# schopplich-toon-json-llm-token-optimization-2025-10-22

## Veille

TOON serialization format optimized for LLMs cutting token costs by 30-60% - GitHub - Johann Schopplich

## Titre Article

TOON - Token-Oriented Object Notation: JSON for LLMs at half the token cost

## Date

2025-10-22

## URL

https://github.com/johannschopplich/toon

## Keywords

TOON, LLM, token optimization, data serialization, JSON, YAML, CSV, TypeScript, LLM API, data compression, API cost, data format, LLM architecture

## Authors

Johann Schopplich (@johannschopplich)

## Ton

**Profile:** Developer-Innovation | First person creator | Technical-Pragmatic | Expert

Schopplich (independent developer) adopts a problem-solving voice presenting the TOON format in response to the practical challenges of LLM API costs. The GitHub project format emphasizes open source sharing. The optimization-centered language (30-60% token reduction, serialization, compression) demonstrates cost-conscious engineering. A pragmatic creator's tone offering a useful tool rather than an academic innovation. The clear problem → solution → benchmarks structure facilitates the adoption decision. Typical of open source projects by independent developers solving concrete problems, targeting cost-conscious practitioners seeking efficiency gains in their LLM workflows.

## Pense-betes

- TOON reduces token consumption by 30-60% compared to JSON, up to 65% in some cases
- Hybrid format merging YAML (hierarchical indentation) and CSV (tabular format)
- Retrieval accuracy: 86.6% (TOON) vs 83.2% (JSON) - better comprehension by LLMs
- Minimal syntax: no quotes, reduced braces, indentation for structure
- Metadata in array headers: `key[N]{field1,field2}:` for explicit validation
- Project created on October 22, 2025, last activity October 27, 2025
- Use cases: analytical exports, GitHub lists, nested e-commerce orders
- Substantial savings for organizations with massive volumes of LLM requests
- Readability superior to conventional binary compression
- Optimized alternative to JSON, YAML, CSV and XML for LLM context

## RésuméDe400mots

TOON is an innovative data serialization format designed specifically to optimize calls to large language models. Unlike JSON, which requires verbose syntax with repetitive quotes and braces, TOON drastically reduces token consumption—a directly billable resource in LLM interactions. The project demonstrates reductions of 30 to 60% in tokens compared to JSON, with some scenarios reaching up to 65% savings depending on the structured data.

The format's architecture merges concepts from YAML (indentation for hierarchy) with CSV (tabular format for uniform data). This hybrid approach proves particularly effective for repetitive structures—collections of identical objects where each record shares the same fields. The minimal syntax eliminates redundant delimiters, using only spaces to indicate nesting and commas for internal separations.

Technically, TOON encodes critical metadata in array headers: `key[N]{field1,field2}:` indicates N elements with specified fields. This explicit approach improves validation by LLMs and facilitates parsing of complex structures. Benchmarks reveal a data retrieval accuracy of 86.6% versus 83.2% for JSON, demonstrating that compactness does not sacrifice model comprehension.

Use cases range from analytical data exports to GitHub repository lists, including nested e-commerce orders. For organizations managing massive volumes of LLM requests, this optimization generates substantial savings on API costs, while developers benefit from syntax that is more readable than conventional binary compression.

The project, created on October 22, 2025 by Johann Schopplich, represents a pragmatic response to a concrete economic problem: every token consumed in an LLM interaction has a direct financial cost. By halving JSON's verbosity while maintaining—or even improving—model comprehension, TOON offers an immediate competitive advantage for AI-intensive applications.

The innovation lies in the balance between technical optimization and human readability. Unlike binary compression formats that become opaque, TOON remains interpretable, facilitating debugging and maintenance. This characteristic proves crucial in production environments where the transparency of data exchanged with LLMs becomes a governance and compliance concern.

## GrapheDeConnaissance

- Johann Schopplich —a_créé→ TOON (TECHNOLOGIE, 0.99)
- TOON —réduit→ consommation de jetons (CONCEPT, 0.99)
- TOON —améliore→ précision de récupération (CONCEPT, 0.95)
- TOON —est_basé_sur→ YAML (TECHNOLOGIE, 0.92)
- TOON —est_basé_sur→ CSV (TECHNOLOGIE, 0.92)
- TOON —remplace→ JSON (TECHNOLOGIE, 0.88)
- TOON —réduit→ coût API LLM (CONCEPT, 0.97)
- Johann Schopplich —publie→ toon-format/toon (TECHNOLOGIE, 0.99)
- toon-format/toon —utilise→ TypeScript (TECHNOLOGIE, 0.95)
- TOON —s_oppose_à→ compression binaire (CONCEPT, 0.85)
- organisations LLM —utilise→ TOON (TECHNOLOGIE, 0.87)
- TOON —améliore→ lisibilité humaine (CONCEPT, 0.88)

---
Canonical: https://www.thekb.eu/en/fiches/schopplich-toon-json-llm-token-optimization-2025-10-22/