Sold by: Carnegie Intelligent Technology
AI gateway and governance for enterprise LLM use: model allow-lists, hard dollar budgets, PII and prompt-injection guardrails, audit logs. Bring your own provider keys.
Overview
Carnegie Relay sits between your applications and Amazon Bedrock, Anthropic, OpenAI, Vertex AI or any OpenAI-compatible provider, using your own provider keys. It enforces a model allow-list per environment, hard monthly budgets in US dollars that stop traffic at the limit, deterministic PII and prompt-injection guardrails, and a request-level audit trail without storing prompt bodies. Developers change one base URL; platform and IT teams get per-environment control, cost allocation by team and project, SSO, and nightly export to a bucket or warehouse they own. Relay never resells model tokens: its price is per organisation and per request.
Highlights
- Hard monthly budgets in dollars per environment: HTTP 402 at the limit, concurrency-safe, counted at provider list price even on your own keys.
- Model allow-list, PII and prompt-injection guardrails, and a request-level audit log with no prompt bodies stored by default.
- One base-URL change for OpenAI- and Anthropic-style SDKs; cost allocation by team and project; SSO; export to your own bucket or SIEM.
Details
Categories
Delivery method
Deployed on AWS
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/12 months |
|---|---|---|
Team plan (annual) | 1 environment, 3 providers, 2M requests/month, 30-day traces, budgets, email support. | $3,600.00 |
Business plan (annual) | 5 environments, unlimited providers, 10M requests/month, 90-day traces, guardrails, SSO. | $14,400.00 |
The following dimensions are not included in the contract terms, which will be charged based on your usage.
Dimension | Description | Cost/unit |
|---|---|---|
Requests beyond Team allowance | One relayed request beyond the 2,000,000 per month included in the Team plan. | $0.00002 |
Requests beyond Business allowance | One relayed request beyond the 10,000,000 per month included in the Business plan. | $0.000012 |
Model access via managed channel (per US cent, list price) | One US cent of model usage at provider list price via the managed channel (BYOK = 0). | $0.01 |
Dimensions summary
You buy Carnegie Relay as an annual contract per organization, choosing either the Team plan or the Business plan. The Team plan covers 1 environment, 3 providers, and 2,000,000 relayed requests each month. The Business plan covers 5 environments, unlimited providers, and 10,000,000 requests each month, with longer trace retention and SSO. If you exceed your plan's monthly requests, you pay per-million overage priced separately for each plan. Model usage through the managed channel bills as a separate line, measured per US cent at provider list price. Bringing your own keys sets that model charge to zero.
Top-of-mind questions for buyers
One request equals one model call passed through Relay, whether streaming or not, no matter how many tokens it uses. Refused requests, such as those blocked by the allow-list, a hard budget, or a guardrail, are not metered. Both the Team and Business plans count requests this way.
Request charges and model usage bill independently. You pay per relayed request against your plan allowance, then overage per million. Model tokens through the managed channel appear as a separate line, measured per US cent at provider list price. If you bring your own keys, that model charge is zero and tokens stay on your provider invoice.
Once you pass the included requests, you pay a per-million overage rate set separately for each plan. The Team plan includes 2,000,000 requests monthly; the Business plan includes 10,000,000. Overage applies only to requests beyond your allowance, not to the whole month's volume.
carnegieintel.com+1
Helpful?
Vendor refund policy
Annual plans are non-refundable after 14 days from the start of the contract; within the first 14 days, contact support@carnegieintel.com for a full refund if the service has not been used in production. Usage charges are non-refundable.
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
Support by e-mail on business days 09:00-18:00 Hong Kong time (UTC+8): support@carnegieintel.com . Security reports: security@carnegieintel.com , acknowledged within two business days. Enterprise plans include an SLA and named support by private offer. Documentation at carnegieintel.com/relay/.
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
RelayShield delivers threat intelligence and identity security via REST API - 4.5M+ IOC corpus, breach detection, SIM swap monitoring, infostealer exposure, ransomware victim tracking, and session hijack detection. Built for MSPs, MSSPs, and security-forward development teams.
Nostr relay infrastructure, deployable through AWS Marketplace in a couple minutes.
Relay42 is the only Customer Data Platform (CDP) built for AI-driven customer journeys with real-time connectivity to all systems and touch points.
RustDesk Server 1.1.16 (AGPL-3.0, open-source hbbs and hbbr) on Ubuntu 24.04. A key pair is generated on your server and only clients with that key are served. No web console. Pinned, patched.
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.