# OpenAI SDK

> Use the official OpenAI Python and TypeScript SDKs with Kurrens.

The OpenAI SDKs work unchanged — point them at the Kurrens base URL.

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.kurrens.ai/v1", api_key="<KURRENS_API_KEY>")
```

```ts

const client = new OpenAI({ baseURL: 'https://api.kurrens.ai/v1', apiKey: process.env.KURRENS_API_KEY });
```

You can also configure it with environment variables and no code changes:

```bash
export OPENAI_BASE_URL="https://api.kurrens.ai/v1"
export OPENAI_API_KEY="$KURRENS_API_KEY"
```

Use Kurrens model ids (Hugging Face ids) for `model`. See [Chat Completions](/docs/inference/chat-completions).
