Host A: Welcome back to Exploring Next! Today we're looking at New Token-Oriented Object Notation (TOON) Hopes to Cut LLM Costs by Reducing Token Consumption.
Host B: Yeah, this one caught our eye because InfoQ Homepage News New Token-Oriented Object Notation (TOON) Hopes to Cut LLM Costs by Reducing Token Consumption Development New Token-Oriented Object Notation (TOON) Hopes to Cut LLM Costs by Reducing Token Consumption Nov 23, 2025 2 min read by Bruno Couriol Write for InfoQ Feed your curiosity.
Host A: So the big idea is TOON adds a small overhead (~5%) with field headers and array declarations, in order to improve LLM accuracy.
Host B: What stood out to me is In latency-critical applications, developers should compare Time To First Token and tokens per second in both formats.
Host A: If you're curious, give the original a read: https://www.infoq.com/news/2025/11/toon-reduce-llm-cost-tokens/.
Host B: And let us know what you try next!