A short summary of the launch path. This page does not replace the full Getting Started guide, which has the complete commands, outputs, and troubleshooting.
An AWS account with console access, plus Bedrock model access. The default model us.anthropic.claude-haiku-4-5-20251001-v1:0 is a cross-region inference profile, so enable model access in both us-east-1 and us-west-2 before you generate.
Subscribe on AWS Marketplace and accept the terms. Your onboarding email contains your Customer ID, Registry JWT, and API key.
Before launching, create two SSM parameters in your deployment region: /stelr/registry/attestation-token and /stelr/api-key, both as SecureString. If either is missing, the stack rolls back.
Launch from Marketplace, enter your STELR Customer ID, and launch CloudFormation. The stack deploys about 96 resources, all inside your own AWS account, and takes 3 to 6 minutes to reach CREATE_COMPLETE.
Open the CloudFormation Outputs tab. Key outputs are ApiEndpoint, the base URL for every API call, SigningKeyArn, LedgerTableName, and TrustLedgerBucket.
If your setup requires a manual invocation of stelr-key-registrar-customer, run it before your first generate. Its expected output includes FunctionError: Unhandled. Do not treat that expected output alone as a failed setup. The stack normally invokes the key registrar automatically as a Custom Resource during launch.