On Cursor Dashboard / Billing & Invoices tab - Other Models pool - incorrect model usage attribution

Support Bug Reports
,
1

Where does the bug appear (feature/product)?

Somewhere else…

Describe the Bug

On Cursor Dashboard / Billing & Invoices tab - Other Models pool seems very broken
I used Fable 5, and saw my Other Model usage percentage grew from 3% to 9%, but the Cursor Dashboard seems to incorrectly attribute this to sand-default (whatever this is).

image
image2172×1562 121 KB

Steps to Reproduce

  1. Use Grok Bot to get sand-default usage grow
  2. use Fable in Cursor IDE
    → get unreasonable usage attribution to models on cursor dashboard

Expected Behavior

it should attribute 6% of my Fable usage to Fable row

Operating System

Windows 10/11

Version Information

Version: 3.17.21 (user setup)
VS Code Extension API: 1.128.0
Commit: 8f2a112cb2845a97b75fd932ea5c470579ca4060
Date: 2026-08-25T01:05:08.089Z
Layout: IDE
Build Type: Stable
Release Track: Default
Electron: 40.10.3
Chromium: 144.0.7559.236
Node.js: 24.15.0
V8: 14.4.258.32-electron.0
xterm.js: 6.1.0-beta.291
OS: Windows_NT x64 10.0.19045

For AI issues: which model did you use?

Fable 5, sand-default

Does this stop you from using Cursor

No - Cursor works, but with this issue

6

Hey @Pavel_Pargachev, thanks for the report!

Good news first: the Other Models total is correct, and the jump you saw (3% to 9%) did come from your Fable 5 usage. sand-default is the internal name for Grok Bot’s model usage. Grok Bot usage is metered separately against its own allowance, so it is not eating into your Cursor quota.

The issue is in the per-model breakdown on that page: Grok Bot rows are currently mixed into the Other Models list, which skews the percentage shown next to each model (including Fable). The team is aware of this issue and working on a fix!