I think what the parent is saying is that the model itself has the best context for whether a portion of a request should be routed. The specifics of that routing (e.g., should you route to KimiK2) are something that can be trained, finetuned, or even included in a model's startup context.
This doesn't seem quite right. For one, I don't need all the intelligence of an expensive model like Opus 5 to do the relatively simple task of choosing a correct model for a task. Additionally, since this isn't something Anthropic would ever put effort into doing well, you could tune a model to do better and faster than Opus 5 does out of the box.
My experience is the opposite - for many cases it’s not very obvious how good a model needs to be to solve it. Worse models tend to just follow their first instincts without proper reasoning
And also btw you don’t need a
routing company to decide, you can do it on your harness. And yeah my Fable has zero issues delegating to Terra instead of Opus.
Are you thinking of single shot? For agentic use cases, your ability to manage cache and context becomes much more important. Price per individual request becomes less about tokens and more about cache.
Sure Claude would comply, but Anthropic has no financial (or other) incentive to optimize this, so there’s no reason to expect it to be particularly good.
It would be like asking the clerk at a Whole Foods which grocery store in the city sells the cheapest eggs. He’d probably answer - he might not even say Whole Foods - but WF is hardly teaching all their staff the best methods to answer this question in training. (Heh, training.)
Yes. I have Claude route to codex all the time as part of a dev process where fable is manager and it oversees the work of sidekicks and subagents. It’s happy to comply.
Which is why 3rd party routers which do route between different models may have an edge. It means they can compete on cost, and it’s definitely not clear that the architectural optimization is always going to be higher quality or cheaper. It might be, but everything changes constantly, so locking into a single model family/company is very much not ideal
The only metric that matters is f(cost, time, task). If Anthropic has a SOTA model, it can easily distill every model in the pareto frontier and have the SOTA model route appropriately. They haven't felt the 'sting' yet to optimize that (still growing their ARR at a crazy growth rate)
Ant can top any benchmark that measures f(cost, time, task). The only entities that can beat them in costs are infrastructure providers who can do optimization at that layer. But a pure Model company can *never* compete with Anthropic on f(cost, time, task) if they continue to have SOTA models
Imo the main issue behind model routing is you need to figure out how much intelligence a new task takes, which is a very non trivial problem. Presumably, a organization knows this about their own tasks and is better suited to built in-house compared to outsourcing to a vendor.
> Model Routing will always be done better by models themselves.
> The models themselves will get better at this and frontier companies will simply give that capability
I would never trust something like model routing to the same company that would profit from it, and that goes for telling models doing their own routing when that could easily be trained into the model to make things more expensive. Sort of a conflict of interest.
Models are first and foremost trained by corporations.
Model routing by the model itself requires the model to pull in a lot of context and it's likely more efficiently just done by people with the context already in their head, even assuming the model is perfect at routing (which last I checked, Claude definitely isn't). I wouldn't trust ML model routers.
Model Routing is just Bitter lesson. The models themselves will get better at this and frontier companies will simply give that capability