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

# Qwen Code on Sideren.

> Three variables in a .qwen/.env file point Qwen Code at the gateway — pick Custom Provider on first launch.

Qwen Code speaks the OpenAI [Chat Completions](/api/chat-completions) dialect, so it runs
on Sideren with three environment variables: the gateway URL (with `/v1`), your Sideren key,
and a [catalog id](/models).

## One command

```sh theme={null}
npx sideren setup --tool qwen --key sdn_your_key
```

The setup helper writes Qwen Code's Sideren settings for you. See [setup helper](/setup).

## Configure

Qwen Code auto-loads a `.qwen/.env` file (project-level, or `~/.qwen/.env` for a user-wide
default). Three variables:

```sh title=".qwen/.env" theme={null}
OPENAI_API_KEY=sdn_your_key
OPENAI_BASE_URL=https://api.sideren.io/v1
OPENAI_MODEL="@sdn/gpt-oss-120b"
```

On first launch pick **Custom Provider** if prompted (or start with
`--auth-type openai`). Switch `OPENAI_MODEL` to `@sdn/glm-5` for heavy sessions.

## Verify

Start `qwen` and send a trivial prompt. To confirm the key works against the gateway
without Qwen Code in the loop:

```sh theme={null}
npx sideren test --key sdn_your_key
```


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