Vultr

透過 Mastra 的模型路由器存取 10 個 Vultr 模型。系統會自動使用 VULTR_API_KEY 環境變數完成身分驗證。

如需進一步了解，請參閱Vultr 文件。

.env

VULTR_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: 'vultr/MiniMaxAI/MiniMax-M2.7',
})

// 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Vultr 文件。

模型

10 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
vultr/deepseek-ai/DeepSeek-V4-Flash	1.0M						$0.30	$1
vultr/MiniMaxAI/MiniMax-M2.7	205K						$0.30	$1
vultr/moonshotai/Kimi-K2.6	262K						$0.30	$1
vultr/nvidia/DeepSeek-V3.2-NVFP4	131K						$0.55	$2
vultr/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16	262K						$0.13	$0.38
vultr/nvidia/Nemotron-Cascade-2-30B-A3B	262K						$0.15	$0.60
vultr/Qwen/Qwen3.5-397B-A17B	262K						$0.30	$2
vultr/Qwen/Qwen3.6-27B	262K						$0.30	$2
vultr/XiaomiMiMo/MiMo-V2.5-Pro	1.0M						$0.55	$2
vultr/zai-org/GLM-5.2-FP8	393K						$0.85	$3

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.vultrinference.com/v1',
    id: 'vultr/MiniMaxAI/MiniMax-M2.7',
    apiKey: process.env.VULTR_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 ? 'vultr/zai-org/GLM-5.2-FP8' : 'vultr/MiniMaxAI/MiniMax-M2.7'
  },
})