← All tools

Token Counter & Prompt Cost

Count pasted text with real BPE or manual tokens and compare three custom input rates.

token-costLOCAL WORKSPACE

Enabling local controls…

Your inputs and assumptions

Local only. No prompt in URLs, no AI requests, no saved form data. Rate and capacity defaults are custom examples; replace them with your verified quotes.

Results

Review the inputs, then run to create a readable result and complete export. Editing cancels active work and clears stale results.

Formula, sources and limits

Input cost = tokens × USD/1M input tokens ÷ 1M. Exact BPE count only for the selected encoding; no output, wrapper or cache charges. Manual count bypasses text. Rates, limits, subscriptions and latency defaults are illustrative custom assumptions, not current vendor quotes or benchmarks. Check official sources and replace them. Each text field ≤32,768 UTF-16 units, total input ≤128 KiB, output ≤1 MiB; local job timeout 30s.

Methodology checked:

gpt-tokenizer encodings and API

How to use this tool

Load the safe sample, review every labeled assumption, then run. Edit any field to clear old results. Copy or download the complete result. Processing stays in this tab.

When not to use it

Input cost = tokens × USD/1M input tokens ÷ 1M. Exact BPE count only for the selected encoding; no output, wrapper or cache charges. Manual count bypasses text. Rates, limits, subscriptions and latency defaults are illustrative custom assumptions, not current vendor quotes or benchmarks. Check official sources and replace them. Each text field ≤32,768 UTF-16 units, total input ≤128 KiB, output ≤1 MiB; local job timeout 30s.