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
- Connected steps are not a workflow: nobody designs the handoff — usehive · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16
- Running PolyStrata + Cline coding agent on a $0-fancy laptop at ~90 tok/s — rpwoerk · 2026-10-16
- How do you attribute agent gains: model training or infrastructure? — jrxna · 2026-10-16
- Feed Claude your books, blogs and top engineers' code for claude.md — 'it now writes better code than me' — blaizedsouza · 2026-10-16
- Open-source /label plugin auto-names and colors Claude Code sessions in one step — hermanschutte · 2026-10-16