> ## Documentation Index
> Fetch the complete documentation index at: https://docs.devic.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Multi-tenant

> Serving your own customers with one Devic account: who they are, what they consume, and what they are allowed.

If you embed Devic in a product, one Devic account serves many of *your* customers. Devic calls each of them a **tenant**, and each user or team inside them a **subtenant**.

Everything that follows — cost, limits, memory, conversations, connected apps — is partitioned along those two axes.

![Tenants](https://mintcdn.com/devic/TaMbtKJRXl9eU5LD/images/tenants/list.png?fit=max\&auto=format\&n=TaMbtKJRXl9eU5LD\&q=85\&s=ff69df83246fe9b9e96e740b43b37a5e)

***

## Tenants register themselves

You do not create tenants. The first time a message or an agent run carries a `tenantId`, Devic records it and starts attributing to it.

```json theme={null}
POST /v1/assistants/support/messages
{
  "message": "Where is my order?",
  "tenantId": "acme-corp",
  "subtenantId": "alex@acme.com"
}
```

From that call onwards, *acme-corp* appears in the tenants list with its conversations, its cost and its subtenants.

> [!NOTE]
>
> Attribution is forward-only. A tenant starts accumulating cost from the moment it first appears — traffic that arrived before it was identified is not retroactively assigned.

***

## What Devic keeps about them

Devic fills in what it can and lets you correct it: a display name, an email, a logo, and the corporate domain inferred from the subtenants' addresses. The inference is deliberately conservative — it needs at least two distinct subtenants sharing a non-generic domain, so one person with a Gmail address never turns into a company. Edit a field by hand and the automatic detection stops touching it.

***

## The three things you get for free

> [card] Cost per customer
>
> Daily and monthly cost by tenant and subtenant, broken down by agent and assistant.

> [card] Isolation
>
> Memory, connected apps and conversations are partitioned by tenant by default.

> [card] Limits
>
> Consumption ceilings per plan, enforced before the model is called.

***

## Next steps

> [card] [Usage limits and plans](https://docs.devic.ai/devic/multi-tenant/usage-limits.md)
>
> Tiers, windows and what happens when someone runs out.

> [card] [Tenant sessions](https://docs.devic.ai/devic/multi-tenant/tenant-sessions.md)
>
> Proving which customer is calling, instead of trusting the browser.

> [card] [Memory buckets](https://docs.devic.ai/devic/memory/buckets.md)
>
> How memory is partitioned along the same axes.

> [card] [Integrations per end user](https://docs.devic.ai/devic/integrations/for-end-users.md)
>
> Each customer connecting their own accounts.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.