ResourcesIntegrationsLarge language models

Perplexity

Connect Perplexity and configure a Sonar model available to your account.

What is Perplexity

Perplexity provides online language models that can generate responses using current web information. Use the Perplexity integration when you want a Sonar model to generate your Vapi assistant’s responses.

Connect Perplexity

Before using Perplexity, connect your account on the Integrations page.

Language model

Set model.provider to perplexity-ai. Set model.model to the exact model ID from the Perplexity Sonar model catalog that your connected account can access.

$curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \
>  -H "Authorization: Bearer $VAPI_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "model": {
>      "provider": "perplexity-ai",
>      "model": "YOUR_PERPLEXITY_MODEL_ID"
>    }
>  }'

For additional configuration options, review the PerplexityAIModel fields in the Create Assistant API reference.

Perplexity Sonar models

Browse the Sonar model IDs currently accepted by Perplexity.

Language models

Compare every language model provider Vapi supports.