Qwen Code in the cloud.
A dedicated Linux machine provides browser VS Code and Qwen Code in the terminal. Authentication uses Oyren's built-in credits with any model in the catalog, or an external API key.
Built-in credits, external API keys or sign-in authentication.
Qwen Code supports Oyren's built-in credits at launch. The model picker offers the whole catalog, including models beyond Qwen, because Qwen Code uses the OpenAI-compatible API that Oyren points at OpenRouter. Alternatively, an API key for the selected model can be entered at launch and set inside the codespace. Qwen Code also supports sign-in through the terminal on the machine.
# On Oyren credits or your own key, both set at launch. Nothing else to do. qwen
Credits cover the model calls. The codespace itself is billed by the hour while it runs.
Codespace capabilities
The same machine under every agent. Qwen Code is one way to drive it.
A dedicated Linux machine
Full Linux with sudo supports installing the build dependencies.
VS Code in the browser
Editor, file tree and terminal in one tab, on any device.
A terminal next to the agent
The agent and development server run in separate terminals.
A public URL
Every codespace has a public URL that routes a port for app access from any device.
Billed by the hour while it runs
Runtime is billed by the hour. Stopping the machine stops runtime billing.
Snapshots to pause and resume
Snapshots preserve the machine's state for later use and are billed monthly in credits.
From launch to a public URL with Qwen Code
- 1
Codespace launch with Qwen Code
Codespace launch selects Qwen Code and a model from the catalog on Oyren credits, or an external API key.
- 2
Terminal or Agent app
The qwen command runs in the VS Code terminal. Qwen Code also runs as an Agent app, a chat view on the same machine.
- 3
Task brief and public URL
A task brief describes the build. VS Code supports change review, and a running app port can be assigned a public URL.
Questions about Qwen Code on Oyren
- Does Qwen Code run on Oyren's built-in credits?
- Yes. Qwen Code supports a model selected from the catalog at launch, paid from Oyren credits, without an external API key.
- Can Qwen Code use models other than Qwen's?
- Yes. On Oyren credits the picker shows the whole model catalog, because Qwen Code uses an OpenAI-compatible endpoint that Oyren points at OpenRouter. An external key supports the models available to that key.
- Do I have to sign in to Qwen Code?
- No. With credits or a key set at launch, Qwen Code is ready when the terminal opens. Sign-in through the terminal on the machine is also supported.
- Where does Qwen Code write its changes?
- Qwen Code writes to the codespace's disk, in repos selected at launch or the specified folder. Browser VS Code supports reviewing the changes, and the terminal supports pushing them.
- How is a Qwen Code session billed?
- Two meters apply: model calls use Oyren credits or an external key, and the codespace is billed by the hour while it runs. The machine can be stopped or snapshotted after the task.
Qwen Code sessions on a codespace
A codespace runs Qwen Code with the supported API-key or sign-in method and a task brief.
Start free