token-estimate-verification

Locks token and cost predictions in before real API calls run, then scores recorded usage and billed spend against them at a 20 percent tolerance by default, covering chained prompts, cached-token billing categories, batch discounts, zero estimates, and past-invoice reconciliation using rates from the billing period. Use when asked to validate or calibrate a token or cost estimator, check estimates before deployment, explain an unexpected API bill, or track estimation drift over time. Not for looking up current model prices, budget forecasting, spend optimization, or comparing models by price.

Version

v1.0.0

Size

17 KB

Updated

2026-10-10

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.