Counting Calls Is Accounting. Scoring Cascades Is Evaluation.

The short version: aiusage

aiusage is a generic AI usage tracker. It counts API calls and token usage across providers — how many calls you made, how many tokens you consumed, how much it cost. It does the accounting layer well: clean numbers, multi-provider coverage, a dashboard of what you spent. But accounting is not evaluation. Counting calls tells you what happened; it does not tell you if you are good at this.

SigRank takes the same token telemetry and asks a different question: how efficiently are you compounding? The headline metric, Υ Yield = cache_read × output / input², rewards the operator who reuses cached context efficiently and penalizes the one who burns fresh input without leverage. aiusage is the ledger; SigRank is the scorecard. Both matter. Only one tells you if you are winning.

Feature comparison

Why counting calls isn't scoring

aiusage answers "how many API calls did I make and how many tokens did I consume?" That is accounting — useful for budgeting, useless for skill evaluation. Two operators can make the same number of calls and burn the same tokens with wildly different outcomes. One reuses cached context efficiently and produces 30K output tokens; the other re-sends the same context every turn and produces 3K. Same call count, ten-fold difference in signal. aiusage sees the same number either way.

SigRank's headline metric, Υ = cache_read × output / input², measures exactly that gap. It rewards the operator who compounds cached context into output and penalizes the one who burns fresh input without leverage. aiusage gives you the call count; SigRank tells you whether the cascade it describes is compounding or burning.

From accounting to evaluation

If you already run aiusage, you have the token counts. SigRank reads the same telemetry and adds the scoring layer usage trackers never had:

npm install -g sigrank
sigrank enroll      # create your operator identity
sigrank submit      # reads logs, scores, signs, publishes

Prefer to inspect before you submit? Run sigrank me --dry-run to see your scored payload locally, or paste your token counts into the /score calculator to compute your Υ Yield, class tier, and compression ratio instantly, no account, no submission, just the numbers.

Frequently asked questions

Is SigRank an aiusage alternative?

They serve different layers. aiusage is a generic AI usage tracker — it counts API calls and token usage across providers. That is accounting: how many calls, how many tokens, how much cost. SigRank is an operator scoring layer: it takes the same token telemetry and computes cascade efficiency (Υ Yield), assigns a class tier, and ranks operators globally. aiusage tells you what you spent; SigRank tells you how efficiently you drove. Counting calls is accounting; scoring cascades is evaluation.

What does aiusage not measure that SigRank does?

aiusage reports API call counts and token usage per provider. SigRank derives the cascade architecture from the same four pillars: Υ Yield (is signal compounding or burning?), compression ratio (output per input), SNR (signal density), Leverage (how much cached context amplifies your input), and Velocity (tokens per unit time). aiusage tells you how many calls you made; SigRank tells you whether your cascade is compounding or burning. Call count is volume; yield is efficiency.

Why is counting API calls not the same as scoring operators?

Counting API calls measures volume, not skill. Two operators can make the same number of calls and burn the same tokens with wildly different outcomes. One reuses cached context efficiently and produces 30K output tokens; the other re-sends the same context every turn and produces 3K. Same call count, ten-fold difference in signal. aiusage sees the same number either way. SigRank sees the 10x difference. Accounting tells you what happened; evaluation tells you how good the operator is.

Can I use both aiusage and SigRank?

Yes. aiusage is a usage tracker; SigRank is a scoring and ranking tool. Run aiusage for the multi-provider API accounting dashboard. Run `sigrank submit` to get your Yield score, class tier, and leaderboard rank. They read from the same local session logs and do not conflict. Many operators use a usage tracker for day-to-day accounting and SigRank for efficiency scoring and leaderboard submission.

Does aiusage have a leaderboard?

No. aiusage is a personal usage tracker — it shows you your own API calls and token consumption. It does not rank operators against each other. SigRank is a public leaderboard: it ranks operators globally by cascade yield, with signed snapshots and verified identities. aiusage is for your own accounting; SigRank is for competition. The first is a ledger; the second is a leaderboard.