Understand your usage
To sync usage to your signed-in VC account, enable Settings → Account → Sync usage to my account on web, desktop, or mobile. Sync is off by default, and the choice is saved separately for each account on each client. While enabled and the client is open, connected environments sync about every five minutes. Signing out or turning the option off stops further uploads and keeps previously synced data. Switching accounts uses that account’s own choice. View the totals on your account portal’s overview. Reports from several devices connected to the same environment count once. Offline environments retain their last synced totals; syncing resumes when a client reconnects. Only daily token and estimated cost totals by provider and model are uploaded, without conversation content or local paths.
Usage counts activity attributable to completed turns requested through VC on your connected environments. External CLI activity and imported history are excluded. It shows token use, cache savings, model breakdowns, and estimated API-equivalent cost. These estimates are not your subscription bill.
Codex, Claude Code, and Grok Build totals come from their CLI session transcripts, attributed to VC turns. When a transcript cannot be matched to a completed VC turn, those providers fall back to the per-turn token ledger so completed work is not dropped. Every other provider VC can drive — OpenCode, Cursor, Antigravity, Command Code, Devin, Kimi, Qwen, Hermes, Pi, Oh My Pi, Kiro, Cline, Qoder, Amp, and any later CLI agent — is counted from the same ledger, when the provider reports usage. Turns from providers that do not report usage contribute no tokens rather than an estimate.
The Tokens view splits input and output. Input is uncached tokens plus cache reads and cache writes; output includes reasoning tokens, which are also shown separately and are not added again. Totals depend on the execution and transcript history available on each server. Running turns are excluded. These totals can therefore undercount usage; missing records are not evidence of zero cost. Subscription limits remain account-wide and may include activity outside VC.
On web and desktop, use the environment dropdown to filter costs, tokens, and limits. All environments are selected by default. The dropdown shows which environments are still scanning; results appear as each one responds.
If recent work is missing or a new model shows no cost, refresh to rescan session history and update model pricing.
When an environment’s usage reporting is reset, Cost and Tokens count only activity after the reset. This applies across reporting windows and survives restarts. Provider session history, conversations, model prices, and subscription limits are unchanged. Other environments keep their own reporting history.
Set custom model prices
On web or desktop, open the environment dropdown on Usage, then choose Model prices to add, edit, or reset a model’s estimated price. Apply to starts with your current Usage filter; choose all environments or select individual destinations. Enter the exact model ID and USD rates per million input and output tokens. You can enter any model ID, including models without public pricing.
Cache read and cache write rates are optional and use the input rate when blank. Enter 0 for
tokens that are free. Saved prices replace automatic pricing for all of that environment’s
history and are shared with clients connected to it. When environments have different prices,
cells show Mixed. Edit rates directly in the table, then choose Save changes to apply all
edited rows. Untouched cells keep each environment’s rate. Select one environment to inspect its
prices. Reset to automatic marks a model’s override for removal when you save; you can undo
it before saving.
Each destination reports whether the change saved. Offline or unavailable environments are marked Not saved. Reconnect them and choose Retry failed saves to finish the same change without writing again to environments that already saved. Changes are not queued after you close the dialog.
Track subscription limits
On web and desktop, choose Quota from the right panel’s + menu to manage limits while working in a thread. The panel shows accounts from that workspace’s environment and supports the same account search, forecasts, refresh, and available reset credits as Usage → Limits.
Usage → Limits lists every subscription account it can see, with one tab per provider. Pick a provider tab to see its pooled quota: each account adds 100% of capacity, so three Claude accounts read out of 300%. The chart shows how much was left over the last few days and a dashed forecast for the next 1, 3, or 7 days. The forecast treats the accounts as interchangeable: the pool keeps spending at its recent rate, moving to the accounts that still have quota when one runs out, and each account refills at its scheduled reset. Below the chart, Pool reaches 0% is when every account would be out at that rate, and Next reset is how much the next refill hands back. Drain rate shows how much quota was spent each hour over the last day. History builds up while the environment is running, so a fresh install starts with only a forecast.
Below the chart, each account is a row with a bar for each window, how much is left, and when it resets. An account that hit its limit shows when it comes back. Search by name, email, or plan, and sort by quota left or next reset. Emails stay masked until you choose Show emails. Refresh quota re-reads one account. Codex and Claude accounts with banked reset credits show the remaining uses. Choose Reset limits to apply the next one through the signed-in CLI, or open the info button on a row and choose Use on a specific credit. A reset refills the windows the credit covers and cannot be undone. The info button also shows credit expiry, refill scope, and past resets. Credit expiry is separate from the quota cycle’s scheduled reset date.
The same account signed in on more than one environment counts once. Filter with the environment dropdown to see what a single machine has.
Account details show upcoming resets in your local time and the latest 50 resets observed by VC. History accumulates as VC receives quota updates; resets from before tracking began are not available.
Every configured provider appears, including providers that are disabled or have not reported quota. These show their status instead of a percentage. All reported windows are included, including model-specific allowances. If a refresh fails, the last known quota remains visible with a notice.
If a window looks stale, refresh Limits to re-check every provider.
Account details show recent successful manual resets observed by your environments. The history survives reconnects and restarts; refreshes and scheduled quota-cycle resets do not add entries. Resets performed outside VC are not reconstructed from changes in quota.
Grok account quotas and Cursor’s Included, Auto, API, and capped On-Demand allowances are read
from the signed-in CLI on each environment. Cursor needs a CLI version with the /usage
command. Its reset date is shown as printed by the CLI, without an estimated countdown.
If Grok’s native protocol cannot report quota, it is unavailable in VC. Antigravity quota is
read from Google for the account signed in to that provider instance. It includes model-specific
allowances and reset times. Other Antigravity sign-in methods do not report subscription quota.
Pick /usage-limits from the composer’s command menu, or send it as a message, to check the
current model’s limits without leaving the conversation. The result opens above the composer and
closes when you dismiss it or send your next message. It uses the same snapshot as Usage → Limits, so it does not run the agent or refresh
anything. The command is offered only for providers with quota data.
API-key accounts may not report subscription limits. This also applies to Claude connections
using a proxy through ANTHROPIC_AUTH_TOKEN.
Existing CLIProxyAPI hubs
Quota and reset credits through CLIProxyAPI are no longer supported. Existing hub settings remain visible in Settings → Providers → Usage providers, where you can remove their saved connection and management key. Use a provider connected directly to its native CLI for supported quota features. Codex reset credits remain available through its native app-server connection.