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

# ![InferX logo](https://models.dev/logos/inferx.svg)InferX

Access 12 InferX models through Mastra's model router. Authentication is handled automatically using the `INFERX_API_KEY` environment variable.

Learn more in the [InferX documentation](https://model.inferx.net/endpoints).

```bash
INFERX_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: "inferx/Agents-A1"
});

// 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 [InferX documentation](https://model.inferx.net/endpoints) for details.

## Models

| Model                                                 | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
| ----------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
| `inferx/Agents-A1`                                    | 262K    |       |           |       |       |       | —          | —           |
| `inferx/deepseek-v4-flash`                            | 1.0M    |       |           |       |       |       | —          | —           |
| `inferx/Devstral-2-123B-Instruct-2512-int4-AutoRound` | 128K    |       |           |       |       |       | —          | —           |
| `inferx/gemma-4-31B-it-fp8`                           | 262K    |       |           |       |       |       | —          | —           |
| `inferx/mimo-v25`                                     | 1.0M    |       |           |       |       |       | —          | —           |
| `inferx/Ornith-1.0-35B-FP8`                           | 262K    |       |           |       |       |       | —          | —           |
| `inferx/Qwen3-Coder-Next-FP8`                         | 256K    |       |           |       |       |       | —          | —           |
| `inferx/Qwen3-Coder-Next-FP8-no-thinking`             | 260K    |       |           |       |       |       | —          | —           |
| `inferx/Qwen3-Embedding-8B`                           | 33K     |       |           |       |       |       | —          | —           |
| `inferx/Qwen3.6-27B-FP8`                              | 262K    |       |           |       |       |       | —          | —           |
| `inferx/Qwen3.6-35B-A3B-FP8`                          | 262K    |       |           |       |       |       | —          | —           |
| `inferx/Qwen3.6-35B-A3B-fp8-no-thinking`              | 262K    |       |           |       |       |       | —          | —           |

## Advanced configuration

### Custom headers

```typescript
const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://model.inferx.net/endpoints/v1",
    id: "inferx/Agents-A1",
    apiKey: process.env.INFERX_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
      ? "inferx/mimo-v25"
      : "inferx/Agents-A1";
  }
});
```