Self-hosted AI platform for Amazon Bedrock: an OpenAI-compatible gateway with budgets, governance, dashboards, and ready-to-use team apps, deployed entirely in your own AWS account.
StrataBlock Enterprise is available through private offers with pricing and terms tailored to your organization. Contact hello@stratablock.io before subscribing and we will put together the right deal.
StrataBlock Enterprise is a self-hosted AI platform for Amazon Bedrock: one governed, OpenAI-compatible endpoint inside your own AWS account, with the control plane your organization needs to roll AI out with confidence. Your teams and tools connect with standard OpenAI SDKs and API keys; prompts, completions, and usage records stay in your cloud.
The control plane is the point. Organizations, roles and invitations give every person a place; per-user and per-team API keys make every request attributable; hard budgets stop spend at the limit you set, org-wide and per person, with a built-in request flow when someone needs more; dashboards break usage and cost down by model, person and application; and a system check page verifies the deployment's own configuration at a glance. Finance stays in the loop without chasing anyone: spend is visible as it happens, every dollar is attributable to a person, team, and model, and monthly reports support showback and chargeback. Because all model usage is billed by AWS on your own account, reconciliation happens against the AWS invoice you already have.
Teams are productive on day one. StrataBlock ships complete working applications on top of the gateway: StrataChat, a full chat workspace with projects and reusable skills; StrataSwarm, for orchestrated multi-agent runs; and StrataBench, for comparing models on your own prompts with shareable leaderboards. Every one of them flows through the same keys, budgets and dashboards as your API traffic.
Deployment is a single CloudFormation stack (ECS on Fargate with DynamoDB) with daily backups included, delivered through AWS Marketplace with License Manager entitlement, and a guided first-boot setup that has you signed in within minutes of the stack completing. Upgrades are a stack update. You pay AWS directly for all Bedrock model usage on your own AWS bill.
Highlights
One OpenAI-compatible endpoint for Amazon Bedrock models (Anthropic Claude and more), running entirely inside your AWS account: prompts, completions, and usage records stay in your cloud.
A real control plane for organizational AI: roles and invitations, per-user API keys, hard budgets that stop spend at the limit, and dashboards that attribute every dollar to a model, person, and application.
Working team apps included from day one: a full chat workspace, multi-agent orchestration, and model benchmarking, all governed by the same keys, budgets, and dashboards as your API traffic.
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 is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
You buy one thing here: a single production deployment licensed for 12 months. The license covers one CloudFormation stack running in your own AWS account. Pricing is a flat upfront contract for the term, not usage-based, so it does not scale with how many model calls you make. Note that this license is separate from your AWS charges. Amazon bills you directly for model usage and the always-on infrastructure that keeps the deployment running. One deployment is allowed per AWS account and region.
Top-of-mind questions for buyers
What exactly does one deployment license cover, and can I run more than one in the same account?
The license covers one production deployment, which is a single CloudFormation stack running in your own AWS account. It uses fixed table names, so a second deployment in the same account and region will not start. To run a staging deployment alongside production, place it in a different region.
Does my bill change based on how many model calls my team makes?
No. The license is a flat upfront fee for the 12-month term and does not scale with usage. Model calls are billed separately by Amazon Bedrock at Amazon's per-token prices. The vendor adds no margin, so what the dashboard shows is what your AWS account pays for model usage.
What happens to the license if I upgrade to a new version or my subscription lapses?
Upgrades cost nothing extra; you change one stack setting and the license carries over. The subscription is checked continuously. If it lapses, the app warns you 30 days before expiry and keeps working 14 days after. Only then does model access stop. Renewing restores it automatically.
stratablock.io+1
Helpful?
Vendor refund policy
All fees are non-refundable except as required by applicable law.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
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.
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Images in StrataChat, a new OpenAI model, and sign-up by invite link works on a self-hosted deployment.
StrataChat now takes images: paste or drag and drop them into a conversation, up to 20 MB each, with thumbnails in the thread and a full-size viewer. This version's template creates a private bucket in your own AWS account to hold them, and an image is deleted with the conversation or message it belongs to.
GPT-6 Astra is available on your deployment: OpenAI's most capable model, for hard end-to-end work across reasoning, coding and research.
Sign-up by invite link works again: an admin shares a link from the Members page and the person sets up their own account. A new deployment setting removes that page if you would rather add people from Members directly. Either way only people your admins add can get an account.
Coding assistants wired to MCP servers no longer fail partway through a conversation. A tool name longer than the upstream limit used to break every later message in that chat, whatever the client.
Plus general fixes and improvements since 1.245.0, including corrected thinking-effort levels across the catalog.
UPGRADING: update your stack with this version's CloudFormation template (linked under deployment resources) as well as the new ContainerImage tag. Fresh installs need nothing special. The template adds the image bucket, its permissions, and one new setting that defaults to keeping invite links available, so there is no parameter value to supply on update.
Additional details
Usage instructions
StrataBlock Enterprise deploys as one CloudFormation stack in your own AWS account and typically takes 20 to 30 minutes end to end. The step-by-step installation guide is linked under Additional resources on this page (stratablock.io/docs/aws/install); it covers the prerequisites (a VPC and an HTTPS certificate), every stack parameter, and the guided first-boot setup that creates your administrator account. The container uses IAM roles for tasks (Amazon ECS) for all AWS service access; it never asks for AWS access keys or credentials.
What to expect: download the CloudFormation template from the deployment resources above and create a stack with ContainerImage set to the image shown on this page. Licensing needs no settings: your AWS Marketplace subscription is your license, the deployment verifies it automatically, and there is no license file to request. When the stack completes, its Outputs tab links you into the setup wizard.
Upgrades are a stack update; the upgrade guide is also linked under Additional resources (stratablock.io/docs/aws/upgrade).
Standard support is included with every license: email support@stratablock.io and we respond as soon as possible. Step-by-step installation and upgrade guides are linked under Additional resources on this page, and every deployment includes a built-in system check that verifies its own configuration. Negotiated support tiers with response-time commitments are available through private offers.
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.
Connect OpenAI, Anthropic, Cohere and Ollama apps to Amazon Bedrock: point them at your own gateway. 100+ models, plus retrieval, batches, images and voice. Runs in your AWS account.
Expert deployment of stdapi.ai, the OpenAI, Anthropic, Cohere and Ollama AI gateway for Amazon Bedrock, into your own AWS account. Production infrastructure configured and secured by specialists.
Dedicated engineering crew delivering production-ready RAG pipelines, LLM integrations, AI agents, and enterprise system connectors on Amazon Bedrock and API Gateway, with compliance evidence packages across your AWS environment.
Scaling generative AI without centralized AWS governance creates compliance risk, uncontrolled costs, and operational blind spots. Adastra's AGate platform is an enterprise LLM Gateway deployed directly in your AWS environment, giving organizations centralized control over model access, usage, performance, and cost across Amazon Bedrock and other LLM providers. With a built-in Admin Portal, monitoring dashboards, audit logging, and EU data residency support, AGate enables organizations to move from AI pilots to scalable production while maintaining security, compliance, and full operational transparency.
With a built-in Admin Portal, monitoring dashboards, audit logging, and EU data residency support, AGate enables organizations to scale GenAI beyond pilots while maintaining security, compliance, and operational transparency.
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.