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

# SDKs

> Drop the base URL into any OpenAI-compatible harness.

# SDKs

Point any OpenAI-compatible client at `https://api.refuseless.dev/v1`.

## Python

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

client = OpenAI(
    base_url="https://api.refuseless.dev/v1",
    api_key="YOUR_KEY",
)
resp = client.chat.completions.create(
    model="glm-5.3-refuseless",
    messages=[{"role": "user", "content": "Write a tight system prompt."}],
)
print(resp.choices[0].message.content)
```

## Node / TypeScript

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

const client = new OpenAI({
  baseURL: "https://api.refuseless.dev/v1",
  apiKey: process.env.REFUSELESS_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "glm-5.3-refuseless",
  messages: [{ role: "user", content: "Write a tight system prompt." }],
});
console.log(resp.choices[0].message.content);
```

## Agent harnesses

Anything that accepts a custom `baseURL` works unchanged — Claude Code,
Codex, OpenClaw, and similar OpenAI-compatible harnesses. Set the base URL,
set the model id from the [lineup](/models), stream as usual.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.