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

# ![Inference 标志](https://models.dev/logos/inference.svg)Inference

通过 Mastra 的模型路由器访问 9 个 Inference 模型。系统会自动使用 `INFERENCE_API_KEY` 环境变量完成身份验证。

更多信息请参阅[Inference 文档](https://inference.net/models)。

```bash
INFERENCE_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: 'inference/google/gemma-3',
})

// 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[Inference 文档](https://inference.net/models)。

## 模型

| Model                                          | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
| ---------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
| `inference/google/gemma-3`                     | 125K    |       |           |       |       |       | $0.15      | $0.30       |
| `inference/meta/llama-3.1-8b-instruct`         | 16K     |       |           |       |       |       | $0.03      | $0.03       |
| `inference/meta/llama-3.2-11b-vision-instruct` | 16K     |       |           |       |       |       | $0.06      | $0.06       |
| `inference/meta/llama-3.2-1b-instruct`         | 16K     |       |           |       |       |       | $0.01      | $0.01       |
| `inference/meta/llama-3.2-3b-instruct`         | 16K     |       |           |       |       |       | $0.02      | $0.02       |
| `inference/mistral/mistral-nemo-12b-instruct`  | 16K     |       |           |       |       |       | $0.04      | $0.10       |
| `inference/osmosis/osmosis-structure-0.6b`     | 4K      |       |           |       |       |       | $0.10      | $0.50       |
| `inference/qwen/qwen-2.5-7b-vision-instruct`   | 125K    |       |           |       |       |       | $0.20      | $0.20       |
| `inference/qwen/qwen3-embedding-4b`            | 32K     |       |           |       |       |       | $0.01      | —           |

## 高级配置

### 自定义请求头

```typescript
const agent = new Agent({
  id: 'custom-agent',
  name: 'custom-agent',
  model: {
    url: 'https://inference.net/v1',
    id: 'inference/google/gemma-3',
    apiKey: process.env.INFERENCE_API_KEY,
    headers: {
      'X-Custom-Header': 'value',
    },
  },
})
```

### 动态选择模型

```typescript
const agent = new Agent({
  id: 'dynamic-agent',
  name: 'Dynamic Agent',
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === 'complex'
    return useAdvanced ? 'inference/qwen/qwen3-embedding-4b' : 'inference/google/gemma-3'
  },
})
```