Observed arrival · 2026-08-25

A Token Calculator That Reads PDFs, DOCX Files, and Images

tokencalculator.dev Observed source

Editorial interest 85/100 Selection signal · not a rating of the site

TokenCalculator.dev counts text, document, code, data, and image tokens while comparing estimated API costs across OpenAI, Claude, Gemini, and DeepSeek.

Landing page captured for the 2026-08-25 issue.

Field notes

The calculator combines prompt text with locally extracted content from supported documents, then presents separate provider views for token counts, context fit, and input-cost estimates. Its methods distinguish exact OpenAI o200k_base BPE tokenization from provider-calibrated UTF-8 projections for other providers. Inputs can include text-based PDFs, DOCX files, code, structured data, and common image formats, with a stated 12 MB per-file limit; scanned PDFs are rejected without OCR.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

○OpenPublic substance visible

✦PrettyNotable craft visible

●ProPolished or operationally mature

◎NicheUnusually specific use

One card from the complete issue

Thirty-One Wells, Not Four

295,249 arrived 1,000 judged 1000 catalogued Enter the complete issue