Skip to content

Meet DeepintShield at Bengaluru Tech Summit 2026, 17 to 19 November, BIEC Hall 1, booth H1A106. Book 20 minutes

Start For Free

Platform · Governance

AI governance platform: who can use which model, with what budget

An AI governance platform controls who can use which model, with what budget and under which policy, and records the proof. DeepintShield does this with virtual keys that carry model access, budgets and rate limits, plus role-based access, single sign-on over OIDC and SCIM sync for your people.

  • Virtual keys with budgets and limits
  • SSO over OIDC, SCIM with Entra ID
  • MFA on every plan
AI governance platform illustration: a shield with a user icon surrounded by identity, building and document icons

Why AI access needs governing

Shared provider keys

One provider key is pasted into many apps, so nobody can tell who spent what or cut off a single user.

No budgets or limits

A runaway agent loop or a busy team can run up a large bill before anyone notices.

No record of who used what

Without an identity on every request, you cannot show which team used which model, or when.

How the AI governance platform works

Governance runs in the same gateway as routing and guardrails. See how a request moves through DeepintShield.

Organise teams and customers

Within a workspace, group usage into teams and customers, each with its own budget and limits.

Issue virtual keys

Each sk-ds- key carries allowed providers and models, budgets, rate limits and MCP tools.

Sign people in

Staff sign in through your OIDC provider, with roles and, for Entra ID, SCIM sync.

Enforce every request

Required headers, budgets and limits are checked before a request reaches any provider.

Governance features

Virtual keys

Keys carry provider and model access, budgets and rate limits. Provider credentials stay on the gateway, never in your apps.

Budgets and limits

Budgets plus request and token limits for customers, teams, keys and providers. Every level must pass.

Routing rules

Routing rules written in CEL steer requests. Developer has 1 rule, Team 10, Business 25 and Enterprise unlimited.

Required headers

A request without a required header gets a 400 error before any provider or MCP tool is called.

MCP tool governance

A key’s MCP configuration is the outer limit: empty means no tools, and request headers can only narrow it.

Role-based access

Admin and Viewer roles plus custom roles across 14 resources and five operations, from View to Download.

Single sign-on over OIDC

Microsoft Entra ID, Okta, Google Workspace, Auth0 or any OIDC provider, with just-in-time provisioning and domain restriction.

SCIM with Entra ID

Sync users from Microsoft Entra ID, with several connections per workspace routed by e-mail domain.

MFA on every plan

Native TOTP multi-factor authentication with single-use recovery codes, including on the free Developer plan.

Teams, customers and per-model budgets need the Team plan or above. Relationship-based authorization with OpenFGA, down to record level, is on Business and above. Compare plans and pricing.

Decide which models each team can reach

The model catalogue lists every provider and model configured on the AI gateway. Virtual keys then decide which of them a team may call, and per-model budgets and rate limits sit in Model Hub usage controls on Team and above.

  • 29 built-in model providers behind one API
  • Over-budget providers drop out of routing
  • Cost is deducted at every level of the hierarchy
AI governance in the DeepintShield console: creating a virtual key with its workspace, guardrail policies and caching settings(opens the full-size image in a new tab)
Creating a virtual key: its workspace, guardrail policies and caching settings.

One key carries the policy

Applications send a virtual key instead of a provider key. The gateway applies that key’s model access, budgets, rate limits and MCP tools, then routes the request. Read the virtual key docs.

  • Send the key as x-deepintshield-vk or a Bearer token
  • Optional: enforce virtual keys on every inference call
pip install openai
export OPENAI_BASE_URL="https://app.deepintshield.com/v1"
export OPENAI_API_KEY="sk-ds-your-virtual-key"

Mapped to AI governance frameworks

Mapped to

  • NIST AI RMF
  • ISO/IEC 42001
  • EU AI Act
  • MITRE ATLAS

Mapping supports your own assessment; it does not replace it. Framework detail and evidence exports are on the AI Compliance page.

Further reading on AI access control

AI governance questions

What is AI governance?

AI governance is the set of rules and records that decide who may use which AI models and tools, at what cost and under which policy. A governance platform enforces those rules on every request and keeps the evidence.

What is a virtual API key?

A virtual key is a DeepintShield key, starting sk-ds-, that applications use instead of a provider key. It carries the models, budgets, rate limits and MCP tools a team may use, while provider credentials stay on the gateway.

Does it work with our identity provider?

Yes, if it supports OIDC. Single sign-on works with Microsoft Entra ID, Okta, Google Workspace, Auth0 and other OIDC providers, and SCIM sync is available for Entra ID. GitHub is not supported as a sign-in connection.

How are budgets enforced?

Budgets and rate limits are checked at every level (customer, team, virtual key and provider configuration), and a request must pass all of them. Cost is deducted at each level, and over-budget providers are dropped from routing. See the budgets and limits docs.

Is MFA included?

Yes. Native TOTP multi-factor authentication is available on every plan, including the free Developer plan, and works with any authenticator app.

Take control of AI access and spend

Issue your first virtual key with a budget on the free Developer plan, or talk to us about rolling out SSO and roles.

Start For Free