Llama

Use llama/<model> with VoltAgent's model router.

Quick start

import { Agent } from "@voltagent/core";

const agent = new Agent({
  name: "llama-agent",
  instructions: "You are a helpful assistant",
  model: "llama/cerebras-llama-4-maverick-17b-128e-instruct",
});

Environment variables

• LLAMA_API_KEY

Provider package

@ai-sdk/openai-compatible

This provider uses the OpenAI-compatible adapter.

Default base URL

https://api.llama.com/compat/v1/

You can override the base URL by setting LLAMA_BASE_URL.

Provider docs

• https://llama.developer.meta.com/docs/models

Models

Show models (7)

• cerebras-llama-4-maverick-17b-128e-instruct
• cerebras-llama-4-scout-17b-16e-instruct
• groq-llama-4-maverick-17b-128e-instruct
• llama-3.3-70b-instruct
• llama-3.3-8b-instruct
• llama-4-maverick-17b-128e-instruct-fp8
• llama-4-scout-17b-16e-instruct-fp8