SandRise
Ep 50 Blog 0:54 w/ Justy & Cody

New Token Oriented Object Notation (TOON) Hopes to Cut LLM Costs by Reducing Token Consumption

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. Help 550k+ global senior developers each month stay ahead.

InferenceLaunchToonBlog
Read the source → Plain-text transcript →
Embed this episode

Paste this on any site — the player is a self-contained iframe with no cookies or trackers. 

<iframe src="https://sandrise.io/exploring-next/embed/50"
  width="100%" height="180" style="max-width:640px;border:0;border-radius:12px;overflow:hidden"
  title="Exploring Next — Episode 50 audio player"
  loading="lazy" allow="autoplay" referrerpolicy="strict-origin-when-cross-origin"></iframe>
Embed & API docs →
Voice OpenAI TTS

Transcript

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!