Daily Usage By Model
Newest day first. Bars extend left-to-right by token count; 1B tokens = 932 px. Stacked by model and tool. Effort stays in the detail table because it is provider-specific and not always captured.
Cadence
The strongest proof signal is not one large number. It is repeated usage over time.
Peak Day
Largest completed-day total in this public window.
Model And Tool Mix
Breadth across tools and models is shown as aggregate share, not as private project attribution.
Models
Tools
Token Anatomy
The split shows what the providers expose: prompt input, cache behavior, output, and reasoning where available.
Data Quality
This page should be useful as a receipt, so incomplete fields are named directly and kept out of headline charts.
Reasoning effort is shown only when the source log captured it. Claude Code usage is marked not applicable instead of forcing a false effort category.
High cache warmth indicates sustained context-heavy agent sessions, not isolated prompt demos.
Usage is grouped by whether source logs are linked to active assistant-session records, historical local logs, fixtures, or mixed provenance.
Usage detail table
| Provider | Tool | Model | Effort | Total | Input | Cache-warm | Output | Confidence |
|---|---|---|---|---|---|---|---|---|
| Anthropic | Claude Code | claude-fable-5 | N/A | 519,768,989 | 1,679,203 | 495,649,900 | 3,651,884 | local-log-derived |
| Anthropic | Claude Code | claude-opus-4-8 | N/A | 156,411,728 | 124,663 | 148,027,117 | 561,438 | local-log-derived |
| Anthropic | Claude Code | claude-sonnet-4-6 | N/A | 38,417,951 | 908 | 33,209,951 | 584,179 | local-log-derived |
| OpenAI | Codex | Model not captured | Not captured | 13,283,006 | 13,231,133 | 11,362,048 | 51,873 | local-log-derived |
| OpenAI | Codex | gpt-5.4 | Not captured | 4,055,014 | 4,039,153 | 3,804,160 | 15,861 | local-log-derived |
| OpenAI | Codex | gpt-5.5 | Not captured | 2,883,028,086 | 2,870,301,154 | 2,714,890,112 | 9,290,623 | local-log-derived |
| OpenAI | Codex | gpt-5.5 | low | 148,249 | 147,017 | 61,056 | 1,232 | local-log-derived |
| OpenAI | Codex | gpt-5.5 | medium | 805,849,990 | 802,670,354 | 756,545,024 | 2,290,155 | local-log-derived |
| OpenAI | Codex | gpt-5.5 | xhigh | 7,007,203,054 | 6,984,196,346 | 6,779,883,392 | 16,743,311 | local-log-derived |
Method
Source table: usage_rollup_daily
Privacy boundary: public-safe-aggregated-no-prompts-no-paths-no-private-projects
Costs are omitted unless explicitly estimated or reconciled upstream.
This page proves recorded model activity. Shipped work and verification are separate evidence streams.
A token is a model accounting unit, not a shipped-feature metric; shipped output needs separate receipts.
Window: 2026-05-14 to 2026-06-13. Generated at: 2026-06-14T17:28:58Z. Machine-readable data: usage.json.
Neutral Observer Cache Read
A public interpretation of cache behavior should be useful without overstating what token logs can prove.
What It Signals
From a neutral observer's perspective, 96.1% cache warmth is evidence of repeated work inside sustained, context-heavy agent sessions. The ledger shows 10.9B cache-warm input signal against 31.1M cache writes, which suggests the same working context is being reused rather than repeatedly rebuilt from scratch.
What It Does Not Prove
Cache usage is not a shipped-work metric and not a quality score. It does not say whether the work was correct, useful, or efficient end-to-end. It says the interaction pattern is persistent and context-rich; shipped artifacts, commits, reviews, and external outcomes remain separate evidence streams. Provider bucket semantics also differ, so cache-warm input should be read as a directional signal, not a precise cross-provider efficiency benchmark.
Observer Conclusion
The constructive read is that this is a mature usage pattern: large context is being carried forward and amortized across many turns. The risk to watch is context sprawl. A high cache ratio is strongest when paired with pruning, compact task boundaries, and visible output. In this window, output and reasoning tokens total 41.9M, so the page should frame cache warmth as operating continuity, not as a standalone claim of productivity.