Launch HN: Tokenless (YC S26) – Automatic model switching to save money

A new startup called Tokenless, revealed on Hacker News, is tackling the soaring cost of AI tokens by routing requests between different models based on what each task needs. The service claims to match the performance of Claude Fable Five at half the cost. The founding team—Rohit, Andrew, and Kev—developed a routing algorithm that queries multiple models simultaneously and uses their responses to decide which one to use for each turn. Companies like Uber and Salesforce have already warned about burning through their AI budgets faster than expected; Tokenless aims to let developers tap frontier-level intelligence without the frontier-level bill.

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton