‹ BackHN Continuity

Thread

Show HN: Open-source model routing for coding agents at Astra-level performance

119 points · 42 comments · adchurch

  1. capocasa · · focus · HN ↗
    That sounds really quite interesting- one question pops up, this sounds like it could produce a lot of non-cache input tokens. How much impact does this have, and are you mitigating it?

    Interested in adding support to my own 3code- <a href="https:&#x2F;&#x2F;3code.capocasa.dev-" rel="nofollow">https:&#x2F;&#x2F;3code.capocasa.dev- which aims to reduce cost by using more compact system prompts and a clever compaction variant.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.