Upstage

通过 Mastra 的模型路由器访问 4 个 Upstage 模型。系统会自动使用 UPSTAGE_API_KEY 环境变量完成身份验证。

更多信息请参阅Upstage 文档。

.env

UPSTAGE_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: 'upstage/solar-mini',
})

// 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Upstage 文档。

模型

4 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
upstage/solar-mini	33K						$0.15	$0.15
upstage/solar-pro2	66K						$0.25	$0.25
upstage/solar-pro3	131K						$0.25	$0.25
upstage/solar-pro4	524K						$0.30	$1

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.upstage.ai/v1/solar',
    id: 'upstage/solar-mini',
    apiKey: process.env.UPSTAGE_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 ? 'upstage/solar-pro4' : 'upstage/solar-mini'
  },
})