Tools/Converters

JSON to TOON Converter

Convert JSON to Token-Oriented Object Notation for 30-60% token reduction in LLM contexts.

LLM OptimizedToken EfficientHuman Readable

Auto-convert

Conversion Options

JSON Input

TOON Output

About TOON Format

Token-Oriented Object Notation (TOON) is a compact, human-readable format designed for passing structured data to Large Language Models with significantly reduced token usage.

TOON was created by Johann Schopplich on October 26, 2025, and announced on X (formerly Twitter) . The library is open-source and available on GitHub .

"Token-Oriented Object Notation is a compact, human-readable format designed for passing structured data to Large Language Models with significantly reduced token usage. It's intended for LLM input, not output. TOON's sweet spot is uniform complex objects – multiple fields per row, same structure across items."
— According to its GitHub description

Proven Performance

TOON has been benchmarked across multiple datasets and LLMs (GPT-5 Nano, Claude Haiku, Gemini 2.5 Flash, and Grok-4), demonstrating:

•Token Efficiency: 30-60% reduction vs JSON on uniform datasets
•Retrieval Accuracy: 70.1% average accuracy (vs JSON's 65.4%) while using 46.3% fewer tokens
•Best-case savings: Up to 58.9% token reduction on time-series analytics data

Key Benefits

✓30-60% fewer tokens than JSON
✓Human-readable structure
✓LLM-friendly guardrails
✓Minimal syntax overhead
✓Tabular format for uniform data

Best Use Cases

✓Large arrays of uniform objects
✓API responses for LLM context
✓Configuration data
✓Database exports
✓Structured prompts

Quick Reference

JSON	TOON	Description
`{ "id": 1, "name": "Ada" }`	`id: 1 name: Ada`	Simple object
`["foo", "bar"]`	`[2]: foo,bar`	Primitive array
`[{"id": 1}, {"id": 2}]`	`[2]{id}: 1 2`	Tabular array
`{ "user": { "id": 1 } }`	`user: id: 1`	Nested object

TOON uses indentation for nesting and declares array lengths and fields upfront for better LLM comprehension.

Syntax Cheatsheet

Object

{ id: 1, name: 'Ada' }

id: 1
name: Ada

Nested object

{ user: { id: 1 } }

user:
  id: 1

Primitive array (inline)

{ tags: ['foo', 'bar'] }

tags[2]: foo,bar

Tabular array (uniform objects)

{ items: [
  { id: 1, qty: 5 },
  { id: 2, qty: 3 }
]}

items[2]{id,qty}:
  1,5
  2,3