Llama

透過 Mastra 的模型路由器存取 7 個 Llama 模型。系統會自動使用 LLAMA_API_KEY 環境變數完成身分驗證。

如需進一步了解，請參閱Llama 文件。

.env

LLAMA_API_KEY=your-api-key

src/mastra/agents/my-agent.ts

import { Agent } from '@mastra/core/agent'

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

// Generate a response
const response = await agent.generate('Hello!')

// Stream a response
const stream = await agent.stream('Tell me a story')
for await (const chunk of stream) {
  console.log(chunk)
}

資訊

Mastra 使用與 OpenAI 相容的 /chat/completions endpoint。部分 Provider 特有功能可能無法使用，詳情請參閱Llama 文件。

模型

7 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
llama/cerebras-llama-4-maverick-17b-128e-instruct	128K						—	—
llama/cerebras-llama-4-scout-17b-16e-instruct	128K						—	—
llama/groq-llama-4-maverick-17b-128e-instruct	128K						—	—
llama/llama-3.3-70b-instruct	128K						—	—
llama/llama-3.3-8b-instruct	128K						—	—
llama/llama-4-maverick-17b-128e-instruct-fp8	128K						—	—
llama/llama-4-scout-17b-16e-instruct-fp8	128K						—	—

進階設定

自訂標頭

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: 'custom-agent',
  name: 'custom-agent',
  model: {
    url: 'https://api.llama.com/compat/v1/',
    id: 'llama/cerebras-llama-4-maverick-17b-128e-instruct',
    apiKey: process.env.LLAMA_API_KEY,
    headers: {
      'X-Custom-Header': 'value',
    },
  },
})

動態選擇模型

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: 'dynamic-agent',
  name: 'Dynamic Agent',
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === 'complex'
    return useAdvanced
      ? 'llama/llama-4-scout-17b-16e-instruct-fp8'
      : 'llama/cerebras-llama-4-maverick-17b-128e-instruct'
  },
})