# Qwen (/docs/providers/qwen)

The Qwen account answers with the visitor's Qwen account. The wallet lists it as Qwen under "With your plan", with the id `qwen`.

## What the visitor needs [#what-the-visitor-needs]

A Qwen account with a plan. The wallet shows the account as paid from the plan.

## Sign in [#sign-in]

1. In the wallet, the visitor picks Qwen under "With your plan".
2. The wallet asks Qwen for a device code at `https://auth.qwen.ai/api/oauth/device/code` and shows the code in the side panel.
3. It opens a window on Qwen's verification page, with the code filled in when Qwen gives such an address.
4. The visitor signs in and approves the code.
5. The wallet asks Qwen's token endpoint each time a page finishes loading in the window, when the window closes, and when the visitor presses "I approved it". Qwen answers `authorization_pending` or `slow_down` until the visitor approves.
6. Qwen returns the tokens, and the account is connected.

The code lasts as long as Qwen says in `expires_in`, and ten minutes when Qwen gives no duration. The wallet renews the access token with the refresh token from one minute before it expires.

## Models [#models]

The wallet has no model list for Qwen. The account answers with `qwen3.8-max`, and the side panel shows no model buttons for its sites.

## Usage and limits [#usage-and-limits]

The wallet reads no usage header specific to Qwen. It reads `x-ratelimit-remaining-tokens` and `x-ratelimit-limit-tokens` on any answer that carries them, as it does for every account. Without them, the card keeps saying "Usage shows after the first answer", and Auto ranks the account among the accounts with no reading.

## Calls [#calls]

Answers come from `https://api.qwen.ai/compatible-mode/v1/chat/completions` in the OpenAI chat completions protocol. All four request options reach Qwen.

## Known issues [#known-issues]

- The sign in borrows the OAuth client of Qwen Code, Qwen's command line tool (`qwen-code-cli`), with its scope `model:invoke profile:read`.