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

# Model Policies

> Control which AI models are available to users in your organization

## What are Model Policies?

Model policies control which AI models users in your organization can access. Choose from two configuration modes — **All models** or **Specific models** — to define the set of available models. Under **All models**, an optional exclusions field lets you block specific models while keeping everything else available.

**Dashboard:** [gateway.getunbound.ai/policies/model-policies](https://gateway.getunbound.ai/policies/model-policies)

## Configuration Modes

### All Models

Allow access to every model available on the Unbound gateway. This is the default and most permissive option.

### Specific Models

Select an explicit list of models that users can access. Only the chosen models will be available — all others are blocked.

Use this to restrict usage to approved models only (e.g., only allow `gpt-4o` and `claude-sonnet-4-20250514`).

### Excluding Specific Models

When using **All models** mode, you can optionally exclude a specific set. In the policy modal, select **All models**, then list the models to block in the **Exclude models (optional)** field. This blocks particular models while keeping everything else available — it is not a separate configuration mode.

Use this to prevent usage of expensive or unapproved models (e.g., exclude `gpt-5.1` to control costs).

## Setting Up Model Policies

1. Go to [Model Policies](https://gateway.getunbound.ai/policies/model-policies) in the Unbound dashboard
2. Choose a mode — **All models** or **Specific models**
3. For **All models**, optionally add models to **Exclude models (optional)**; for **Specific models**, select the models to allow
4. Save your configuration

## Applying to Users

By default, a model policy with no user groups applies to **everyone** in your organization. To restrict a policy to specific teams, assign it to one or more [user groups](https://gateway.getunbound.ai/users/user-groups) during creation or editing.

<Note>
  Model policies also accept a `scope_tool_types` field (via the policy API) to restrict the policy to specific AI tool types; an empty list applies it to all tools. This scoping is currently API-only and not exposed in the dashboard.
</Note>

## Managing via CLI

List and manage model policies from the terminal:

```bash theme={null}
unbound policy list --type MODEL
unbound policy get <policy-id>
```

<CardGroup cols={2}>
  <Card title="CLI Policy Management" icon="terminal" href="/cli/policies">
    Create and manage model policies from the terminal
  </Card>

  <Card title="List Models" icon="brain" href="/integrations/api-models">
    See which models are available in your gateway
  </Card>
</CardGroup>