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

# Model Parameter

> Override the AI model for specific actions in your workflow prompts

The `model` parameter lets you specify which AI model to use for individual `focused_action` and screenshot actions that include `extract_prompt`, directly in your workflow prompt.

<Info>
  For comprehensive documentation on model configuration, including workflow-level settings, custom configurations, and supported providers, see [Model Configuration](/concepts/model-configuration).
</Info>

## Syntax

Add `model="Model Name"` to your action:

```text theme={null}
Use focused_action with model="Sonnet 4.5 (Thinking)" to verify the order status

Take screenshot with extract_prompt="Extract invoice data" and model="Sonnet 4.5"
```

## Using the Model Picker

In the prompt editor:

1. **Slash menu**: Type `/` → select "Model Override" → inserts `model=""`
2. **Tab autocomplete**: Type `model` → press Tab → inserts `model=""`
3. **Direct typing**: Type `model=""` manually

With your cursor inside the quotes, a dropdown appears showing all available models. Hover to see model details including computer use support.

The dropdown also includes **System Default**, which clears the override and lets Cyberdesk choose the normal default for that action.

## Computer Use Requirement

<Warning>
  **For `focused_action`**: Prefer models marked as "computer use" models. The editor warns if you pick another configured model, because non-computer-use models may not handle clicking, typing, and navigation reliably.

  **For `extract_prompt`**: Any vision-capable model works since it only reads the screen.
</Warning>

## What Happens If You Omit `model`

* `focused_action` uses the workflow's main agent model, or Cyberdesk's main default if the workflow does not set one
* `extract_prompt` uses Cyberdesk's current extraction default unless you override it

## Example Prompts

### Using Different Models for Different Tasks

```text theme={null}
Navigate to the patient records system and log in.

Use focused_action with model="Sonnet 4.5 (Thinking)" to find the patient 
whose name is {patient_name} and MRN ends with {mrn_suffix}. This requires 
careful reasoning to match the correct record.

Once on the patient chart, take a screenshot with extract_prompt="Extract 
all vital signs as JSON: {blood_pressure, heart_rate, temperature, 
oxygen_saturation}" and model="Sonnet 4.5"

Navigate to the lab results tab and extract data from each page:
- Take screenshot with extract_prompt="Extract lab results as JSON array" 
  and model="Sonnet 4.5" and process_async="batch"
- Scroll down
- Repeat until all results captured
```

### Cost Optimization with Model Selection

```text theme={null}
Open the invoice management portal.

Search for invoice {invoice_number} and open the details page.

Use focused_action with model="Sonnet 4.5 (Thinking)" to verify this is 
the correct invoice by checking the customer name matches {customer_name} 
and the date is {invoice_date}.

Take a screenshot with extract_prompt="Extract complete invoice data: 
invoice_number, date, customer info, all line items with descriptions 
and amounts, subtotal, tax, and total. Format as detailed JSON." 
and model="Sonnet 4.5" and process_async="run"

Continue to the next invoice while extraction runs in background.
```

### Complex Decision-Making with Thinking Models

```text theme={null}
Navigate to the appointment scheduling system.

Use focused_action with model="Sonnet 4.5 (Thinking)" to analyze the 
calendar and find an available slot that meets ALL criteria:
- Day is {preferred_day}
- Time is between {earliest_time} and {latest_time}
- Provider is {preferred_doctor}
- Duration allows for {appointment_length} minutes

If no slot meets all criteria, use focused_action with model="Sonnet 4.5 (Thinking)" 
to find the closest alternative and explain the tradeoff.

Click to book the selected slot.
```

### Batch Extraction with Consistent Model

```text theme={null}
Open the product catalog and navigate to category {category_name}.

For each page of products:
- Take screenshot with extract_prompt="Extract all visible products as JSON: 
  {sku, name, price, stock_status, rating}" and model="Sonnet 4.5" 
  and process_async="batch"
- Scroll to next page
- Repeat until end of catalog

All extractions use the same fast model for consistent results and cost.
```

### Verification Steps with Reasoning

```text theme={null}
Submit the insurance claim form.

Use focused_action with model="Sonnet 4.5 (Thinking)" to analyze the 
confirmation screen:
- Verify the claim ID is displayed
- Check that all submitted fields match our input values
- Identify any warnings or additional steps required
- Save the claim ID as {{claim_id}}

If any discrepancies are found, use declare_task_failed with details.

Take screenshot with extract_prompt="Extract confirmation details: 
claim_id, submission_date, estimated_processing_time, any reference 
numbers" and model="Sonnet 4.5"
```

### Mixed Extraction Strategy

```text theme={null}
Open the monthly financial report.

Fast clipboard extraction for key fields:
- Triple-click Report Date field, use copy_to_clipboard with key "report_date"
- Triple-click Total Revenue field, use copy_to_clipboard with key "total_revenue"

Vision extraction for complex content:
- Take screenshot of the revenue breakdown chart with extract_prompt=
  "Extract revenue by category from this chart as JSON" and model="Sonnet 4.5"

- Take screenshot of the expenses table with extract_prompt=
  "Extract all expense line items as JSON array" and model="Sonnet 4.5" 
  and process_async="batch"

Dynamic verification:
- Use focused_action with model="Sonnet 4.5 (Thinking)" to verify the totals 
  in the summary section match the detailed breakdowns
```

## Model Selection Guidelines

| Task Type                                   | Recommended Model                               | Why                                    |
| ------------------------------------------- | ----------------------------------------------- | -------------------------------------- |
| Complex decisions, multi-criteria matching  | Thinking models (e.g., "Sonnet 4.5 (Thinking)") | Better reasoning for nuanced decisions |
| Simple verification, straightforward clicks | Standard computer-use models                    | Faster, lower cost                     |
| Bulk data extraction                        | Fast vision models (e.g., "Sonnet 4.5")         | Speed and cost efficiency              |
| Critical accuracy needs                     | Thinking models with verification               | Reduces errors on important data       |

## Tips

<CardGroup cols={2}>
  <Card title="Default is Usually Fine" icon="check">
    If you don't specify a model, the workflow uses its configured default. Only override when you have a specific reason.
  </Card>

  <Card title="Match Model to Task" icon="bullseye">
    Use thinking models for complex reasoning, standard models for bulk extraction.
  </Card>

  <Card title="Check Computer Use" icon="display">
    The model picker shows which models support computer use. Required for `focused_action`.
  </Card>

  <Card title="Combine with Async" icon="bolt">
    Pair `model=` with `process_async` for efficient bulk extraction with your preferred model.
  </Card>
</CardGroup>

## Related Documentation

* [Model Configuration](/concepts/model-configuration) — Full details on workflow-level and per-action model settings
* [Focused Action](/workflow-prompting/focused-action) — Dynamic decisions and observations
* [Extract Prompt](/workflow-prompting/extract-prompt) — Vision-based data extraction