Atomic Chat

透過 Mastra 的模型路由器存取 5 個 Atomic Chat 模型。系統會自動使用 ATOMIC_CHAT_API_KEY 環境變數完成身分驗證。

如需進一步了解，請參閱Atomic Chat 文件。

.env

ATOMIC_CHAT_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: 'atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF',
})

// 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Atomic Chat 文件。

模型

5 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
atomic-chat/gemma-4-E4B-it-IQ4_XS	33K						—	—
atomic-chat/gemma-4-E4B-it-MLX-4bit	33K						—	—
atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF	131K						—	—
atomic-chat/Qwen3_5-9B-MLX-4bit	33K						—	—
atomic-chat/Qwen3_5-9B-Q4_K_M	33K						—	—

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: 'http://127.0.0.1:1337/v1',
    id: 'atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF',
    apiKey: process.env.ATOMIC_CHAT_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
      ? 'atomic-chat/gemma-4-E4B-it-MLX-4bit'
      : 'atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF'
  },
})