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

# Model

> Choose which LLM powers your agent – including PolyAI Raven, our proprietary model family built for conversational AI.

Choose the LLM that powers your agent. The model directly affects response quality, latency, and cost – a wrong choice can make your agent slow, expensive, or inaccurate.

<Tip>
  **Recommended:** PolyAI's **[Raven](/agent-settings/raven)** model family is purpose-built for conversational AI and is the recommended choice for most deployments. Raven supports 24+ languages, delivers sub-300ms latency, and produces concise, natural responses without extensive prompt engineering. **Raven 3.5** powers both voice and chat, with auto-reasoning and out-of-domain detection.
</Tip>

## Available models

<Tabs>
  <Tab title="PolyAI Raven (Recommended)" icon="brain">
    PolyAI's proprietary **[Raven](/agent-settings/raven)** model family is specialized for customer service across voice and chat. Raven eliminates the trade-off between speed and accuracy – delivering sub-300ms latency, fewer errors, and more natural responses than general-purpose LLMs.

    **Raven 3.5** is the recommended model for all deployments. It supports voice and chat, 24+ languages, and has powerful auto-reasoning, out-of-domain detection, custom style following, and built-in safety.

    <Card title="Learn more about Raven" icon="arrow-right" href="/agent-settings/raven">
      Full details on capabilities, supported languages, and why Raven is recommended for most deployments.
    </Card>
  </Tab>

  <Tab title="OpenAI" icon="wand-magic-sparkles">
    | Model            | Good for                                                        |
    | ---------------- | --------------------------------------------------------------- |
    | **GPT-5.2**      | High-quality interactions requiring nuance and strong reasoning |
    | **GPT-5.2 chat** | Extended dialogue and conversational stability                  |
    | **GPT-5 mini**   | Lower latency and reduced cost for mid-complexity use cases     |
    | **GPT-5 nano**   | Simple tasks and fast-response workloads                        |
    | **GPT-4o**       | Versatile balance of reasoning, speed, and cost                 |
    | **GPT-4o mini**  | Everyday queries and high-volume deployments                    |
    | **GPT-4.1**      | Strong reasoning with improved cross-task performance           |
    | **GPT-4.1 mini** | Cost-effective, latency-focused for lighter workloads           |
    | **GPT-4.1 nano** | Minimal compute and high throughput                             |

    See [OpenAI model documentation](https://platform.openai.com/docs/models) for detailed specifications.
  </Tab>

  <Tab title="Amazon Bedrock" icon="aws">
    | Model                | Good for                                               |
    | -------------------- | ------------------------------------------------------ |
    | **Claude 3.5 Haiku** | Simple, predictable tasks with strong safety alignment |
    | **Nova Micro**       | Efficiency with strong general-purpose performance     |

    See [Anthropic Claude docs](https://docs.anthropic.com/) and [Amazon Nova docs](https://docs.aws.amazon.com/ai/responsible-ai/nova-micro-lite-pro/overview.html) for more details.
  </Tab>
</Tabs>

## Configuring the model

<img src="https://mintcdn.com/polyai/Qu880HppNqT19Eyr/images/agent-settings/model.png?fit=max&auto=format&n=Qu880HppNqT19Eyr&q=85&s=48f803fa36f166606aaa0d529d5415cf" alt="Model selection" width="3006" height="1424" data-path="images/agent-settings/model.png" />

<Steps>
  <Step title="Open model settings">
    Navigate to **Channels > Voice > [Voice configuration](/voice/voice-configuration)** or **Channels > Chat > [Chat configuration](/webchat/chat-configuration)** to select the model for each channel.
  </Step>

  <Step title="Select a model">
    Choose the desired model from the dropdown.
  </Step>

  <Step title="Save changes">
    Click **Save** to apply your changes.
  </Step>
</Steps>

## Related pages

<CardGroup cols={2}>
  <Card title="Raven" icon="brain" href="/agent-settings/raven">
    Full details on PolyAI's proprietary model family – capabilities, versions, and supported languages.
  </Card>

  <Card title="Bring your own model" icon="plug" href="/agent-settings/byom">
    Connect your own LLM endpoint to PolyAI.
  </Card>

  <Card title="Voice configuration" icon="gear" href="/voice/voice-configuration">
    Select the model for your voice channel.
  </Card>

  <Card title="Chat configuration" icon="message" href="/webchat/chat-configuration">
    Select the model for your chat channel.
  </Card>
</CardGroup>