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

# ![EmpirioLabs AI logo](https://models.dev/logos/empiriolabs.svg)EmpirioLabs AI

Accédez à 42 modèles EmpirioLabs AI via le routeur de modèles de Mastra. L’authentification est gérée automatiquement à l’aide de la variable d’environnement `EMPIRIOLABS_API_KEY`.

Pour en savoir plus, consultez la [documentation EmpirioLabs AI](https://docs.empiriolabs.ai).

```bash
EMPIRIOLABS_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: "empiriolabs/deepseek-v3-2"
});

// 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);
}
```

> **Info:** Mastra utilise le point de terminaison `/chat/completions` compatible avec OpenAI. Certaines fonctionnalités propres au Provider peuvent ne pas être disponibles. Consultez la [documentation EmpirioLabs AI](https://docs.empiriolabs.ai) pour plus de détails.

## Modèles

| Model                                  | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
| -------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
| `empiriolabs/deepseek-v3-2`            | 128K    |       |           |       |       |       | $0.57      | $2          |
| `empiriolabs/deepseek-v4-flash`        | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
| `empiriolabs/deepseek-v4-flash-0731`   | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
| `empiriolabs/deepseek-v4-pro`          | 1.0M    |       |           |       |       |       | $2         | $3          |
| `empiriolabs/gemma-4-26b-a4b`          | 262K    |       |           |       |       |       | $0.05      | $0.29       |
| `empiriolabs/glm-4-5-flash`            | 200K    |       |           |       |       |       | —          | —           |
| `empiriolabs/glm-4-7-flash`            | 200K    |       |           |       |       |       | —          | —           |
| `empiriolabs/glm-5-1`                  | 202K    |       |           |       |       |       | $0.82      | $3          |
| `empiriolabs/glm-5-2`                  | 1.0M    |       |           |       |       |       | $1         | $4          |
| `empiriolabs/kimi-k2-6`                | 256K    |       |           |       |       |       | $0.89      | $4          |
| `empiriolabs/kimi-k2-7-code`           | 256K    |       |           |       |       |       | $0.95      | $4          |
| `empiriolabs/kimi-k2-7-code-highspeed` | 256K    |       |           |       |       |       | $2         | $8          |
| `empiriolabs/kimi-k3`                  | 1.0M    |       |           |       |       |       | $3         | $15         |
| `empiriolabs/mimo-v2-5`                | 1.0M    |       |           |       |       |       | $0.70      | $1          |
| `empiriolabs/mimo-v2-5-pro`            | 1.0M    |       |           |       |       |       | $2         | $4          |
| `empiriolabs/minimax-m2-7`             | 200K    |       |           |       |       |       | $0.15      | $0.60       |
| `empiriolabs/minimax-m2-7-highspeed`   | 200K    |       |           |       |       |       | $0.30      | $1          |
| `empiriolabs/minimax-m3`               | 1.0M    |       |           |       |       |       | $0.23      | $0.90       |
| `empiriolabs/mistral-medium-3`         | 130K    |       |           |       |       |       | —          | —           |
| `empiriolabs/mistral-small-4`          | 256K    |       |           |       |       |       | $0.15      | $0.60       |
| `empiriolabs/muse-spark-1-1`           | 1.0M    |       |           |       |       |       | $1         | $4          |
| `empiriolabs/qwen3-5-122b-a10b`        | 256K    |       |           |       |       |       | $0.12      | $0.92       |
| `empiriolabs/qwen3-5-27b`              | 256K    |       |           |       |       |       | $0.09      | $0.69       |
| `empiriolabs/qwen3-5-35b-a3b`          | 256K    |       |           |       |       |       | $0.06      | $0.46       |
| `empiriolabs/qwen3-5-397b-a17b`        | 256K    |       |           |       |       |       | $0.17      | $1          |
| `empiriolabs/qwen3-5-4b`               | 262K    |       |           |       |       |       | $0.04      | $0.07       |
| `empiriolabs/qwen3-5-9b`               | 262K    |       |           |       |       |       | $0.09      | $0.13       |
| `empiriolabs/qwen3-5-flash`            | 1.0M    |       |           |       |       |       | $0.09      | $0.37       |
| `empiriolabs/qwen3-5-plus`             | 1.0M    |       |           |       |       |       | $0.36      | $2          |
| `empiriolabs/qwen3-6-27b`              | 256K    |       |           |       |       |       | $0.41      | $2          |
| `empiriolabs/qwen3-6-35b-a3b`          | 131K    |       |           |       |       |       | $0.07      | $0.42       |
| `empiriolabs/qwen3-6-flash`            | 1.0M    |       |           |       |       |       | $0.25      | $2          |
| `empiriolabs/qwen3-6-max-preview`      | 256K    |       |           |       |       |       | $1         | $8          |
| `empiriolabs/qwen3-6-plus`             | 1.0M    |       |           |       |       |       | $0.50      | $3          |
| `empiriolabs/qwen3-7-flash`            | 1.0M    |       |           |       |       |       | $0.03      | $0.13       |
| `empiriolabs/qwen3-7-max`              | 1.0M    |       |           |       |       |       | $3         | $8          |
| `empiriolabs/qwen3-7-plus`             | 1.0M    |       |           |       |       |       | $0.40      | $2          |
| `empiriolabs/qwen3-8-max`              | 1.0M    |       |           |       |       |       | $2         | $6          |
| `empiriolabs/qwen3-max`                | 256K    |       |           |       |       |       | $1         | $6          |
| `empiriolabs/step-3-5-flash`           | 256K    |       |           |       |       |       | $0.10      | $0.30       |
| `empiriolabs/step-3-5-flash-2603`      | 256K    |       |           |       |       |       | $0.10      | $0.30       |
| `empiriolabs/step-3-7-flash`           | 256K    |       |           |       |       |       | $0.20      | $1          |

## Configuration avancée

### En-têtes personnalisés

```typescript
const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.empiriolabs.ai/v1",
    id: "empiriolabs/deepseek-v3-2",
    apiKey: process.env.EMPIRIOLABS_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});
```

### Sélection dynamique du modèle

```typescript
const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "empiriolabs/step-3-7-flash"
      : "empiriolabs/deepseek-v3-2";
  }
});
```