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

# Choose Your Model

DumGum offers two model tiers: Smart and Pro. The difference is output quality, cost, and features.

## Smart vs Pro

<table style={{tableLayout: 'fixed', width: '100%'}}>
  <thead>
    <tr>
      <th style={{width: '20%'}} />

      <th style={{width: '40%', textAlign: 'left'}}><strong>Smart</strong></th>
      <th style={{width: '40%', textAlign: 'left'}}><strong>Pro</strong></th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td><strong>Quality</strong></td>
      <td>Solid, reliable output</td>
      <td>Highest quality output</td>
    </tr>

    <tr>
      <td><strong>Best for</strong></td>
      <td>High-volume standard conversations</td>
      <td>Premium or complex conversation flows</td>
    </tr>

    <tr>
      <td><strong>Features</strong></td>
      <td>SoulEngine, Core Guardian, Vision Link, Smart Share, Fictional Disclosure, Platform Information, User Suggestions</td>
      <td>Everything in Smart, plus Long-term Memory</td>
    </tr>

    <tr>
      <td><strong>Cost</strong></td>
      <td>€0.025 per reply</td>
      <td>€0.035 per reply</td>
    </tr>
  </tbody>
</table>

New projects use `chat-2-smart` by default.

## Current and Legacy Models

The current generation is `chat-2-smart` and `chat-2-pro`. These models support Vision and Smart Share features.

The `dating-smart-1` and `dating-pro-1` models are the legacy generation, still supported, but new projects should use the `chat-2-*` models.

<Note>To set your model, use the `model` parameter in the API request. See the [API reference](/api-reference/content-creation/endpoints/enqueue-conversation) for details.</Note>