Aurimas Griciลซnas@Aurimas_Gr
TOON (Token-Oriented Object Notation) is out for some days now and it aims to make communication with LLMs more accurate and token-efficient.
The TOON topic is now one of the hottest news on the LLM market and it might actually matter.
๐ช๐ต๐ ๐ ๐๐ต๐ถ๐ป๐ธ ๐๐ผ:
I was initially hesitant to cover this, potentially being another hype to quickly fade, but:
โ
The format has been shown to increase the accuracy of models while decreasing the token count. I was not sure if there were any accuracy retention studies made, it seems there were.
โ
Token efficiency is extremely important when working with Agentic Systems that require a lot of structured context inside of their reasoning chains. And we are moving towards a post-PoC world where there is a lot of emphasis placed on optimisation of the workflows.
๐ ๐๐ต๐ผ๐ฟ๐ ๐๐๐บ๐บ๐ฎ๐ฟ๐:
- Token-efficient: typically 30-60% fewer tokens on large uniform arrays vs formatted JSON.
- LLM-friendly guardrails: explicit lengths and fields enable validation.
- Minimal syntax: removes redundant punctuation (braces, brackets, most quotes).
- Indentation-based structure: like YAML, uses whitespace instead of braces.
- Tabular arrays: declare keys once, stream data as rows.
An example:
๐๐๐๐ ๐ง๐ฐ๐ณ๐ฎ๐ข๐ต:
"shopping_cart": [
{ "id": "GDKVEG984", "name": "iPhone 15 Pro Max", "quantity": 2, "price": 1499.99, "category": "Electronics" },
{ "id": "GDKVEG985", "name": "Samsung Galaxy S24 Ultra", "quantity": 1, "price": 1299.99, "category": "Electronics" },
{ "id": "GDKVEG986", "name": "Apple Watch Series 9", "quantity": 1, "price": 199.99, "category": "Electronics" },
{ "id": "GDKVEG987", "name": "MacBook Pro 16-inch", "quantity": 1, "price": 2499.99, "category": "Electronics" }
]
}
๐๐ฉ๐ฆ๐ฏ ๐ฆ๐ฏ๐ค๐ฐ๐ฅ๐ฆ๐ฅ ๐ช๐ฏ๐ต๐ฐ ๐๐๐๐ ๐ง๐ฐ๐ณ๐ฎ๐ข๐ต:
shopping_cart: items[4]{id,name,quantity,price,category}:
GDKVEG984,iPhone 15 Pro Max,2,1499.99,Electronics
GDKVEG985,Samsung Galaxy S24 Ultra,1,1299.99,Electronics
GDKVEG986,Apple Watch Series 9,1,199.99,Electronics
GDKVEG987,MacBook Pro 16-inch,1,2499.99,Electronics
๐ฅ๐ฒ๐๐๐น๐:
โ
43% savings in token amount.
โ
Directly translates to 43% savings in token cost for this LLM input.
โ๏ธ Be sure to know when NOT to use the format (and always test it for your application specifically):
- Deeply nested or non-uniform structures.
- Semi-uniform arrays.
- Pure tabular data.
โน๏ธ I will be testing it in the upcoming weeks.
Let me know if you have already tested TOON and what are your takeaways! ๐
#LLM #AI #MachineLearning
