Skip to main content
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.

​
Available models

Our default, proprietary models optimized for voice AI.
ModelBest for
Raven V2Production-hardened, real-time voice interactions and high retrieval precision
Raven V3Improved grounding, paraphrasing, and robustness for enterprise voice use cases
Raven V3.5All the capabilities of Raven V3, also tuned for chat interactions
Raven V2 and V3 are purpose-built for conversational voice AI and can only be selected in Voice configuration. Raven V3.5 is also tuned for chat and can be selected in both Voice configuration and Chat configuration.

​
Configuring the model

Model selection
1

Open model settings

Navigate to Channels > Voice > Voice configuration or Channels > Chat > Chat configuration to select the model for each channel.
2

Select a model

Choose the desired model from the dropdown.
3

Save changes

Click Save to apply your changes.

Bring your own model

Connect your own LLM endpoint to PolyAI.

Voice configuration

Select the model for your voice channel.

Chat configuration

Select the model for your chat channel.
Last modified on March 27, 2026