Launch HN: Tokenless (YC S26) – Dynamic model routing to halve AI costs

rohaga · hn · 2026-07-29

Tokenless (YC S26) launched an AI API gateway that dynamically switches between models turn-by-turn to reduce inference costs.

Core Tech: Queries multiple models simultaneously and routes based on generation progress, without destroying the cache during switches.
Performance: Matches Claude 3.5 Sonnet performance at half the cost.
Background: Founded by a Princeton PhD student, the routing algorithm quickly hit SOTA during internal testing.
Roadmap: Integration with Kimi K3 and other upcoming models is planned.

More from coding & agent