tokenstat
tokenstat

Model catalog

Usage cost calculator

Type a token count, pick a model, and see the published API price. The result is an estimate you can compare. It is not an invoice.

Models · AI plans · Install tokenstat to measure real sessions

Using the cheapest published API price for Gpt 5.4 Pro 2026 03 05 ($30 in / $180 out per MTok).

INPUT
$300
10 MTok × $30
OUTPUT
$360
2 MTok × $180
CACHE READ
$120
40 MTok × $3
CACHE WRITE
$0.00
2 MTok × $0

Published API price for this shape

$780

Million tokens × published $/MTok. Cache rates use the cheapest listed cache field when the model is known. Otherwise the custom rates you entered.

Measure the tokens behind your work

The app reads the session logs your coding tools already write and lays them out by model, project, and day. Track the tokens behind your work and the published API price your subscription covered.