> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://respan.ai/docs/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://respan.ai/docs/_mcp/server.

# Qwen Code (gateway)

> Set up Qwen Code with the Respan gateway.

Route [Qwen Code](https://github.com/QwenLM/qwen-code)'s LLM calls through the Respan gateway for automatic logging, caching, and model switching. Qwen Code supports any OpenAI-compatible endpoint, so only your `RESPAN_API_KEY` is needed.

## Setup

#### Install Qwen Code

```bash
npm install -g @qwen-code/qwen-code@latest
```

#### Set environment variables

Add to your shell profile (`.bashrc`, `.zshrc`, or PowerShell `$PROFILE`), or to `~/.qwen/.env`:

```bash
export OPENAI_API_KEY="YOUR_RESPAN_API_KEY"
export OPENAI_BASE_URL="https://api.respan.ai/api"
export OPENAI_MODEL="gpt-4o"
```

Then tell Qwen Code to use the OpenAI-compatible auth type without the interactive `/auth` prompt. Add to `~/.qwen/settings.json`:

```json
{
  "security": {
    "auth": {
      "selectedType": "openai"
    }
  }
}
```

No separate provider key needed. The Respan gateway handles provider authentication.

#### Run Qwen Code

```bash
qwen
```

For a one-shot, non-interactive run:

```bash
qwen -p "your prompt"
```

All LLM calls now route through Respan.

## Switch models

Change `OPENAI_MODEL` to use any of the 1000+ models available through the gateway.

```bash
export OPENAI_MODEL="gpt-4o"
# export OPENAI_MODEL="claude-sonnet-4-5-20250929"
# export OPENAI_MODEL="gemini/gemini-3.5-flash"
```

See the [full model list](https://platform.respan.ai/platform/models).