RouteLLM: A framework for serving and evaluating LLM routers

From what I understand, it's from people using it in their workflows - say, Claude but keep hitting the rate limits, so they have to wait until Claude says "you got 10 messages left until 9pm", so when they hit that, or before they switch to (maybe) ChatGPT manually.

With the router thingy, it keeps a record, so you know every query where you stand, and can switch to another model automatically instead of interrupting workflow?

I may be explaining this very badly, but I think that's one use-case for how these LLM Routers help.

Trained routers are provided out of the box, which we have shown to reduce costs by up to 85%

The answer is here. This is a cost-saving tool.

All companies and their moms want to be in the GenAI game but have strict budgets. Tools like this help to keep GenAI projects within budget.

For the company I work for, one of the most important aspects is ensuring we can fallback to different models in case of content filtering since they are not equally sensitive/restrict.

I think a lot of people are just interested in hitting the LLM without any bells or whistles, from Typescript. A low level connector lib would come in handy, yeah? https://github.com/monarchwadia/ragged

Yeah. I can't even consistently get JSON output out of all models. What are people doing that they don't care about output format?...

You may have a variety of model types/sizes, fine tunes, etc, that serve different purposes - optimizing for cost/speed/specificity of task. At least that's the general theory with routing. This one only seems to optimize for cost/quality.

I think unify.ai (like openrouter) does that - it has several paramters you can choose from.

But the underlying "how to choose a model that's smart enough but not too smart" seems difficult to understand.

Portkey does that with configuration. You assign a base model, then add more models with weight to load-balance.

actually ModelBox(model.box) offers that, the autorouter function can dynamically switch to different models according to latency, geo-position and costs.

Some of that is already possible, since it can generate a difficulty score for a prompt that could be manually mapped between models based on ranges.

The weak-to-strong assumption is that it is easier to eval the result of a task than to generate it. If it is wrong, human can not make a stronger intelligence than us.

Not true. You can easily train a BERT single class classification model without having to train an LLM.

not true at all, you could have a efficient cheap model which is generally terrible at most things but has a savant like capacity for categorizing tasks by requirement and difficulty. Even easier when you dont need to support multiple languages and a truly staggering breadth of domains, like a conventional llm does. You could train a really small model to reject out of domain requests and partition the rest, running at a fraction of the cost of a more capable model.

In this paper, they tried a couple different methods for determining how similar the incoming request is to requests that they have scored in their dataset. Actually, one of the best methods they used does not involve using a model at all to evaluate the incoming query (similarity-weighted ranking) although it _does_ use pre-trained embeddings.

Using this, they were able to produce quite good results applying this similarity measurement to unseen queries using a standard benchmark. The leap of faith here is assuming that the same query similarity method will continue to bear fruit when extended to queries that aren't benchmarkable.

You can distill evaluation ability

Cost is a plus but at least what I see is that getting good response time is even bigger. Something like OpenAI Azure instances are inconsistent and it is far too normal to get a 40sec lag with responses with gpt4-o.

Addendum to parent to make link clickable:

https://github.com/pulzeai-oss/knn-router

// HN doesn't handle squared circle as MD.

You're reading it right. They have developed a system that automatically decides which model is sufficient, depending on your inputs, saving you costs even within one conversation stream.

The OpenAI-compatible API allows you to talk to the router like a regular GPT model.

OpenRouter is also interesting solution but I almost end up using like one or two LLMs and I rarely feel the need to switch between different LLMs so I ask why I am even using openrouter in the first place.