AWS Bedrock

​

Prerequisites

• You must have an AWS account with Bedrock enabled and model access approved.
• You must have an Ona enterprise license.
• Your enterprise runner must be deployed in the same AWS account and have IAM permissions to invoke Bedrock.

​

Network access (VPC endpoints)

​

Set up AWS permissions and model access

1. Go to the AWS Bedrock console
2. Open Model access and request access to the Anthropic Claude model(s) you plan to use, such as Opus 4.8 or Sonnet 5.
3. Important for Anthropic models: First-time customers must submit use case details before invoking an Anthropic model. This is required once per account or once at the organization’s management account. You can submit use case details by:
   • Selecting an Anthropic model from the model catalog in the Amazon Bedrock console, or
   • Calling the PutUseCaseForModelAccess API command
   Access to the model is granted immediately after use case details are successfully submitted. If you submit the form at the root account, it will be inherited by other accounts in the same AWS Organizations. Learn more in the AWS Bedrock Model Access documentation.
4. Wait for approval

​

Configure the Bedrock endpoint

​

Endpoint format

bedrock://<model-id>

​

Add the configuration to Ona

• Ona CLI
• Through the UI

​

Option 1: Ona CLI

gitpod runner config llm-integration create <runner-id> SUPPORTED_MODEL_SONNET_5 bedrock://global.anthropic.claude-sonnet-5 ignore

# Optional: set a specific maximum token limit
# Prefer defaults unless you have specific constraints.
gitpod runner config llm-integration set-max-tokens <integration-id> 4000

# Verify integrations
gitpod runner config llm-integration list

​

Option 2: Through the UI

1. Go to the Runners settings page
2. Select an enterprise runner where you want to enable LLM integration
3. Scroll down to the “LLM Providers” section
4. Click the Configure button
5. In “Bedrock Model ID”, enter the model ID for your region (for example, global.anthropic.claude-sonnet-5). Tip: Verify the identifier for your region in the AWS Bedrock model IDs documentation.
6. “API Key”: Not required for Bedrock (AWS credentials are used).
7. If a model preset selector is shown, choose “Claude Sonnet 5” or another supported Claude model.
8. Click Create Integration

​

Verify the integration

1. Create a new environment with the configured runner
2. Open Ona Agent and start a session
3. If Ona Agent responds, the integration is working. Test with a simple code generation request

​

Supported models

​

Identifying available models

# List available inference profiles
aws bedrock list-inference-profiles

# List available foundation models
aws bedrock list-foundation-models

​

Testing model connectivity

# Set your foundation model or inference profile ID
export MODEL_ID="global.anthropic.claude-sonnet-5"

# Test the model with a simple request
aws bedrock-runtime invoke-model \
    --model-id "$MODEL_ID" \
    --body '{
        "messages": [
            {
                "role": "user",
                "content": "Hi there!"
            }
        ],
        "max_tokens": 50,
        "anthropic_version": "bedrock-2023-05-31"
    }' \
    --cli-binary-format raw-in-base64-out

​

Getting help

1. Check Ona Agent logs for detailed error messages
2. Verify AWS quotas and Bedrock model access
3. Contact your account manager for additional support

​

Next steps

• Review the AWS Bedrock User Guide
• See Anthropic Claude on Bedrock
• Use AWS Bedrock Mantle for the documented OpenAI routing flow
• Monitor usage and performance in CloudWatch

​

Troubleshooting