ZON-Format/zon-TS

ZON → 35-70% cheaper LLM prompts than JSON/TOON. Zero overhead.

38
/ 100
Emerging

This project helps anyone working with Large Language Models (LLMs) to reduce the cost of their prompts and improve data accuracy. It takes your existing structured data, like what you'd typically put in a JSON file, and converts it into a highly compact, human-readable format. The result is significantly cheaper LLM interactions and more reliable data retrieval for data scientists, AI engineers, and researchers.

Use this if you are frequently sending structured data to LLMs and want to cut down on token costs while ensuring the LLM accurately understands and processes your information.

Not ideal if your workflow doesn't involve LLMs or if you primarily work with unstructured text data where token efficiency for structured formats isn't a concern.

LLM-prompt-optimization AI-cost-reduction data-serialization prompt-engineering AI-data-fidelity
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 13 / 25
Community 7 / 25

How are scores calculated?

Stars

45

Forks

3

Language

TypeScript

License

MIT

Last pushed

Jan 22, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ZON-Format/zon-TS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Compare