A developer has introduced TOON, a new data format designed to significantly reduce token usage when sending JSON arrays to large language models like GPT and Claude. TOON achieves this by declaring keys only once and then listing values row by row, which can cut token counts by 30-60% for repetitive data. While not suitable for deeply nested or mixed-shape data, this format offers substantial cost savings and context window efficiency for users who frequently input large arrays of similar objects into LLMs. A free online converter and token estimator for TOON is also available. AI
IMPACT Reduces LLM operational costs and increases context window efficiency for users processing large JSON datasets.
RANK_REASON New data format for optimizing LLM prompt efficiency.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
