# Point the OpenAI SDK at RouterBase in a few minutes

> Source: <https://dev.to/routerbasecom/point-the-openai-sdk-at-routerbase-in-a-few-minutes-epm>
> Published: 2026-06-30 17:17:47+00:00

If your application already uses OpenAI-style chat-completions calls, the lowest-friction way to test another routing layer is to keep the client code familiar and change only the base URL, API key, and model id.

[RouterBase](https://routerbase.com) is designed for that kind of experiment. It exposes an OpenAI-compatible endpoint at `https://routerbase.com/v1`

, so existing SDK setup can stay close to what developers already know.

```
ROUTERBASE_API_KEY=your_routerbase_key
ROUTERBASE_BASE_URL=https://routerbase.com/v1
ROUTERBASE_MODEL=google/gemini-2.5-flash
```

Keeping the model in configuration makes it easier to compare providers later without editing the application path that calls the model.

``` python
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ROUTERBASE_API_KEY,
  baseURL: process.env.ROUTERBASE_BASE_URL || "https://routerbase.com/v1"
});

const completion = await client.chat.completions.create({
  model: process.env.ROUTERBASE_MODEL || "google/gemini-2.5-flash",
  messages: [
    {
      role: "user",
      content: "Write a one-paragraph changelog entry for a developer tool."
    }
  ]
});

console.log(completion.choices[0]?.message?.content);
```

Before using the setup in a production workflow, run a short checklist: