Weave Router 2.0 - Subscription aware coding agent router
by•
Use Claude models in Codex and GPT models in Claude Code on your existing plans, routed to whichever has quota left. Weave Router 2.0 routes each coding agent request to the cheapest model that can get it right. On Terminal-Bench 4.0 and SWE-Atlas it matches GPT-6 Astra at half the cost, 2x faster. Powered by a new classifier that scores task complexity and cache-aware switching that only moves when savings beat the rebuild cost.
Replies
I have used Weave for my team and it noticeably improved our engineering output.
Weave Engineering Intelligence
@joseph_collins2 love to hear it :)
Does it shows users why a specific model was chosen for each request?
Weave Engineering Intelligence
@ethanc44 we don't have this, but will def add it as a feature request!
I have been using Weave and the experience has been great, especially because it significantly reduces token costs.
Weave Engineering Intelligence
@thomas_jack3 amazing to year that :)
Weave Engineering Intelligence
Hello everyone! 🎉 I'm thrilled that we've launched Weave Router 2.0! 🚀 Many of you have seen us preparing for the launch, and we've done it! Today is a big day for us, as this launch is actually our first public product release.
We would greatly appreciate your feedback, comments, and reviews. 💬
Also, as a gift to all Product Hunt community members, we are offering a 20% discount on routing through the end of 2026!
Dumper cheaper models are known to produce longer trajectories when solving the same task. What are your thoughts on it in the context of smart routing and cost optimisation?
Weave Engineering Intelligence
@dmytriis Totally agree! We've run a lot of rollouts on production agent traces to measure how efficient each model actually is. On many tasks (usually complex ones, though not only those) dumber models spin their wheels and burn a ton of tokens, so we try to limit the scenarios where that happens. Artificial Analysis publishes a pretty great tokens-per-task score for every model. We try to go a bit deeper by delineating between task complexity and type as well.
Does it provide any visibility into how much quota each request saves?
Weave Engineering Intelligence
@alheri_murya yes! You can see it on every turn
Given that this routing is done via quota across the providers, what will happen if there is a case whereby the quotas for Claude and GPT are depleted at the same time?
Additionally, Congratualtions @adchurch @adambcohen & team @Weave Engineering Intelligence 🚀✌️
Weave Engineering Intelligence
@aymi_malik Hey Muhammad, great question. In this case we still try to route to the best model for the job, whether that be an open source model or one of the Anthropic/OpenAI models at API pricing.
Congrats on the launch. I'm interested to know that when a cheaper model gets a turn slightly wrong, does the router notice and escalate on the next turn, or does the agent carry the mistake forward?
Weave Engineering Intelligence
@joy_gu yes it does! it's aware that if it's running and not working as effectively as possible it will escalate it to a more intelligent model.
Very awesome guys - especially now that the 20x plan in codex is temporarily disabled 😵😵😵
Weave Engineering Intelligence
@ilyatkachov ahaha 100%
The cheapest model that can get it right approach is really interesting How does Weave decide which model is best for each coding task?
Weave Engineering Intelligence
@shivam_kushwaha16 We trained a model on an extremely large dataset that we gathered from customer agent traces as well as model rollouts and continuously improve via RLHF!