STACKIT

通过 Mastra 的模型路由器访问 8 个 STACKIT 模型。系统会自动使用 STACKIT_API_KEY 环境变量完成身份验证。

更多信息请参阅STACKIT 文档。

.env

STACKIT_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: 'stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8',
})

// 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)
}

信息

Mastra 使用兼容 OpenAI 的 /chat/completions endpoint。部分 Provider 特有功能可能不可用，详情请参阅STACKIT 文档。

模型

8 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
stackit/cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic	128K						$0.53	$0.76
stackit/google/gemma-3-27b-it	37K						$0.53	$0.76
stackit/intfloat/e5-mistral-7b-instruct	4K						$0.02	$0.02
stackit/openai/gpt-oss-120b	131K						$0.53	$0.76
stackit/openai/gpt-oss-20b	131K						$0.18	$0.29
stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8	218K						$2	$2
stackit/Qwen/Qwen3-VL-Embedding-8B	32K						$0.09	$0.09
stackit/Qwen/Qwen3.6-27B	262K						$0.53	$0.76

高级配置

自定义请求头

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: 'custom-agent',
  name: 'custom-agent',
  model: {
    url: 'https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1',
    id: 'stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8',
    apiKey: process.env.STACKIT_API_KEY,
    headers: {
      'X-Custom-Header': 'value',
    },
  },
})

动态选择模型

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
      ? 'stackit/openai/gpt-oss-20b'
      : 'stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8'
  },
})