> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tokenfactory.nebius.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Open Router

> Accessing Nebius Token Factory models via Open Router

OpenRouter is a platform/unified API gateway that provides access to a large number of large-language models (LLMs) from many providers.  OpenRouter lets you use a **single API key** and one interface to call many models

[Open Router docs](https://openrouter.ai/docs/quickstart)

## Using Nebius Token Factory Models with Open Router

### Pre-requisites

1. Create an **OPENROUTER\_API\_KEY** at [Open Router](https://openrouter.ai/)
2. Save the key into an environment variable

   ```shellscript theme={null}
   export OPENROUTER_API_KEY="<API_key>"
   ```
3. Install the `openai` package:

   ```shellscript theme={null}
   pip install openai
   ```

## Example

```python theme={null}
import os
from openai import OpenAI

client = OpenAI(
  base_url="https://openrouter.ai/api/v1",
  api_key=os.environ.get("OPENROUTER_API_KEY")
)

completion = client.chat.completions.create(
  model="Qwen/Qwen3-30B-A3B",
  messages=[
    {
        "role": "system",
        "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "How many moons does Jupyter have?"
    }
  ],
  provider={
        "only": ["nebius"],
        "allow_fallbacks": False
    },
  extra_headers={ #optional
    "HTTP-Referer": "<YOUR_SITE_URL>", # Optional. Site URL for rankings on openrouter.ai.
    "X-Title": "<YOUR_SITE_NAME>", # Optional. Site title for rankings on openrouter.ai.
  }
)

print(completion.choices[0].message.content)
```