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

# Models

> The model type represents a configured LLM endpoint with its provider binding, rate limits, and budget controls.

export const EditionBadge = ({edition}) => <Tooltip tip={edition === "ee" ? "Requires an Enterprise Edition license." : "Available in the Community Edition."}>
    <span style={{
  fontFamily: "RobotoMono, monospace",
  fontSize: "12px",
  textTransform: "uppercase",
  letterSpacing: "0.04em",
  border: "1px solid var(--imp-hair-light)",
  padding: "2px 8px"
}}>
      {edition === "ee" ? "Enterprise" : "Community"}
    </span>
  </Tooltip>;

A `model` record defines one LLM connection available to agents on the platform. It points to a provider by name, carries the auth variable for credentials, and optionally enforces rate and cost limits per budget window. See [Models](/administration/models) for product context.

```graphql theme={null}
type model {
  name: String!
  description: String
  provider: String!
  authvariable: String
  active: Boolean
  requests_per_window: Float
  window_seconds: Float
  token_budget: Float
  cost_budget_usd: Float
  budget_window: String
  last_processed_at: Date
  embeddings_updated_at: Date
  rights_mode: String
  created_by: Float!
  createdAt: Date
  updatedAt: Date
  id: ID!
  RBAC: RBACData
}
```

## Field notes

| Field                   | Notes                                                                                           |
| ----------------------- | ----------------------------------------------------------------------------------------------- |
| `provider`              | Internal provider slug (e.g. `"anthropic"`, `"azure_openai"`); matches the LiteLLM provider ID. |
| `authvariable`          | Name of the `variable` record that holds the API key or credential for this model.              |
| `requests_per_window`   | Maximum number of requests allowed per `window_seconds`; `null` means unlimited.                |
| `window_seconds`        | Duration in seconds for the rate-limit window (e.g. `60` for per-minute limiting).              |
| `token_budget`          | Maximum cumulative tokens per `budget_window`; `null` means unlimited.                          |
| `cost_budget_usd`       | Maximum cumulative cost in USD per `budget_window`; `null` means unlimited.                     |
| `budget_window`         | Calendar boundary for budget resets: `"daily"`, `"weekly"`, `"monthly"`, or `"yearly"`.         |
| `rights_mode`           | `"public"` or `"private"`; controls which users can assign this model to agents.                |
| `created_by`            | Numeric ID of the creating user.                                                                |
| `last_processed_at`     | Timestamp of the last knowledge-embedding pass over this record.                                |
| `embeddings_updated_at` | Timestamp when vector embeddings were last regenerated.                                         |

## Example query

```graphql theme={null}
query {
  modelsPagination(
    limit: 20
    filters: [{ active: { eq: true } }]
    sort: { field: "name", direction: ASC }
  ) {
    items {
      id
      name
      provider
      active
      token_budget
      cost_budget_usd
      budget_window
    }
    pageInfo {
      currentPage
      hasNextPage
    }
  }
}
```