Deployment · Fully Managed Cloud
Managed AI gateway: DeepintShield Cloud with zero infrastructure
A managed AI gateway is one you use without running any infrastructure. DeepintShield Cloud hosts both the control plane and the data plane, so you deploy, scale and patch nothing. Point your app at the cloud endpoint with a virtual key, and guardrails, budgets and logging apply at once. You can move to hybrid or self-hosted later.
- Nothing to install, scale or patch
- Free Developer plan with 50,000 requests a month
- Hosting region chosen to meet your requirements

Who the managed cloud is best for
Fast evaluation
Sign up, add a provider key and send a governed request in minutes, with no cluster to build.
Teams without strict residency rules
Workloads that can be processed in DeepintShield Cloud, in a region chosen to meet your requirements.
Small platform teams
Get the gateway, guardrails and audit trail without running databases, caches, detectors or upgrades yourself.
How the managed AI gateway works: five steps
Nothing runs on your side except your own application. Each request then passes the checks described in how DeepintShield works.
Sign up
Create an account at app.deepintshield.com; the Developer plan is free.
Open your workspace
Your workspace holds policies, keys, budgets, logs and team members.
Connect a provider
Add your own key for OpenAI, Anthropic, Bedrock or any of 29 built-in providers.
Create a virtual key
Issue an sk-ds- virtual key that carries model access, budgets and rate limits.
Send traffic
Point your client at https://app.deepintshield.com/v1 and every request is governed.
What runs where
| Part | Who runs it | Details |
|---|---|---|
| Control plane | DeepintShield | Console, policies, virtual keys, budgets, analytics and user access |
| Data plane | DeepintShield | Gateway, guardrails, policy checks, caching and logging |
| Prompts and responses | Processed in DeepintShield Cloud | In a region chosen to meet your requirements; content logging can be switched off and zero retention is available |
| Provider keys and model usage | You | You bring your own provider keys; model usage is billed on your own accounts with 0% markup |
Need prompts to stay in your own network? See hybrid deployment or self-hosted deployment.
Compare the three deployment options
All three options run the same gateway, guardrails and agent controls. They differ in who operates each part and where your data stays.
| Fully Managed Cloud | Hybrid Cloud | Self-Hosted | |
|---|---|---|---|
| Control plane | DeepintShield runs it | DeepintShield runs it | You run it |
| Data plane (gateway, guardrails, policy checks) | DeepintShield runs it | You run it in your cloud | You run it in your cloud |
| Where prompts, responses and keys stay | In DeepintShield Cloud, in a region chosen to meet your requirements; zero retention available | In your VPC: no prompt, response, key or audit data leaves | In your environment: no data leaves and nothing calls home |
| Link to DeepintShield | Your apps call the cloud endpoint | One outbound-only link, pinned mutual TLS on port 443 | None required; air-gapped option |
| Set-up effort | None: sign up and change one base URL | One Helm chart in your Kubernetes cluster | Helm chart and Terraform; you run upgrades, scaling and secrets |
| Who it suits | Fast evaluation and teams without strict data-residency rules | Data residency without running the control plane | Teams that must own the full stack, including sovereign and air-gapped sites |
| Plans | Developer (free), Cloud Team ($49 a month), Cloud Business ($249 a month) | Enterprise VPC, from $12,000 a year | Enterprise Self-Hosted, from $24,000 a year |
Prices are in USD and exclude taxes. See pricing for request limits, seats and add-ons.
Fully Managed Cloud at a glance
How we protect data in each mode is set out on the trust and security page.
OpenAI-compatible base URL
Change one base URL and keep your OpenAI, Anthropic, Google GenAI or Bedrock client code.
Isolated tenants
Each tenant’s workspace, policies, keys and logs are isolated from every other tenant in the cloud.
Encryption in transit and at rest
Requests and stored data are encrypted, and TOTP multi-factor sign-in is available on every plan.
Configurable zero retention
Switch off content logging so prompts and responses stay out of logs, or ask for zero retention.
Managed cloud questions
Where is my data hosted?
Your data is hosted in DeepintShield Cloud, in a region chosen to meet your requirements. The managed cloud is multi-region, so tell us your residency needs before you send production traffic. Talk to our team about regions.
Can prompts be kept out of logs?
Yes, switch off content logging and request and response bodies are no longer stored. Usage data such as tokens, cost and latency is still recorded, and zero retention is available. See built-in observability in the docs.
Can I move to hybrid or self-hosted later?
Yes, you can move when your data rules change. Your applications keep the same OpenAI-compatible API and only need a new base URL that points at your own host; plan the move of policies and keys with our team.
Which plans run on the managed cloud?
Three plans run on the managed cloud: Developer, Cloud Team and Cloud Business. Developer is free with 50,000 requests a month, Cloud Team is $49 a month with 500,000 requests, and Cloud Business is $249 a month with 3,000,000 requests; yearly billing costs ten times the monthly price.
Start in minutes with nothing to install
Create a free Developer workspace and send your first governed request today.