Coding Usage

Coding Usage aggregates every local Claude Code and Codex session on your machines into one API-equivalent cost view. Across sessions it totals ( authoritative, estimated), spanning . On a flat subscription you do not actually pay these amounts — the figure answers “what would this have cost on the API”, exactly like Claude Code's own /usage.

Two kinds of cost

Authoritative — for Claude sessions you have opened, the cost is Claude Code's own /usage figure. The status line records it per session to ~/.claude/usage-ledger.json and the report uses it verbatim (no estimation).

Estimated (shown with a leading ~) — older Claude sessions and all Codex sessions have no ledger entry, so their cost is tokens × API list price. Only sessions opened after the status line was configured have an authoritative entry; that is why most rows are estimates.

Per-model breakdown vs. session total

The Cost column is the whole-session total. Expand a row to see every model it used, most expensive first, with that model's tokens and an estimated cost. When the session total is authoritative, the per-model estimates will not sum to exactly the same number — e.g. an authoritative $44.08 next to a per-model subtotal of ~$46.35. That is expected: one is Claude's billed figure, the other is a token-based estimate. It is not a double count.

Models and the <synthetic> marker

Each session lists all models it used. Claude Code subagent and sidechain transcripts from <session-id>/subagents/*.jsonl are folded into the parent session, so a mostly Opus row can also show Sonnet or Haiku when Claude delegated work. Claude Code's internal <synthetic> entries (locally-generated messages such as interrupts and error notices) carry no tokens and no API call, so they are filtered out — they are not a real model.

Codex auto-review sessions

codex-auto-review entries are automatic reviewer-agent transcripts that Codex writes when Auto-review evaluates approval requests. They are read-only model calls, not coding sessions you manually started. When the transcript includes a parent_thread_id, the report attaches the auto-review cost under the matching Codex session instead of showing it as a separate top-level row. Use the Model filter to find sessions that include them.

Filters and saved view

The filter panel is collapsed by default so the charts stay visible first, especially on mobile. The report stores your selected filters, filter-panel state, sort order, page size, expanded state, and active tab in this browser's localStorage. Refreshing the file keeps that view; the Reset filters button only clears the filtering fields.

Monthly attribution

A session's entire cost is attributed to the month it started. Almost all sessions happen within one day, so this rarely matters; a session that spans a month boundary counts in its start month. Per-day splitting is not done because the authoritative /usage figure is a single session total with no daily breakdown.

Caching

Anthropic bills a cache-write premium (5-minute TTL 1.25×, 1-hour 2×) and cheap cache reads (0.1×). OpenAI has no write surcharge — only a cached-input discount — so Codex cache writes are not charged.

Where the data comes from

Each app writes transcripts to its own home directory, so WSL and Windows are separate locations:

CLI vs Desktop is not a different folder — it is recorded inside each transcript and shown in the Surface column. Cloud / container sessions (Codex Cloud tasks, Claude Code on the web) run server-side and leave no local transcript, so they cannot be measured here.

Multiple devices & privacy

Each machine writes a committed data/<host>.json; this site is rebuilt from those files, and the Device filter narrows totals to one machine. The data holds project names, dates and costs — no secrets — but keep the repo private if that matters.

For this host, the previous data/<host>.json is imported before scanning local transcripts. Normal hook runs only add or grow known sessions: an archived, missing, or briefly smaller transcript does not remove already exported history.