Show HN: Smart model routing directly in Claude, Codex and Cursor

Post by elgertam » Sun, Jun 28, 2026, 12:31 AM UTC

thombles wrote: post #102

elgertam wrote: post #101

I ran into a problem at work recently: we are given access to a bunch of models up to a full Claude Opus 4.8, but a monthly budget of 100k tokens. We are also given access to Gemini 3.5 Flash & 3.1 Pro with a daily budget of 50M tokens, but no tool calling. I'd love to hook Claude Code (or Pi) into the Gemini model, but the lack of tool-calling makes it quite difficult. I've been planning out how an intelligent route…

I’m curious how a workplace ends up with a model policy like this. It seems like you’d spend more time trying to work out how to use a tiny number of Opus tokens than doing it yourself.

Post by nawi » Sun, Jun 28, 2026, 12:02 PM UTC

Post by adchurch » Mon, Jun 29, 2026, 1:46 PM UTC

virangjhaveri wrote: post #124

Do you reward the RL model based on the token consumption when multiple LLMs complete the task ?

Post by jarodrh » Thu, Jul 02, 2026, 2:14 AM UTC

adchurch wrote: post #79

jmalicki wrote: post #60

> with no noticeable differences in quality or velocity. Have you done any A/B tests on this with evidence? (That's one thing I'd be very interested to see for claims like this - I'm not necessarily doubting you, it just seems like it could be useful to understand claims of quality/efficiency)

Great question! Our main product quantifies engineering productivity & quality so I think we're uniquely qualified to answer this - our velocity has only gone up and our quality (bugs introduced, code turnover) has not budged per our own analysis.