Start
Costs and cleanup
What each of the four samples for agentic AI on Amazon Bedrock and Amazon Bedrock AgentCore costs to run, as far as its documentation says, and how to remove everything afterwards. Where a project publishes no figure, this page says so instead of guessing.
Every project deploys real, billable AWS resources
All four projects deploy real, billable AWS resources and every project invokes Amazon Bedrock models. Costs accrue while resources exist, whether or not you are using them. Tear down when you finish, using each project's cleanup commands below. source for the cost notice (opens in new tab)
1. LearnBuilding an Enterprise Agentic AI Platform
| Fact | Value | Source |
|---|---|---|
| Cost | About $15 to $30 for a one-day run in us-west-2 (workshop estimate) At an AWS-run event the account is provided and the cost is covered. Cost accrues per hour whether or not the environment is in use. | index.en.md: Cost (opens in new tab) |
| Teardown | Follow the workshop Cleanup module for Module 4 and Module 3a resources, then run ./deploy-cfn.sh destroy from the workshop folder. At an AWS event Workshop Studio cleans up the account automatically. | README.md: Delete Everything (opens in new tab) |
Teardown: At an AWS event
Nothing to do. Workshop Studio cleans up the account when the event ends. source for teardown: At an AWS event (opens in new tab)
Teardown: Self-paced in your own account
Tear everything down to stop charges. source for teardown: Self-paced in your own account (opens in new tab)
./deploy-cfn.sh destroy2. BuildAgentCore Visual Workflow Platform
| Fact | Value | Source |
|---|---|---|
| Cost | About $0.02 to $0.39 per month for the platform infrastructure at low to moderate usage (docs/COSTS.md estimate, us-east-1 list prices) Excludes the WAF web ACL that infra/stacks/platform_stack.py always creates, which is billed separately and for which the repository publishes no figure, and all agent inference, AgentCore and vector-store usage. | COSTS.md: Monthly Cost Estimates (opens in new tab) |
| Teardown | Run ./scripts/cleanup.sh (prompts for confirmation). It deletes every AgentCore resource the platform created, empties the S3 buckets and runs cdk destroy. | README.md: Cleanup (opens in new tab) |
Teardown
The cleanup script deletes every AgentCore resource the platform created, empties the S3 buckets and runs cdk destroy. It prompts for confirmation. source for teardown: Deploy the platform (opens in new tab)
./scripts/cleanup.sh3. GovernEnterprise MCP Governance Gateway
| Fact | Value | Source |
|---|---|---|
| Cost | not documented The README lists what the stack creates (AgentCore Gateway and policy engine, four Lambdas, a Cognito user pool, a Secrets Manager secret, a customer-managed KMS key, SSM parameters, and a Bedrock Guardrail) but publishes no cost figure. | none |
| Teardown | Disconnect the MCP client first, then cdk destroy EnterpriseMcpGatewayStack (destroy the two connector stacks first if you deployed them). CloudWatch log groups are not removed. | README.md: Teardown (opens in new tab) |
Teardown
Disconnect the MCP client first. If you deployed the Atlassian connector, destroy its two stacks before the gateway stack. CloudWatch log groups are not removed by cdk destroy. source for teardown: Deploy and prove the governance (opens in new tab)
cd cdk
cdk destroy EnterpriseMcpGatewayStack
cd ..4. ScaleEnterprise Agentic AI Platform Blueprint
| Fact | Value | Source |
|---|---|---|
| Cost | not documented README section 8 describes a two-layer cost model (shared Platform cost and Workstream cost) and recommended controls such as allocation tags, budgets and CUR reconciliation, but publishes no figure. | none |
| Teardown | Run python3 scripts/final_teardown.py per account role (workstream, then platform, then management), first as a dry run and then with --apply; verify with scripts/residue_inventory.py | README.md: 16. Cleanup (opens in new tab) |
Teardown
Retire Platform alias grants first, then run the fail-closed teardown per account role: Workstream, then Platform, then Management. Each run is a dry run until you add --apply. Finish with the residue inventory. source for teardown: Prerequisites and deployment sequence (opens in new tab)
python3 scripts/final_teardown.py \
--account-role workstream \
--expected-account <WORKSTREAM_ACCOUNT> \
--region eu-west-1