> Discover all available pages from the documentation index: https://mastra.zisheng.pro/zh-TW/llms.txt

# ![Regolo AI 標誌](https://models.dev/logos/regolo-ai.svg)Regolo AI

透過 Mastra 的模型路由器存取 18 個 Regolo AI 模型。系統會自動使用 `REGOLO_API_KEY` 環境變數完成身分驗證。

如需進一步了解，請參閱[Regolo AI 文件](https://docs.regolo.ai/)。

```bash
REGOLO_API_KEY=your-api-key
```

```typescript
import { Agent } from '@mastra/core/agent'

const agent = new Agent({
  id: 'my-agent',
  name: 'My Agent',
  instructions: 'You are a helpful assistant',
  model: 'regolo-ai/apertus-70b',
})

// 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[Regolo AI 文件](https://docs.regolo.ai/)。

## 模型

| Model                               | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
| ----------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
| `regolo-ai/apertus-70b`             | 30K     |       |           |       |       |       | $0.46      | $2          |
| `regolo-ai/brick-complexity-pro`    | 100K    |       |           |       |       |       | $0.12      | $0.46       |
| `regolo-ai/brick-v1-beta`           | 100K    |       |           |       |       |       | —          | —           |
| `regolo-ai/deepseek-ocr-2`          | 4K      |       |           |       |       |       | —          | —           |
| `regolo-ai/faster-whisper-large-v3` | 448     |       |           |       |       |       | —          | —           |
| `regolo-ai/gemma4-31b`              | 100K    |       |           |       |       |       | $0.46      | $2          |
| `regolo-ai/glm5.2`                  | 96K     |       |           |       |       |       | $2         | $6          |
| `regolo-ai/gpt-oss-120b`            | 128K    |       |           |       |       |       | $1         | $4          |
| `regolo-ai/gpt-oss-20b`             | 128K    |       |           |       |       |       | $0.40      | $2          |
| `regolo-ai/llama-3.3-70b-instruct`  | 128K    |       |           |       |       |       | $0.60      | $3          |
| `regolo-ai/mistral-small-4-119b`    | 256K    |       |           |       |       |       | $0.75      | $3          |
| `regolo-ai/qwen-image`              | 8K      |       |           |       |       |       | $0.50      | $2          |
| `regolo-ai/qwen3-coder-next`        | 262K    |       |           |       |       |       | $0.30      | $1          |
| `regolo-ai/qwen3-embedding-8b`      | 33K     |       |           |       |       |       | $0.10      | $0.10       |
| `regolo-ai/qwen3-reranker-4b`       | 33K     |       |           |       |       |       | $0.12      | $0.12       |
| `regolo-ai/qwen3.5-122b`            | 262K    |       |           |       |       |       | $0.90      | $4          |
| `regolo-ai/qwen3.5-9b`              | 262K    |       |           |       |       |       | $0.15      | $0.60       |
| `regolo-ai/qwen3.6-27b`             | 120K    |       |           |       |       |       | $0.58      | $2          |

## 進階設定

### 自訂標頭

```typescript
const agent = new Agent({
  id: 'custom-agent',
  name: 'custom-agent',
  model: {
    url: 'https://api.regolo.ai/v1',
    id: 'regolo-ai/apertus-70b',
    apiKey: process.env.REGOLO_API_KEY,
    headers: {
      'X-Custom-Header': 'value',
    },
  },
})
```

### 動態選擇模型

```typescript
const agent = new Agent({
  id: 'dynamic-agent',
  name: 'Dynamic Agent',
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === 'complex'
    return useAdvanced ? 'regolo-ai/qwen3.6-27b' : 'regolo-ai/apertus-70b'
  },
})
```