Available for Enterprise organizations where OpenAI model routing is enabled. Contact sales to learn more.
This feature is only supported in AWS EC2 Runners.
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:Add the integration with the UI
- Go to the Runners settings page.
- Select the AWS EC2 runner where you want to configure Bedrock Mantle.
- Scroll to LLM Providers.
- Click Configure.
- Select AWS Bedrock Mantle.
- Confirm that the model option is OpenAI.
- Enter your Bedrock Mantle endpoint.
- Paste the Bedrock Mantle token into API Key.
- Click Create Integration.

Add the integration with the CLI
Verify the integration
- Create a new environment with the configured AWS EC2 runner.
- Start an agent that uses OpenAI model routing.
- Confirm that the agent can answer a simple code question.
Troubleshooting
AWS Bedrock Mantle is not shown
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.
Endpoint validation fails
Endpoint validation fails
Use an endpoint on the
bedrock-mantle.<region>.api.aws domain. For OpenAI model routing, include the /openai/v1/responses path.Token authentication fails
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.