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

# How to Choose Your AI Model

> Select the right AI model for your campaigns from the Kakiyo dashboard. Compare model families, understand the quality vs. cost trade-off, and learn how to test and switch models.

<Info>
  **This guide is for dashboard users.** Model selection is done inside the [Kakiyo dashboard](https://app.kakiyo.com) when configuring prompts. No code required.
</Info>

> The AI model you choose directly affects how intelligent and natural your conversations sound. A cheaper model saves credits per message, but poor-quality responses that prospects ignore waste more money than a better model that generates real replies.

## Where to Change the AI Model

1. In the sidebar, click **Prompts**.
2. Click the prompt you want to edit.
3. In the prompt editor, look for the **AI Model** dropdown.
4. Select the model you want to use.
5. Click **Save**.

The model applies to all campaigns that use this prompt. Changing the model does not affect ongoing conversations — only new messages generated after the change.

***

## Available Model Families

| Family                              | Provider  | Strengths                                                                                |
| ----------------------------------- | --------- | ---------------------------------------------------------------------------------------- |
| **Claude** (Sonnet, Haiku, Opus)    | Anthropic | Excellent conversational AI, strong reasoning, natural tone, good at handling objections |
| **GPT** (GPT-4o, GPT-4o-mini, etc.) | OpenAI    | Well-rounded performance, good general knowledge, reliable across conversation types     |
| **Gemini** (Pro, Flash)             | Google    | Strong analytical capabilities, good conversation flow                                   |
| **Grok**                            | xAI       | Varied performance, worth testing for specific use cases                                 |

<Note>
  Available models may change as new versions are released. Check the **AI Model** dropdown in your prompt editor for the current list. You can also see all available models via [API](/api-reference/models/list).
</Note>

***

## Recommended Starting Point

**Claude Sonnet 4.5 (Anthropic)** is the recommended default model as of February 2026. It delivers an excellent balance of:

* Conversation quality and natural tone
* Objection handling capability
* Personalization based on prospect profiles
* Credit efficiency relative to output quality

<Warning>
  Model performance evolves. What's best today may not be best in six months. Re-test periodically and compare against newer models as they become available.
</Warning>

***

## How to Test and Compare Models

### Step 1: Pick Two Models to Compare

Choose your current model and one alternative you want to test.

### Step 2: Test in the Sandbox

1. Go to **Prompts** in the sidebar.
2. Open the prompt you want to test.
3. Set the model to **Model A** and save.
4. Open the **Sandbox** for a campaign using this prompt.
5. Run 3-5 conversations simulating different prospect types (interested, skeptical, busy).
6. Note the quality of responses.
7. Change the model to **Model B** and save.
8. Run the same 3-5 conversations.
9. Compare: which model produced more natural, relevant, and persuasive responses?

### Step 3: Run a Live Comparison (Optional)

For more reliable data:

1. Create two identical campaigns (same offering, same prompt text, same prospect profile).
2. Set Campaign A to use Model A.
3. Set Campaign B to use Model B.
4. Import similar prospects into each (50-100 per campaign minimum).
5. After 2 weeks, compare reply rates and conversation quality in **Analytics**.

***

## Quality vs. Cost: How to Think About It

| Approach                                      | When to use                                                                                                                                |
| --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
| **Optimize for quality** (use the best model) | High-value prospects, enterprise sales, complex products. Better conversations = more meetings = higher ROI even if credit cost is higher. |
| **Optimize for cost** (use a cheaper model)   | High-volume, simpler outreach (event invites, content sharing). Messages are short and straightforward.                                    |
| **Balanced approach**                         | Start with the recommended model, then test cheaper alternatives. Switch only if quality is comparable.                                    |

<Tip>
  Focus on **cost per meeting booked**, not cost per message. A model that costs 2x more per message but books 3x more meetings is the better choice.
</Tip>

***

## Key Metrics to Track When Switching Models

After changing your AI model, monitor these metrics for 1-2 weeks:

| Metric                   | Where to find it            | What to look for                |
| ------------------------ | --------------------------- | ------------------------------- |
| **Reply rate**           | Analytics > Campaign Stats  | Did it go up or down?           |
| **Conversation quality** | Inbox > Read conversations  | Do responses sound natural?     |
| **Qualification rate**   | Analytics > Qualified Leads | Is the AI correctly qualifying? |
| **Meeting booking rate** | Analytics > Campaign Stats  | More or fewer meetings?         |
| **Credit consumption**   | Billing > Credits           | How much are you spending?      |

***

## Related Guides

* [Understanding the Prompts](/guides/core-features/understanding-the-prompts)
* [Understanding the Sandbox](/guides/core-features/understanding-the-sandbox)
* [Billing and Credits](/guides/team-billing/billing-and-credits)
* [Analytics](/guides/optimize-your-results/analytics)