We run it in your cloud. You stay in control.
What you need, what we do, and what happens if you ever leave.
Where your AI requests go.
Compare a hosted gateway with Intramura running inside your own cloud account.
With Intramura, the gateway runs in your own cloud account. Requests go straight to the AI companies you choose. We only receive what each request used and cost.With a hosted gateway, every request your staff and agents make, and the documents in it, passes through another company's servers before it reaches the AI.
Illustrative example.
Who does what.
You make the decisions. We do the work of running it.
What you need
- A cloud account (AWS, Google Cloud or Azure), your own servers, or a VPS.
- Somewhere to run it: Kubernetes, AWS ECS or a single virtual machine. If you have none of these, one virtual machine is enough to start.
- Someone on your team who can approve our access.
What we do
- Set it up in your account, to your network and security rules.
- Connect it to your sign-in system and staff list.
- Monitor it, upgrade it and deal with incidents.
- Keep it current as AI moves: new models, prices and ways to call them, as they ship.
What your team does
- Approves our access, once.
- Sets budgets and rules in the console.
- Chooses which AI companies and models to use.
Getting started
- You approve accessYour team lets us set up in your cloud account.
- We set it upOne command installs the gateway in your account.
- We connect your companyYour sign-in system and staff list, so every request has an owner.
- Your teams switch overApps and AI tools point at your gateway. Spend shows up from the first request.
Leaving is easy.
What happens if you ever stop working with us? Try it.
- AI requests
- FlowingStill flowing
- Budgets and rules
- Per team, person and projectOne company-wide cap
- Running it, single sign-on, staff list
- IntramuraStop
Today, we run the gateway for you. Your requests go straight to the AI companies.Contract ended. Your gateway moves to the free plan, so it doesn't switch off: requests keep flowing, security updates stay available for you to apply, and within the free plan's limits your keys, approved models, routing and a company-wide spending cap keep working. What stops is what you paid us for: running it, budgets per team, single sign-on and the staff list. Your apps call standard AI APIs at an address in your own cloud, so moving elsewhere is still a configuration change, not a rewrite.
If you run more than one gateway installation, you choose which one moves to the free plan; the others keep serving on their last settings, without updates. The free plan's user limit applies, and you choose who keeps access. The gateway at the core is open source (Apache 2.0). On the free plan you run it yourself, and you can move back to Managed whenever you want us to run it again.
Compared with the alternatives.
A hosted gateway puts another company in the middle of every request. Building it yourself means your team runs it forever. Intramura is neither.
| What you get | A hosted gateway | Build and run it yourself | Intramura |
|---|---|---|---|
| Prompts, documents and keys never pass through a third party | No | Yes | Yes |
| Spend and budgets by team and project | Yes | You build it | Yes |
| Connected to your sign-in system and staff list | Limited | You build it | Yes |
| Upgrades, monitoring and incidents handled | Yes | Your team | Yes |
| Not switched off if you leave | No | Yes | Yes |
Common questions
How does Intramura help us control AI spend?
Every AI request goes through the gateway, which records its cost and the team and project behind it. On top of that you set budgets and limits, so money goes to the projects you have approved and unapproved use is blocked.
How is this different from a hosted AI gateway?
A hosted gateway runs on its vendor's infrastructure, so your prompts, responses and provider keys pass through a third party. Intramura runs the gateway inside your own cloud account and operates it for you.
What is an AI gateway?
The single point your applications and agents go through to reach AI models. It gives applications one API for many models and gives you one place for credentials, routing, budgets and usage. It can also give agents controlled access to tools through MCP servers.
What do we need to have in place?
Somewhere to run it: a cloud account (AWS, Azure or Google Cloud), your own servers or a VPS, and someone who can approve our access. We set it up within your network and security rules and run it from there.
Which sign-in and HR systems do you work with?
Microsoft Entra, Okta and Google for sign-in and your staff list, or a spreadsheet if you prefer. Tell us what else you use and we will scope it during the demo.
What happens if we stop using Intramura?
The gateway doesn't switch off. It moves to the free plan: it keeps serving your requests, security updates stay available for you to apply, and within the free plan's limits your keys, approved models, routing and a company-wide spending cap keep working. What stops is what you paid us for: us running it, budgets per team and project, single sign-on and staff list sync. Your apps call standard AI APIs at an address in your own cloud, so moving them to another gateway, or straight to the AI companies, is a configuration change, not a rewrite. If you run more than one installation, you choose which one moves to the free plan; the others keep serving on their last settings, without updates. The free plan's user limit applies, and you choose which people keep access.