DeepInfra

DeepInfra provides hosted model inference that you can use to generate your voice agent’s responses. In Vapi, you supply the model ID served by DeepInfra rather than choosing from a Vapi-maintained model list.

You can use DeepInfra through Vapi’s default integration, or use your own DeepInfra account by connecting it in Integrations.

Language model

Set model.provider to deepinfra. For model.model, use any model ID available to your DeepInfra account.

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

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

Related