Berget.AI

透過 Mastra 的模型路由器存取 9 個 Berget.AI 模型。系統會自動使用 BERGET_API_KEY 環境變數完成身分驗證。

如需進一步了解，請參閱Berget.AI 文件。

.env

BERGET_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: 'berget/google/gemma-4-31B-it',
})

// 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Berget.AI 文件。

模型

9 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
berget/google/gemma-4-31B-it	128K						$0.28	$0.55
berget/meta-llama/Llama-3.3-70B-Instruct	128K						$0.99	$0.99
berget/mistralai/Mistral-Medium-3.5-128B	262K						$2	$6
berget/mistralai/Mistral-Small-3.2-24B-Instruct-2506	32K						$0.33	$0.33
berget/moonshotai/Kimi-K2.6	262K						$0.83	$4
berget/moonshotai/Kimi-K3	328K						$3	$15
berget/openai/gpt-oss-120b	128K						$0.22	$0.83
berget/zai-org/GLM-4.7	128K						$0.77	$3
berget/zai-org/GLM-5.2	524K						$2	$5

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.berget.ai/v1',
    id: 'berget/google/gemma-4-31B-it',
    apiKey: process.env.BERGET_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 ? 'berget/zai-org/GLM-5.2' : 'berget/google/gemma-4-31B-it'
  },
})