# Grok (/docs/providers/grok)

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

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

An xAI 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 Grok under "With your plan".
2. The wallet asks xAI for a device code at `https://auth.x.ai/oauth2/device/code` and shows the code in the side panel.
3. It opens a window on xAI's verification page, with the code filled in when xAI gives such an address.
4. The visitor signs in and approves the code.
5. The wallet asks xAI's token endpoint each time a page finishes loading in the window, when the window closes, and when the visitor presses "I approved it". xAI answers `authorization_pending` or `slow_down` until the visitor approves.
6. xAI returns the tokens, and the account is connected.

The code lasts as long as xAI says in `expires_in`, and ten minutes when xAI 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 Grok. The account answers with `grok-4.6`, 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 Grok. 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.x.ai/v1/responses` in OpenAI's Responses protocol. The protocol has no stop sequences, so the wallet leaves `stop` out of its calls.

## Known issues [#known-issues]

- The sign in borrows the OAuth client of Grok's command line tool and asks for its scope, `grok-cli:access`.