PEAK DAILY TOKENS
—
—
Token usage
Loading usage history…
OpenAI account-reported tokens + retained local Anthropic tokens. Coverage differs between sources.
COMBINED RECORDED TOKENS MIXED COVERAGE
—
Loading…
LONGEST STREAK
— days
—
Token usage
—tokens across recorded history
Recorded tokens—
Daily activity
Hover or focus a day to inspect it. No record Less More
Dates are shown as returned by OpenAI.
Token breakdown
Total = uncached input + cache creation + cache reads + output. Cached tokens count toward volume; this chart does not estimate spending.
Accounting
By model
SELECTED PROJECTS · LOCAL HISTORY
Codex by project
A closer look at the work behind the tokens. These estimates come from retained Codex history; some historical usage may be missing.
Loading projects…
—
——
All projects
Tile area shows share of this view. B = billion tokens · M = million tokens · ↗ opens a project.
Hover or focus a tile for the exact token total.
Exact project totals
| Project | Recorded tokens | Share |
|---|---|---|
| All listed projects | — | — |
—Share of all listed projects
Scheduled to refresh daily at 9 a.m. Pacific when the collector is available. This snapshot covers the selected Codex projects only and stays the same when switching providers above. It includes cached input and subagent work, with inherited counters removed. Its coverage differs from the account-wide totals. Private entries retain their counts while their names and links are withheld.
Monthly totals
| Month | OpenAI | Anthropic | Tokens | Share |
|---|---|---|---|---|
| Total recorded | — | — | — | 100% |
Select a month to explore its daily activity. First and latest months may be partial.
Sources & coverage
Account usage
These are token counts returned by OpenAI’s account usage endpoint, not estimates from conversation length.
Coverage
Classic ChatGPT chat coverage is not verified. This source does not separate ChatGPT from Codex, or break totals down by model, input, output, or cache.
Snapshot
Loading snapshot details…