Qwen Code CLI on Windows: Install and First Run

Qwen Code is Qwen’s open-source terminal coding agent. Current releases can use qwen3.8-max, Alibaba’s production flagship, through Model Studio. The CLI can read a repository, edit files, and run commands, so start it in a project where you can review or revert changes.

This covers installing and first-running Qwen Code on Windows, getting it talking to DashScope, and the pricing choices. If you’d rather use Qwen through a different agent, see run Qwen3-Coder with Claude Code.

Step 1: Node#

Qwen Code is a Node package, so install Node first. Native Windows and WSL both work. See the WSL install guide if the project already uses Linux tooling.

curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
nvm install --lts

Step 2: Install Qwen Code#

Install it globally with npm (check the project’s current package name in Alibaba’s docs):

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

Confirm it’s available:

qwen --version

Step 3: API key from DashScope#

Create an Alibaba Cloud Model Studio account and generate a DashScope API key. Set it as the environment variable Qwen Code expects (its docs name the exact variable), and use the international endpoint outside mainland China:

export DASHSCOPE_API_KEY="sk-your-key"

Step 4: First run#

Point Qwen Code at qwen3.8-max and start it in a project folder:

cd ~/myproject
qwen

Give it a small first task such as “summarize this repo and list the entry points”. Confirm that it reads files before allowing edits or commands.

Models#

For a new hosted configuration, start with qwen3.8-max. Use the exact ID shown by your provider because local and third-party deployments often use a different name.

Pricing and coding plan#

• Pay-per-token on DashScope, with a cache-hit discount on repeated input.
• Alibaba’s current Token Plan is credits-based. Check the live plan page for seat prices and credit multipliers.

See Alibaba Coding Plan vs pay-per-token to choose. Verify current quotas and rates on Model Studio, as they change.

Troubleshooting#

• If qwen is not found, reopen the shell and check npm’s global binary path.
• For authentication failures, check the region endpoint and API key variable.
• If the model is not found, confirm that qwen3.8-max is available in the selected workspace and region.
• If file operations are slow in WSL, keep the project in the Linux file system instead of /mnt/c.

Verify the installation#

Run qwen --version, start the CLI in a small repository, and ask it to explain one file without making edits. Once authentication and model selection work, approve a small change and inspect the diff.

To use Qwen elsewhere, see Qwen3-Coder with Codex CLI or use Qwen with Aider.