ResourcesIntegrationsLarge language models

Cerebras

Use Cerebras's fast Llama inference as the language model for your Vapi voice agent.

Cerebras is a large language model provider that runs open models with very fast inference. Connect Cerebras to use its Llama model as the LLM on a Vapi assistant. This page covers what Cerebras is and the model it supports.

What is Cerebras

Cerebras serves open large language models on its own inference hardware, optimized for low latency. On Vapi, you select a Cerebras model as the LLM for a voice agent.

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

Language model

Set model.provider to cerebras and model.model to a Cerebras 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": "cerebras", "model": "llama3.1-8b" }
>  }'

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

ModelModel ID
Llama 3.1 8Bllama3.1-8b
Model providers

Compare every LLM provider Vapi supports.