Basically I have a use-case where I am building an llm-based tutor where some questions you ask the tutor can be adequately answered by gpt-4o-mini but others required gpt-4o. I'm looking for a router that can route to gpt-4o only when necessary and otherwise route to the cheaper gpt-4o-mini. First of all, is this even something that can be done reliably at this point? If so, are there any recommendations for LLM routers that can do this?
I would check out if Not Diamond (no personal affiliation) [0] fits your use case. They had a really interesting blog post recently where they open sourced their older model router [1].<p>[0] <a href="https://www.notdiamond.ai/features" rel="nofollow">https://www.notdiamond.ai/features</a><p>[1] Blog - Routing on Random Forests - <a href="https://www.notdiamond.ai/blog/rorf" rel="nofollow">https://www.notdiamond.ai/blog/rorf</a>