Sold by: GreenPT
GreenPT lets scheduled Amazon Bedrock AgentCore agents run when the electricity grid is cleanest. Each agent calls the GreenPT tool at the start of a run. GreenPT then lets the run go ahead, or moves it to a greener hour within limits you set, and shows how sure it is about the grid. Nothing runs in your account except a one-shot schedule for each moved run.
Overview
AI agents that run on a schedule, such as nightly reports, digests and batch jobs, rarely need to start at an exact minute. GreenPT Carbon-Aware uses that slack to run them when the grid has less CO2 per kWh.
How it works
- Each gated agent calls GreenPT's carbon_gate tool, over MCP, at the very start of a run. It proves who it is with its own AWS identity token (sts:GetWebIdentityToken). No API keys.
- GreenPT looks up the grid's carbon intensity for where the agent's model runs, and the forecast within the longest wait you allow.
- If a later start saves at least your minimum, GreenPT creates a one-shot EventBridge Scheduler schedule in your account that starts the agent again at that time, and tells the current run to stop. Otherwise the run goes ahead straight away.
- A moved run starts once, at its greener time, and isn't moved again.
Built to never block your work
- If GreenPT can't reach the grid data, can't identify the caller, or your plan's checks are used up, the run goes ahead straight away.
- Rules per agent: the longest wait, the typical run length and the smallest saving worth waiting for.
- Honest grid labels: exact when the model runs in one region, "in zone" for EU and US inference profiles, and an estimate for global profiles. With your opt-in, GreenPT reads where each model really ran from CloudTrail.
Reporting Every decision is stored with its time, grid, saving and label. A monthly CSRD-style report and CSV export show checked runs, moved runs and the average saving.
Setup: pick your regions, turn on outbound identity federation, install one CloudFormation stack (it creates two roles and the schedule group), and add the tool and one instruction line to each agent.
Highlights
- Moves scheduled AgentCore runs to greener hours within the limits you set, and never blocks a run.
- Agents prove who they are with their own AWS identity token, without API keys.
- Shows every decision, saving and grid label, with monthly reports and a CSV export.
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on the duration and terms of your contract with the vendor, and additional usage. You pay upfront or in installments according to your contract terms with the vendor. This entitles you to a specified quantity of use for the contract duration. Usage-based pricing is in effect for overages or additional usage not covered in the contract. These charges are applied on top of the contract price. If you choose not to renew or replace your contract before the contract end date, access to your entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/month |
|---|---|---|
Starter plan | 10,000 gate checks a month included | $49.00 |
Team plan | 100,000 gate checks a month included | $249.00 |
Business plan | 500,000 gate checks a month included | $999.00 |
The following dimensions are not included in the contract terms, which will be charged based on your usage.
Dimension | Description | Cost/request |
|---|---|---|
Starter extra checks | Gate checks above the Starter plan's included checks | $0.005 |
Team extra checks | Gate checks above the Team plan's included checks | $0.003 |
Business extra checks | Gate checks above the Business plan's included checks | $0.002 |
Dimensions summary
This listing uses a contract model built around three base plans. The Starter plan includes 10,000 gate checks a month, the Team plan includes 100,000, and the Business plan includes 500,000. A gate check is a request that confirms when and where to run a job. Each base plan pairs with a matching extra-checks dimension. These add-ons bill for gate checks you use beyond the included monthly amount. You pick one plan to match your expected volume, then rely on the matching extra-checks rate only when you exceed its included checks.
Top-of-mind questions for buyers
A gate check is one request your agent or code makes to confirm when and where to run a job. The service answers how clean the grid is, the cleanest window before your deadline, and the token cost. Each such request counts as one check against your monthly included amount.
Each base plan includes a set monthly amount: 10,000 for Starter, 100,000 for Team, and 500,000 for Business. Once you pass that amount, the matching extra-checks dimension bills only the additional checks beyond the included total. The included checks remain covered by your base plan.
No. Gate checks meter the carbon-aware and price-aware requests that decide when and where a job runs. Running the actual AI work through an API key is billed separately per token from API credits and never counts toward your plan's included gate checks.
greenpt.com+1
Helpful?
Vendor refund policy
Cancel within 14 days of a purchase for a full refund of that month's contract fee. Extra checks already used aren't refunded. Email support@greenpt.ai , or request it through AWS Support.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Resources
Vendor resources
Support
Vendor support
Email support@greenpt.ai . We answer within one business day (CET), and within four hours for an outage of the gate. Your plan includes setup help by email.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Deploy a production-ready AI agent using Amazon Bedrock AgentCore in just 4 weeks. Launch secure, scalable, and extensible GenAI agents that can reason, plan, act, and integrate with your business systems.
Building Agentic AI with Amazon Bedrock AgentCore focuses on designing and deploying autonomous AI agents that can reason, plan, and take actions using foundation models on AWS. The course covers how to orchestrate tools, workflows, and APIs with Bedrock AgentCore to build scalable, secure, and production-ready agentic AI applications.
Learn to design and deploy secure, scalable, production-ready multi-agent systems using Amazon Bedrock AgentCore.
No compromised, emergent, or hostile agent can execute - regardless of what it reasons.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.