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

# ![Neuralwatt logo](https://models.dev/logos/neuralwatt.svg)Neuralwatt

Access 22 Neuralwatt models through Mastra's model router. Authentication is handled automatically using the `NEURALWATT_API_KEY` environment variable.

Learn more in the [Neuralwatt documentation](https://portal.neuralwatt.com/docs).

```bash
NEURALWATT_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: "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8"
});

// 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);
}
```

> **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Neuralwatt documentation](https://portal.neuralwatt.com/docs) for details.

## Models

| Model                                   | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
| --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
| `neuralwatt/deepseek-v4-flash`          | 1.0M    |       |           |       |       |       | $0.10      | $0.21       |
| `neuralwatt/gemma-4-31b`                | 262K    |       |           |       |       |       | $0.14      | $0.42       |
| `neuralwatt/glm-5.2`                    | 1.0M    |       |           |       |       |       | $1         | $5          |
| `neuralwatt/glm-5.2-fast`               | 1.0M    |       |           |       |       |       | $1         | $5          |
| `neuralwatt/glm-5.2-flex`               | 1.0M    |       |           |       |       |       | $0.72      | $2          |
| `neuralwatt/glm-5.2-short`              | 200K    |       |           |       |       |       | $1         | $5          |
| `neuralwatt/glm-5.2-short-fast`         | 200K    |       |           |       |       |       | $1         | $5          |
| `neuralwatt/glm-5.2-short-fast-flex`    | 200K    |       |           |       |       |       | $0.72      | $2          |
| `neuralwatt/glm-5.2-short-flex`         | 200K    |       |           |       |       |       | $0.72      | $2          |
| `neuralwatt/kimi-k2.5-fast`             | 262K    |       |           |       |       |       | $0.52      | $3          |
| `neuralwatt/kimi-k2.6-fast`             | 262K    |       |           |       |       |       | $0.69      | $3          |
| `neuralwatt/kimi-k2.6-flex`             | 262K    |       |           |       |       |       | $0.34      | $2          |
| `neuralwatt/kimi-k2.7-code-flex`        | 262K    |       |           |       |       |       | $0.47      | $2          |
| `neuralwatt/kimi-k3`                    | 1.0M    |       |           |       |       |       | $3         | $15         |
| `neuralwatt/kimi-k3-fast`               | 1.0M    |       |           |       |       |       | $3         | $15         |
| `neuralwatt/moonshotai/Kimi-K2.5`       | 262K    |       |           |       |       |       | $0.52      | $3          |
| `neuralwatt/moonshotai/Kimi-K2.6`       | 262K    |       |           |       |       |       | $0.69      | $3          |
| `neuralwatt/moonshotai/Kimi-K2.7-Code`  | 262K    |       |           |       |       |       | $0.95      | $4          |
| `neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8` | 262K    |       |           |       |       |       | $0.69      | $4          |
| `neuralwatt/Qwen/Qwen3.6-35B-A3B`       | 131K    |       |           |       |       |       | $0.29      | $1          |
| `neuralwatt/qwen3.5-397b-fast`          | 262K    |       |           |       |       |       | $0.69      | $4          |
| `neuralwatt/qwen3.6-35b-fast`           | 131K    |       |           |       |       |       | $0.29      | $1          |

## Advanced configuration

### Custom headers

```typescript
const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.neuralwatt.com/v1",
    id: "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8",
    apiKey: process.env.NEURALWATT_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});
```

### Dynamic model selection

```typescript
const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "neuralwatt/qwen3.6-35b-fast"
      : "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8";
  }
});
```