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

# AWS Bedrock Mantle

> Set up AWS Bedrock Mantle for OpenAI model routing on an AWS EC2 runner

<Note>Available for Enterprise organizations where OpenAI model routing is enabled. [Contact sales](https://ona.com/contact/sales) to learn more.</Note>

<Note>
  This feature is only supported in **AWS EC2 Runners**.
</Note>

Use AWS Bedrock Mantle when your AWS EC2 runner should route OpenAI model requests through a Bedrock Mantle endpoint.

This page covers the OpenAI setup exposed in Ona. For Anthropic Claude models through AWS Bedrock Runtime, see [AWS Bedrock](/ona/agents/llm-providers/bedrock).

## Prerequisites

* Your organization has OpenAI model routing enabled.
* You have an AWS EC2 runner configured in Ona.
* You have a Bedrock Mantle endpoint and token.
* The runner can reach the Bedrock Mantle endpoint over HTTPS.

## Configure the endpoint

Use the Bedrock Mantle endpoint for your AWS region:

```bash theme={null}
https://bedrock-mantle.<region>.api.aws/openai/v1/responses
```

The Ona UI defaults to:

```bash theme={null}
https://bedrock-mantle.us-east-1.api.aws/openai/v1/responses
```

## Add the integration with the UI

1. Go to the [Runners settings page](https://app.ona.com/settings/runners).
2. Select the AWS EC2 runner where you want to configure Bedrock Mantle.
3. Scroll to **LLM Providers**.
4. Click **Configure**.
5. Select **AWS Bedrock Mantle**.
6. Confirm that the model option is **OpenAI**.
7. Enter your Bedrock Mantle endpoint.
8. Paste the Bedrock Mantle token into **API Key**.
9. Click **Create Integration**.

<img src="https://mintcdn.com/gitpod-13c83c2b/mQ50qjkw4wYNkVqx/images/bedrock-mantle.png?fit=max&auto=format&n=mQ50qjkw4wYNkVqx&q=85&s=2235c6e249ba1e422d4e6073e858dfdb" alt="AWS Bedrock Mantle LLM integration form showing endpoint URL, API key, and OpenAI model fields" width="674" height="646" data-path="images/bedrock-mantle.png" />

## Add the integration with the CLI

```bash theme={null}
gitpod runner config llm-integration create <runner-id> SUPPORTED_MODEL_OPENAI_AUTO https://bedrock-mantle.<region>.api.aws/openai/v1/responses <bedrock-mantle-token>
```

To verify the integration:

```bash theme={null}
gitpod runner config llm-integration list
```

## Verify the integration

1. Create a new environment with the configured AWS EC2 runner.
2. Start an agent that uses OpenAI model routing.
3. Confirm that the agent can answer a simple code question.

## Troubleshooting

<Accordion title="AWS Bedrock Mantle is not shown">
  AWS Bedrock Mantle is available only on AWS EC2 runners when OpenAI model routing is enabled for your organization. It is not shown on GCP runners.
</Accordion>

<Accordion title="Endpoint validation fails">
  Use an endpoint on the `bedrock-mantle.<region>.api.aws` domain. For OpenAI model routing, include the `/openai/v1/responses` path.
</Accordion>

<Accordion title="Token authentication fails">
  Confirm that the value in **API Key** is a Bedrock Mantle token. AWS Bedrock Mantle does not use the IAM-based credential flow from the AWS Bedrock Runtime integration.
</Accordion>