Serving and cost

tokenmeter

Count tokens and estimate prompt cost before sending.

0 downloads/month on PyPI

Install

pip install tokenmeter-cli

If you use uv, also as an isolated CLI:

uv tool install tokenmeter-cli

What it does

Prompt templates grow, an example gets added, the retrieved context balloons, and suddenly every call costs more than you thought. tokenmeter gives the exact count and a dollar estimate up front.

In action

A real recorded session of the CLI running.

Read it as text

input       in tok  out tok  cost (USD)
prompt.txt      18        0   $0.000045

$ tokenmeter count prompt.txt --model gpt-4o
input       in tok  out tok  cost (USD)
prompt.txt      18        0   $0.000045

Features

—Exact counting with tiktoken for OpenAI encodings.
—Per-model cost estimate from a dated table.
—A file, a directory or stdin.
—Budget gate for CI.

View the code on GitHub →

Other tools

dsdiff

A git-style diff between two datasets, with distribution drift.

splitcheck

Detect rows leaking between train, validation and test splits.

pii-sweep

Scan datasets for PII before sharing them.