DeepSeek

DeepSeek is a large language model provider whose models generate your voice agent’s responses. Connect DeepSeek to use DeepSeek-V3 or DeepSeek-R1 on a Vapi assistant. This page covers what DeepSeek is and the models it supports.

What is DeepSeek

DeepSeek builds large language models, including the DeepSeek-V3 chat model and the DeepSeek-R1 reasoning model. On Vapi, you select a DeepSeek model as the LLM for a voice agent.

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

Language model

Set model.provider to deep-seek and model.model to a DeepSeek model.

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

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

Related