# AI Gateway Concepts

The Zuplo AI Gateway is a proxy that sits between your apps and LLM providers
like OpenAI, Anthropic, Google, Mistral, and xAI. Instead of each app holding
provider API keys and calling providers directly, every request flows through
the gateway, which applies policies, controls, and monitoring. This page
explains the concepts behind it. For the full feature tour, see the
[AI Gateway overview](../ai-gateway/overview.mdx).

## Providers, teams, and apps

Three building blocks organize an AI Gateway:

- **[Providers](../ai-gateway/providers.mdx)** are the LLM vendors your gateway
  can route to. Administrators configure providers once, including any
  [custom OpenAI-compatible providers](../ai-gateway/custom-providers.mdx), and
  consumers never see the underlying credentials.
- **[Teams](../ai-gateway/teams.mdx)** group users and carry budget limits that
  cascade down the hierarchy: gateway-wide limits, then team limits, then
  per-app limits. See [Usage Limits](../ai-gateway/usage-limits.mdx).
- **[Apps](../ai-gateway/apps.mdx)** are the pieces of software that call the
  gateway — a support chatbot is one app, an internal coding agent is another.
  Each app gets its own gateway URL, its own Zuplo-managed API key, and its own
  policy chain.

## Policy chains

Every app runs its own ordered [policy chain](../ai-gateway/policy-chains.mdx) —
model filtering, fallback models, budgets, semantic caching, guardrails,
tracing, and any [custom policies](../ai-gateway/custom-policies.mdx) written in
TypeScript. Team [policy templates](../ai-gateway/policy-templates.mdx) give new
apps a consistent starting pipeline, and chain changes apply within about a
minute with no redeploy.

App-level controls are opt-in: an app with an empty policy chain applies no
model restrictions, budgets, guardrails, or caching of its own — though gateway
and team usage limits still apply.

## The Universal API

Every app exposes an OpenAI-compatible
[Universal API](../ai-gateway/universal-api.mdx). Point any SDK that supports a
custom base URL at the app's gateway URL, send the app's API key as a bearer
token, and reference models as `providerName/model` (for example
`openai/gpt-5-mini`). One app can use models from several providers through the
same endpoint, so switching providers is a configuration change rather than a
code change.

## How it fits into Zuplo

An AI Gateway is a type of Zuplo project. Its routes and policy declarations
live in a [Git repository](../ai-gateway/source-control.mdx), so gateway changes
go through the same review workflow as the rest of your Zuplo configuration, and
the providers, teams, and apps you configure belong to that project. The
platform primitives — deployment model, environments, analytics — are the same
ones described in [How Zuplo Works](./how-zuplo-works.mdx).

## Next steps

- [Get started with the AI Gateway](../ai-gateway/getting-started.mdx)
- [Browse the SDK integrations](../ai-gateway/integrations/openai.mdx) for
  OpenAI, the Vercel AI SDK, LangChain, Claude Code, Codex, and Goose
- Explore the [AI Gateway policies](../ai-gateway/policies/overview.mdx)