TOONToken-Oriented Object Notation

A compact, human-readable encoding of the JSON data model for LLM prompts.

Token-Efficient & Accurate

TOON matches JSON's retrieval accuracy (72.2% vs 71.4%) while using 42.6% fewer tokens.

Encodes the same objects, arrays, and primitives as JSON with deterministic, lossless round-trips.

[N] declares how many rows, {fields} how wide – so truncated or malformed output can't slip through.

Uses indentation instead of braces and minimizes quoting, giving YAML-like readability with CSV-style compactness.

Uniform objects – in an array or under keys – declare the field list once, then stream one row each.

Official implementations, plus dozens of community ports, all targeting one spec with a shared conformance test suite.