Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Introducing Weave Code Max: We have hyper-optimized routing and inference so you can get $50+ in usage for just $10/month. You can use our tuned open-source models in Codex, OpenCode, Pi, or Claude Code. The most coding $10 can buy.

13,129 görüntüleme • 1 ay önce •via X (Twitter)

27 Yorum

Adam Cohen profil fotoğrafı
Adam Cohen1 ay önce

How we stack up

Adam Cohen profil fotoğrafı
Adam Cohen1 ay önce

How it works

Adam Cohen profil fotoğrafı
Adam Cohen1 ay önce

Get started:

Dalton Caldwell profil fotoğrafı
Dalton Caldwell1 ay önce

👀

Landseer Enga profil fotoğrafı
Landseer Enga1 ay önce

Baller

steven profil fotoğrafı
steven1 ay önce

🤩🤩🤩

Josh profil fotoğrafı
Josh1 ay önce

Heat

Layton Gott profil fotoğrafı
Layton Gott1 ay önce

Looks very intriguing! I want to know more about how this works. Can I read about it somewhere? Doc?

Brennan Lupyrypa profil fotoğrafı
Brennan Lupyrypa1 ay önce

life saver

Yash Tike profil fotoğrafı
Yash Tike1 ay önce

I'm interested to try this out, but could you elaborate more on "every prompt going to the cheapest model that can handle it"? I am currently an opencode Go user but I do like to pick my own models, interested in knowing more about your offerings

Adam Cohen profil fotoğrafı
Adam Cohen1 ay önce

Our early users prefer the router to pick the right model as it's been exhausting keeping up with every new release and burning tokens testing what each model is good/bad at. Give it a shot and lmk your thoughts.

Aïssa Nassiri profil fotoğrafı
Aïssa Nassiri1 ay önce

C'est une offre incroyable pour le prix.

Samuel Hu profil fotoğrafı
Samuel Hu1 ay önce

nah, only if the spend stays capped. i hit the same “cheap” route, the retry loop burned the budget, and i rolled back to the old model.

Adam Cohen profil fotoğrafı
Adam Cohen1 ay önce

Capped unless you add credits

Junaid Ackroyd profil fotoğrafı
Junaid Ackroyd1 ay önce

The best coding agent on the market

catman profil fotoğrafı
catman1 ay önce

By routing each request to tuned open-source models and optimizing inference, Weave aims to stretch a fixed subscription budget further.

Antoni profil fotoğrafı
Antoni1 ay önce

We did shut downsizing dev (doubling the subscription) because - providers fight routers, for example, Claude signs commands with its private keys, so you can’t effectively route between providers back and forth - Quality and stability matter much more than cost savings to the customers we’ve spoken to - When you route, you break the cache, which makes it financially unfeasible in many cases But maybe you guys will find a way through! @daltonc

Kamal Bisht 🔴 AI Marketer profil fotoğrafı
Kamal Bisht 🔴 AI Marketer1 ay önce

$50 in usage for $10 is wild if the models actually hold up under real workloads. The tuned open-source angle is smart, but I'd trust it more once I see how the smaller models handle edge-case bugs.

Adam Cohen profil fotoğrafı
Adam Cohen1 ay önce

Give it a test. Think you’ll be impressed

Kamal Bisht 🔴 AI Marketer profil fotoğrafı
Kamal Bisht 🔴 AI Marketer1 ay önce

Will do. Curious if the smaller models handle complex refactoring or just simple completions, that's where most tuned models fall apart.

安叫兽|Bird🕊️ 🔶 BNB profil fotoğrafı
安叫兽|Bird🕊️ 🔶 BNB1 ay önce

长任务跑下来稳不稳啊?

swork1 profil fotoğrafı
swork11 ay önce

ok but can i say when to use lesser models somehow? For example there are use cases (that it might not understand) that can be easily done by smaller/cheaper models

Cupsey profil fotoğrafı
Cupsey1 ay önce

the $10 price point is kind of absurd for that much coding headroom

Sam Sung profil fotoğrafı
Sam Sung1 ay önce

@daltonc Where are the open source models hosted? US?

Adam Cohen profil fotoğrafı
Adam Cohen1 ay önce

@daltonc All hosted in US

Sam Sung profil fotoğrafı
Sam Sung1 ay önce

@daltonc awesome thanks!

Yash profil fotoğrafı
Yash1 ay önce

So wait, we don't know which models are being served under the hood, or even which ones are a part of the underlying stack? Even the docs page seems to be missing. Will the analytics give an idea here? No offence but this seems to be having a lot of trust me bro energy

Benzer Videolar