For sure that’s absolutely true because you’re switching context from a kV cache to another one. We introduced 2 algorythms for solving this :
1) sticky : switches model only when convenient
2) smartsqueeze : fast advanced compression for reingesting context
Brick is a cheap & smart spatial router that plugged into claude code redirects the query to the best model in your pool. You can use it to save tokens, use other providers in claude code without changing models by hand or making your plans way longer in code time
We have a new update for brick : with feedbacks from users we inserted context caching aware routing. so that savings are improved even if switching models transfers context from one kv cache to another. we introduced a tier1 compaction algorythm that makes the router cheaper while mantaining performances. Try it out with brick claude settings > cache aware routing > smartsqueeze