ES version is available. Content is displayed in original English for accuracy.
At Weave, we write most of 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!
Discussion (53 Comments)Read Original on HackerNews
It looks like much more context is required to decide on the best model (e.g., summarizing logs might use a cheap model, whereas you likely want Opus/Mythos/GPT 5.6 to debug multithreading logic). In an agentic system, a decision about the model may be embedded in the decision to orchestrate the model.
But intuitively I think it makes sense that a model can learn what model to route things to if it has all the relevant info, and experimentally it works pretty well in our experience
Based on what OP said elsewhere in the discussion "threshold to switch to another model will be higher" means that essentially you reduce the workflow into two models at most. The two model primitive, one planner and one executor, is already sufficient for such a use case.
For lower than 2 models, it's just a simple single model cache-preserving conversation which arguably doesn't need another layer. For larger than 2 models, you are likely paying a large aggregate cache penalty that negates most of the gains
1. Small models can carry out a good number of requests e2e 2. Small model for part of a request + cache miss < big model for entire request in many cases 3. Subagents
For our own usage we've saved 40% so far (that is of course including costs of uncached requests when switching models)
For example, if my task was "refactor this component to decouple all messy nesting", the problem router can't possibly know what is being referred to. This works for clear cut and dry problems but not for ambiguous problems. Most of the real world problems carry a lot of ambiguity.
Hard to quantify this ofc but that's what I've felt vibes wise from using this for the last month.
How does this router translate to $$$ when developing?
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.
In practice you just pick one and stick with it until the API stops or you hit performance issues.
I'm just trying to figure out why on the fly routing would beat testing and tuning and locking models and versions for each class of call, with evals and auto tunes running to explore more possible models for commonly run classes of prompt over time . . .
Also i am pretty sure neither open ai or anthropic leets you seed the agents own tokens.
As prices increase we will see more of these tools to optimise and make the best use of token budget
Happy to talk about this in some more depth if there's anything specific you're curious about!
Will this use my Claude Pro/Max subscription? Or will it always use the API billing "pay as you go"?
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
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
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)
1. https://github.com/instavm/murmur - Murmur
Also the throughput kind of increases since providers are different.
In practice, lots of ppl are using this to make their Claude sub limits go further!
This is probably not a very effective way of marketing imo. At least, it turns me completely off.
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).
Do people voluntarily use these proxies/routers, knowing their prompts, outputs and code will be seen by other people ?
I get it might be ok for personal projects, but for anything that makes money and is a part of business... this must be big no-no ?
But of course since the source is available you can also run it locally or self host