Kiro

透過 Mastra 的模型路由器存取 12 個 Kiro 模型。系統會自動使用 KIRO_API_KEY 環境變數進行驗證。

詳情請參閱Kiro 文件。

.env

KIRO_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: 'kiro/auto',
})

// 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 端點。部分 Provider 專屬功能可能無法使用，詳情請參閱Kiro 文件。

模型

12 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
kiro/auto	1.0M						—	—
kiro/claude-haiku-4.5	200K						—	—
kiro/claude-opus-4.5	200K						—	—
kiro/claude-opus-4.6	1.0M						—	—
kiro/claude-opus-4.7	1.0M						—	—
kiro/claude-sonnet-4	200K						—	—
kiro/claude-sonnet-4.5	200K						—	—
kiro/claude-sonnet-4.6	1.0M						—	—
kiro/deepseek-3.2	164K						—	—
kiro/minimax-m2.1	196K						—	—
kiro/minimax-m2.5	196K						—	—
kiro/qwen3-coder-next	256K						—	—

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://q.us-east-1.amazonaws.com',
    id: 'kiro/auto',
    apiKey: process.env.KIRO_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 ? 'kiro/qwen3-coder-next' : 'kiro/auto'
  },
})

直接安裝 Provider

此 Provider 亦可直接安裝為獨立套件，用來取代 Mastra 模型路由器字串。詳情請參閱套件文件。

npm

npm install kiro-acp-ai-provider

pnpm

pnpm add kiro-acp-ai-provider

Yarn

yarn add kiro-acp-ai-provider

Bun

bun add kiro-acp-ai-provider