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

[adchurch]

We built a model router that plugs into coding agents (e.g. Claude Code, Codex, Cursor, etc.) and intelligently sends requests to the best model to serve them. Here's a quick demo of running it locally: https://www.youtube.com/watch?v=isKhAyivtfM.

At Weave, we write ~all our code with AI, and it's been getting more expensive. This came to a head when Opus 4.7 was released and, thanks to its tokenizer changes, our costs shot up. We knew we didn't need Opus for everything but we didn't want to lose out on the intelligence for the cases where you really need it. So we decided to build a model router to handle this for us.

The Weave Router acts as an Anthropic/OpenAI endpoint specifically for coding agents. It looks at every inference request and intelligently (more on that in a sec) decides what model to send it to, handling all the translations required along the way. So it can use faster/cheaper models (e.g. DeepSeek v4, GLM 5.2, Kimi K2.6) when possible, and frontier models (Opus 4.8 & GPT 5.5 (& Fable whenever it's back)) when necessary.

How do we know what model to route to? We trained an RL model on tens of thousands (so far!) of agent traces. We reward the routing model when it selects an LLM that successfully completes the given task.

Here's an example: if you ask the router to plan a complex change, it will (probably) route that request to Opus 4.8. Subagents exploring the codebase to gather context will be routed to more suitable models (e.g. DeepSeek V4 Flash). Then when you have the plan ready to implement, it will be (most likely) be handed to a quicker model (e.g. GLM 5.2) to carry it out.

We've been using this internally for the last month or so. We've saved 40% on tokens vs. what we otherwise would have paid, with no noticeable differences in quality or velocity.

The router is source-available under Elastic License 2.0, so you can self-host it. Or if you prefer, you can also use our hosted version: weaverouter.com.

I'll be here to answer any questions you may have!

[g00k]

Man, I'm not so sure if I'd use something like this because the way I prompt already changes based upon what model I am using. I'm not convinced it would route to the right model based on my diction or whatever.

[adchurch]

Yeah that's a really interesting point, tbh I think the more relevant variable here is the harness you're using rather than the specific model? i.e. GPT 5.5 in the Claude harness behaves a lot more like Claude than Codex if that makes sense.

Hard to quantify this ofc but that's what I've felt vibes wise from using this for the last month.

[alansaber]

Yep this was always the reason to avoid "auto" mode in cursor.

[stpedgwdgfhgdd]

The thing I do not get with these routers is that you will have more cache misses (5min ttl). And if there is one thing i’ve learned; using the cache is crucial.

How does this router translate to $$$ when developing?

[adchurch]

You're right and that's why we built the router to be cache aware! Once it starts using one model, the threshold to switch to another model will be higher because the additional cost of the cache miss needs to be worth the cost savings or quality increase.

This is the key thing that other routers we've seen miss: they're stateless so for a coding agent use case you end up spending more money due to all the cache misses.

[alansaber]

That is interesting, sounds like in practice you only end up routing between 2 models

[adchurch]

I'd say that a typical main agent loop has 1-3 models (obviously very situationally dependent), but when you have subagents those can get routed independently since they have a fresh context window, so there are a lot more degrees of freedom there.

[k9294]

What about request caching? If you swap to a cheaper model mid execution it might cost more that to make multiple requests to the already cached provider?

[adchurch]

Yep 100%, mentioned this in another thread (https://news.ycombinator.com/item?id=48689448) but tl;dr we build the router to be cache aware

[spqw]

This + making sure common requests are saved as reusable skills and scripts would probably save a large part of my token usage

As prices increase we will see more of these tools to optimise and make the best use of token budget

[adchurch]

100%, from what we've seen, for a lot of big companies that 1. don't have subsidized usage and 2. are pushing AI adoption hard, figuring out token costs is P0 or P1 for their eng leadership

[suyash]

I would rather just use OpenCode - leverage AI models, even can host locally or paid ones with ease.

[adchurch]

We integrate with OpenCode too! OpenCode provides the harness, then the router selects the right model for the task.

We haven't yet set up local model routing though, that's really interesting - have you had any success using local models for coding tasks? Tbh I haven't heard many success stories from using local models yet

[gautam_io]

This is cool!

Will this use my Claude Pro/Max subscription? Or will it always use the API billing "pay as you go"?

[adchurch]

Yep it uses the Claude sub if possible and falls back to API billing only if you don't have a Claude sub or it's out of usage! Same deal for Codex

[alansaber]

"We reward the routing model when it selects an LLM that achieves the task successfully" sounds pretty oversimplified

[adchurch]

Indeed it is :) I skipped over talking about all the RL machinery, network design, reward function design, state representations, etc. because really the intuition is that we tell the model when it accomplishes its goal, and then it learns over time how to get better at making the right decisions in order to accomplish its goal.

Happy to talk about this in some more depth if there's anything specific you're curious about!

[debarshri]

It is funny. We are building something similar.

[adchurch]

Oh cool, feel free to reach out to me at [e-mail] if you ever want to share notes! We've learned a lot in the process of building this so far :)

[_pdp_]

Cool.. but I still don't get how this is going to save money. It seems to me that it might actually burn more money just because the whole system now seems to be coming from different LLMs.

Also, small LLMs are prone to stop before completion, throw errors and produce loops. Is this factored in the design of the tool? I am not sure.

edit: spellcheck

[adchurch]

It saves money because some agent sessions can be entirely handled by a smaller model (also relevant: subagents use fresh context windows so a subagent with a simple task can be routed to a smaller model even if the main agent needs a frontier model).

Totally right about small LLMs btw, that's why we trained this on real agent sessions where we forced it to use different models. If the routing model sees small models can't handle a certain type of task then they won't be assigned. (Also as a fallback we have some guardrails that will have a bigger model come in to "rescue" a smaller model if it gets stuck)

[slopinthebag]

> At Weave, we write ~all our code with AI

This is probably not a very effective way of marketing imo. At least, it turns me completely off.

[emilio_srg2]

but this means you work with API pricing rather than subscription pricing. Isn’t it better to use claude or codex CLI etc directly in terms of cost?

[adchurch]

If you have a Claude/Codex subscription then we use that (and account for the subsidized price accordingly when making routing decisions) instead of API billing. So you get the best of both worlds: subsidized usage for frontier models + save by using open/smaller models when it's genuinely better.

In practice, lots of ppl are using this to make their Claude sub limits go further!

[emilio_srg2]

I see but didn’t they severely limited the usage allowed with `claude -p`

[adchurch]

But we're not routing via `claude -p`, if you have sub usage available + it's the right choice to route to a Claude model, then the router is approximately a transparent passthrough. So it gets billed like normal `claude` usage rather than `claude -p`.

[arendtio]

What is the difference from Cursors 'auto' mode?

[adchurch]

Fun fact: Cursor's "auto" mode is just Composer (or at least it was last time I checked). So it's different in the sense that it actually does route to more than 1 model

[ai_slop_hater]

Isn't this more expensive than always using the same model, since, as I understand, by routing to different models you give up on cache?

[adchurch]

If you statelessly route each new request: yes it does end up being more expensive!

So our routing is cache-aware. It will have a much higher threshold to switch from one model to another if there's already some cache for the first model. Experimentally this solves the problem (like I said we've saved 40% ourselves vs. what we would have otherwise paid).