The recently released Token-Oriented Object Notation (TOON) aims to be a schema-aware alternative to JSON that significantly reduces token consumption at a similar level of accuracy. While the existence and importance of token saved depend on the data shape. some benchmarks show TOON may use in some cases 40% fewer tokens than JSON, possibly resulting in LLM and inference cost savings.<\/b>
\nThe recently released Token-Oriented Object Notation (TOON) aims to be a schema-aware alternative to JSON that significantly reduces token consumption at a similar level of accuracy. While the existence and quantity of saved tokens depend on the data shape, some benchmarks show that TOON may use 40% fewer tokens in some cases than JSON, potentially resulting in LLM and inference cost savings.
TOON self-describes as a compact, human-readable encoding of the JSON data model for LLM prompts.
Consider the following JSON: { «context»: { «task»: «Our favorite hikes together», «location»: «Boulder», «season»: «spring_2025» }, «friends»: [«ana», «luis», «sam»], «hikes»: [ { «id»: 1, «name»: «Blue Lake Trail», «distanceKm»: 7.5, «elevationGain»: 320, «companion»: «ana», «wasSunny»: true }, { «id»: 2, «name»: «Ridge Overlook», «distanceKm»: 9.2, «elevationGain»: 540, «companion»: «luis», «wasSunny»: false }, { «id»: 3, «name»: «Wildflower Loop», «distanceKm»: 5.1, «elevationGain»: 180, «companion»: «sam», «wasSunny»: true } ] }
In the TOON format, the same data becomes: context:
task: Our favorite hikes together
location: Boulder
season: spring_2025
friends[3]: ana,luis,sam
hikes[3]{id,name,distanceKm,elevationGain,companion,wasSunny}:
1,Blue Lake Trail,7.5,320,ana,true
2,Ridge Overlook,9.2,540,luis,false
3,Wildflower Loop,5.1,180,sam,true
Running this example in an online playground will show a 55% reduction in tokens vs. pretty-printed JSON, 25% vs. compact JSON, and 38% vs. YAML.<\/p>\n

As the previous example showcases, TOON combines YAML (for nested objects) and CSV (for uniform arrays) layouts to save tokens. However, for non-uniform data, JSON may be more efficient. For deeply nested objects, YAML may be more token-efficient. For flat datasets, CSV remains the most compact format. TOON adds a small overhead (~5%) with field headers and array declarations, in order to improve LLM accuracy.
Johann Schopplich explained on X:
\u201cDoes token efficiency hurt accuracy?\u201d
No \ud83d\ude42 TOON hits 99.4% accuracy on GPT 5 Nano while using 46% fewer tokens.
Tested across ~160 questions and 3 LLMs with semantic validation.
I think explicit lengths + field lists = fewer mistakes.
Readers may review TOON\u2019s specifications, documentation, online playgrounds, and run their own efficiency and accuracy benchmarks. In latency-critical applications, developers should compare Time To First Token and tokens per second in both formats.
The reference implementation in TypeScript\/JavaScript is maintained at github.com\/toon-format\/toon. The reference implementation includes a complete encoder and decoder, CLI tools for JSON-to-TOON conversion, and performance benchmarks. TOON 1.0 was released under the MIT license two weeks ago.<\/p>\n