stream = client.run_local(
    model="amazon.nova-lite-v1:0",
    messages=[{"role": "user", "content": "Write a poem about the cloud."}],
    stream=True,
)

for chunk in stream:
    print(chunk, end="")
```

## Async Usage

```python theme={null}
result = await client.arun_local(
    model="amazon.nova-lite-v1:0",
    messages=[
        {"role": "user", "content": "What are the benefits of cloud computing?"}
    ],
)
```

## Available Models

Bedrock provides access to models from multiple vendors:

| Vendor    | Example Model ID                            | Description                 |
| --------- | ------------------------------------------- | --------------------------- |
| Amazon    | `amazon.nova-lite-v1:0`                     | Amazon's Nova family        |
| Anthropic | `anthropic.claude-sonnet-4-5-20250929-v1:0` | Claude models via Bedrock   |
| Meta      | `meta.llama4-scout-17b-instruct-v1:0`       | Llama models via Bedrock    |
| Mistral   | `mistral.mistral-large-3-675b-instruct`     | Mistral models via Bedrock  |
| DeepSeek  | `deepseek.v3-v1:0`                          | DeepSeek models via Bedrock |
| Cohere    | `cohere.command-r-plus-v1:0`                | Cohere models via Bedrock   |

See the [AWS Bedrock documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) for the complete list of available models.