# Qoder Setup Guide

> Add a custom model in Qoder CLI (v1.1.50+) and point its Base URL and API Key at LLMoxy.

Website: [https://qoder.com](https://qoder.com) · China: [https://qoder.cn](https://qoder.cn)

Before you start, get an [LLMoxy token](https://en.llmoxy.com/docs/get-started/get-token). The **auto** group is recommended. Qoder CLI **v1.1.50** or later is required.

Custom models in the Qoder **IDE** only accept preset vendors (Bailian / DeepSeek / Zhipu / Kimi / MiniMax / MIMO) with their matching API Keys. They **cannot** take an arbitrary Base URL, so they can't connect to LLMoxy. To use the gateway, use the CLI below.

## CLI

```bash
qoder
```

1. Type `/model` and switch to **Custom**.
2. Choose **Add custom model**.
3. Choose OpenAI-compatible or Anthropic-compatible as the protocol.
4. Enter the Base URL, Model ID, name, and API Key in order, save, then switch to that model and send a message to confirm.

| Protocol | Base URL | Example model |
| --- | --- | --- |
| OpenAI-compatible | `https://llmoxy.com/v1` | `grok-4.7` |
| Anthropic-compatible | `https://llmoxy.com` (no `/v1`) | `claude-opus-5-5` |

For the API Key, enter your LLMoxy token.

This is the markdown version of https://en.llmoxy.com/docs/code-tutorials/qoder.
