> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://poly-ai.ferndocs.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://poly-ai.ferndocs.com/_mcp/server.

# 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: [Raven 3.5](/agent-studio/behavior/models/raven).** PolyAI's purpose-built conversational model — 24+ languages, sub-300 ms latency, powers both voice and chat.

## Available models

#### PolyAI Raven (Recommended)

PolyAI's proprietary **[Raven](/agent-studio/behavior/models/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.

#### [Learn more about Raven](/agent-studio/behavior/models/raven)

Full details on capabilities, supported languages, and why Raven is recommended for most deployments.

#### OpenAI

| 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.

#### Amazon Bedrock

| Model                 | Good for                                                          |
| --------------------- | ----------------------------------------------------------------- |
| **Claude Opus 4.8**   | Highest-capability reasoning for complex, multi-step interactions |
| **Claude Sonnet 4.6** | Balanced quality and speed for general-purpose conversations      |
| **Claude Haiku 4.5**  | Low-latency responses for high-volume, predictable tasks          |
| **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.

## Configuring the model

![Model selection](/_fern-files/_img/d874e9816e20108c3da64f16edb95d95a18cbafa3421d1f9350decfc5caa08c0.webp)

#### Open model settings

Navigate to **Voice > [Voice configuration](/agent-studio/voice/advanced-settings)** or **Messaging > [Chat configuration](/agent-studio/messaging/advanced/configuration)** to select the model for each channel.

#### Select a model

Choose the desired model from the dropdown.

#### Save changes

Click **Save** to apply your changes.

## Related pages

#### [Raven](/agent-studio/behavior/models/raven)

Full details on PolyAI's proprietary model family – capabilities, versions, and supported languages.

#### [Bring your own model](/agent-studio/behavior/models/bring-your-own-model-byom)

Connect your own LLM endpoint to PolyAI.

#### [Voice configuration](/agent-studio/voice/advanced-settings)

Select the model for your voice channel.

#### [Chat configuration](/agent-studio/messaging/advanced/configuration)

Select the model for your chat channel.