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.
Coding agents send every request to one model. A one-line config change and a cross-service migration both go to the same frontier model at the same price. Teams are paying frontier rates for routine work, and the bill grows with every agent they add.
Most tools in this space follow one of two flawed approaches:
❌ Gateways – They give you one endpoint and a menu of models. You still pick the model yourself, so nothing actually gets cheaper.
❌ Manual model switching – Flipping /model mid-session breaks your prompt cache, and on long sessions the re-billed context eats the savings.
After running into this on our own agent traffic, we built Weave Router to solve it.
How Weave Router 2.0 is Different 🚀
Weave Router plugs into Claude Code, Codex, and Cursor as a drop-in endpoint. It reads every request your agent makes, scores how hard it is, and sends it to the cheapest model that will get it right.
The benchmarks
We ran 2.0 head to head against GPT-6 Astra, each task run twice (pass@2).
📊 Terminal-Bench 4.0 – Tied pass rate within the confidence interval. 52% of Astra's cost. 2.2x faster.
📊 SWE-Atlas Codebase QnA – Tied pass rate within the confidence interval. 46% of Astra's cost. 2.5x faster.
🔹 Complexity-scored routing – A new classifier trained on 10x more real agentic coding sessions routes on task difficulty, not task type. DeepSeek, GLM, and Kimi handle the simple turns. Astra and Fable handle the hard ones.
🔹 Cache-aware switching – 2.0 tracks cache state per provider and per session. It only switches models when the expected savings beat the cost of rebuilding the cache. This is where most of the cost win comes from.
🔹 Multi-subscription routing – Use Claude models inside Codex and GPT models inside Claude Code. Route by complexity, by cost, or by whichever plan still has quota this month.
Who is this for?
If you or your team run coding agents daily, Weave Router gets you Astra-level results at about half the cost and more than twice the speed, without changing your tools.
🔗 Get started today
Try it at weaveos.com/router. Install with one command: npx @workweave/router. Source-available under Elastic License 2.0. Teams of 50+ engineers can book time with our FDEs.
Congrats on the launch! This looks really useful. My Question: Is there a free tier to try it out first?
Congrats on the launch! 🙌 🙌 was literally just weighting a local model to cut agent costs, and this is the smarter take.
quick question - when it routes down and gets it wrong, does it catch it med-task and bump back up, or do i only find out after a cheaper model quietly shipped a worse answer? and, is the routing personalized at all, does it learn from my own history or feedback over time, or is it one global classifier for everyone?
neat idea either way 😃
The cache-aware switching is the detail that makes this feel practical, since a cheaper model is not really cheaper if every switch rebuilds a large context. I also like that the model pool stays configurable.
The cheapest model that can get it right approach is really interesting How does Weave decide which model is best for each coding task?
Very awesome guys - especially now that the 20x plan in codex is temporarily disabled 😵😵😵
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?
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 is a very great product, they way it reduced the token cost. quick question does weave select all the models for coding or its depend on there models?
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!
using weave is a quite great experience for me and my team, it save a lot of our time. my support is with you best of luck with the launch.
congrats on the launch,its a great product. my question to Weave Router team is, what is the most unique feature of your product have that make it different from others products.
Love this. Once you're running more than one coding agent, subscription-aware routing stops being a nice-to-have. Excited to try how you balance quality and cost across models.
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 🚀✌️
using weave allowed our lead engineers to optimize overall workflow speed by sixteen percent.
I have been using Weave and the experience has been great, especially because it significantly reduces token costs.
About Weave Router 2.0 on Product Hunt
“Subscription aware coding agent router”
Weave Router 2.0 launched on Product Hunt on September 16th, 2026 and earned 337 upvotes and 45 comments, earning #1 Product of the Day. 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.
Weave Router 2.0 was featured in Open Source (68.8k followers), Developer Tools (519.6k followers) and Artificial Intelligence (478.9k followers) on Product Hunt. Together, these topics include over 221.9k products, making this a competitive space to launch in.
Who hunted Weave Router 2.0?
Weave Router 2.0 was hunted by Ben Lang. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Weave Router 2.0 stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Ben Lang
Hey Product Hunt, I'm Adam, Co-founder of Weave!
The Problem
Coding agents send every request to one model. A one-line config change and a cross-service migration both go to the same frontier model at the same price. Teams are paying frontier rates for routine work, and the bill grows with every agent they add.
Most tools in this space follow one of two flawed approaches:
❌ Gateways – They give you one endpoint and a menu of models. You still pick the model yourself, so nothing actually gets cheaper.
❌ Manual model switching – Flipping /model mid-session breaks your prompt cache, and on long sessions the re-billed context eats the savings.
After running into this on our own agent traffic, we built Weave Router to solve it.
How Weave Router 2.0 is Different 🚀
Weave Router plugs into Claude Code, Codex, and Cursor as a drop-in endpoint. It reads every request your agent makes, scores how hard it is, and sends it to the cheapest model that will get it right.
The benchmarks
We ran 2.0 head to head against GPT-6 Astra, each task run twice (pass@2).
📊 Terminal-Bench 4.0 – Tied pass rate within the confidence interval. 52% of Astra's cost. 2.2x faster.
📊 SWE-Atlas Codebase QnA – Tied pass rate within the confidence interval. 46% of Astra's cost. 2.5x faster.
Full results at weaveos.com/router.
🔹 Complexity-scored routing – A new classifier trained on 10x more real agentic coding sessions routes on task difficulty, not task type. DeepSeek, GLM, and Kimi handle the simple turns. Astra and Fable handle the hard ones.
🔹 Cache-aware switching – 2.0 tracks cache state per provider and per session. It only switches models when the expected savings beat the cost of rebuilding the cache. This is where most of the cost win comes from.
🔹 Multi-subscription routing – Use Claude models inside Codex and GPT models inside Claude Code. Route by complexity, by cost, or by whichever plan still has quota this month.
Who is this for?
If you or your team run coding agents daily, Weave Router gets you Astra-level results at about half the cost and more than twice the speed, without changing your tools.
🔗 Get started today
Try it at weaveos.com/router. Install with one command: npx @workweave/router. Source-available under Elastic License 2.0. Teams of 50+ engineers can book time with our FDEs.