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

# Quickstart

> Send your first OmniMux Chat Completions request in a few minutes.

This guide covers: create an API key → set the Base URL → send a request.

## Prerequisites

* Access to the [OmniMux console](https://geminix.cc/dashboard)
* Available quota (or a token provisioned by an admin)

## Steps

<Steps>
  <Step title="Create an API key">
    Sign in to the [console](https://geminix.cc/dashboard), open **Tokens / API Keys**, and create a key.

    Keys look like `sk-...`. Store them only on the server or in private environment variables — never in frontend code or public repos.
  </Step>

  <Step title="Set the Base URL">
    Gateway Base URL (API host):

    ```text theme={null}
    https://api.geminix.cc
    ```

    For OpenAI-compatible SDKs, set:

    ```text theme={null}
    https://api.geminix.cc/v1
    ```

    The SDK appends `/chat/completions` and other paths. The console lives at [geminix.cc/dashboard](https://geminix.cc/dashboard) and is separate from the API host.
  </Step>

  <Step title="Send your first request">
    With curl:

    ```bash theme={null}
    curl https://api.geminix.cc/v1/chat/completions \
      -H "Authorization: Bearer $OMNIMUX_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "gpt-4o-mini",
        "messages": [
          {"role": "user", "content": "Hello — introduce yourself in one sentence"}
        ]
      }'
    ```

    `model` must be enabled for your account. Check the console or call `GET /v1/models`. See [Models](/en/guides/models).
  </Step>
</Steps>

## Official OpenAI SDKs

### Python

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

client = OpenAI(
    api_key="sk-...",  # OmniMux token
    base_url="https://api.geminix.cc/v1",
)

resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
```

### Node.js

```javascript theme={null}
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OMNIMUX_API_KEY,
  baseURL: "https://api.geminix.cc/v1",
});

const resp = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);
```

## Next steps

| Topic                                       | What you get                                  |
| ------------------------------------------- | --------------------------------------------- |
| [Configure Base URL](/en/guides/base-url)   | Client / SDK setup                            |
| [Authentication](/en/guides/authentication) | Header format and security notes              |
| [Models](/en/guides/models)                 | How to list and pick a model                  |
| [API reference](/en/api-reference/overview) | Chat, Claude, Gemini, images, video, and more |

<Warning>
  API keys can spend account quota. Keep them server-side only. Rotate immediately if exposed.
</Warning>