Loading video...

Video Failed to Load

Go Home

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 views • 1 month ago •via X (Twitter)

27 Comments

Adam Cohen's profile picture
Adam Cohen1 month ago

How we stack up

Adam Cohen's profile picture
Adam Cohen1 month ago

How it works

Adam Cohen's profile picture
Adam Cohen1 month ago

Get started:

Dalton Caldwell's profile picture
Dalton Caldwell1 month ago

👀

Landseer Enga's profile picture
Landseer Enga1 month ago

Baller

steven's profile picture
steven1 month ago

🤩🤩🤩

Josh's profile picture
Josh1 month ago

Heat

Layton Gott's profile picture
Layton Gott1 month ago

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

Brennan Lupyrypa's profile picture
Brennan Lupyrypa1 month ago

life saver

Yash Tike's profile picture
Yash Tike1 month ago

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's profile picture
Adam Cohen1 month ago

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's profile picture
Aïssa Nassiri1 month ago

C'est une offre incroyable pour le prix.

Samuel Hu's profile picture
Samuel Hu1 month ago

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's profile picture
Adam Cohen1 month ago

Capped unless you add credits

Junaid Ackroyd's profile picture
Junaid Ackroyd1 month ago

The best coding agent on the market

catman's profile picture
catman1 month ago

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

Antoni's profile picture
Antoni1 month ago

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's profile picture
Kamal Bisht 🔴 AI Marketer1 month ago

$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's profile picture
Adam Cohen1 month ago

Give it a test. Think you’ll be impressed

Kamal Bisht 🔴 AI Marketer's profile picture
Kamal Bisht 🔴 AI Marketer1 month ago

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's profile picture
安叫兽|Bird🕊️ 🔶 BNB1 month ago

长任务跑下来稳不稳啊?

swork1's profile picture
swork11 month ago

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's profile picture
Cupsey1 month ago

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

Sam Sung's profile picture
Sam Sung1 month ago

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

Adam Cohen's profile picture
Adam Cohen1 month ago

@daltonc All hosted in US

Sam Sung's profile picture
Sam Sung1 month ago

@daltonc awesome thanks!

Yash's profile picture
Yash1 month ago

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

Related Videos