Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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 Aufrufe • vor 1 Monat •via X (Twitter)

27 Kommentare

Profilbild von Adam Cohen
Adam Cohenvor 1 Monat

How we stack up

Profilbild von Adam Cohen
Adam Cohenvor 1 Monat

How it works

Profilbild von Adam Cohen
Adam Cohenvor 1 Monat

Get started:

Profilbild von Dalton Caldwell
Dalton Caldwellvor 1 Monat

👀

Profilbild von Landseer Enga
Landseer Engavor 1 Monat

Baller

Profilbild von steven
stevenvor 1 Monat

🤩🤩🤩

Profilbild von Josh
Joshvor 1 Monat

Heat

Profilbild von Layton Gott
Layton Gottvor 1 Monat

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

Profilbild von Brennan Lupyrypa
Brennan Lupyrypavor 1 Monat

life saver

Profilbild von Yash Tike
Yash Tikevor 1 Monat

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

Profilbild von Adam Cohen
Adam Cohenvor 1 Monat

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.

Profilbild von Aïssa Nassiri
Aïssa Nassirivor 1 Monat

C'est une offre incroyable pour le prix.

Profilbild von Samuel Hu
Samuel Huvor 1 Monat

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.

Profilbild von Adam Cohen
Adam Cohenvor 1 Monat

Capped unless you add credits

Profilbild von Junaid Ackroyd
Junaid Ackroydvor 1 Monat

The best coding agent on the market

Profilbild von catman
catmanvor 1 Monat

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

Profilbild von Antoni
Antonivor 1 Monat

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

Profilbild von Kamal Bisht 🔴 AI Marketer
Kamal Bisht 🔴 AI Marketervor 1 Monat

$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.

Profilbild von Adam Cohen
Adam Cohenvor 1 Monat

Give it a test. Think you’ll be impressed

Profilbild von Kamal Bisht 🔴 AI Marketer
Kamal Bisht 🔴 AI Marketervor 1 Monat

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

Profilbild von 安叫兽|Bird🕊️ 🔶 BNB
安叫兽|Bird🕊️ 🔶 BNBvor 1 Monat

长任务跑下来稳不稳啊?

Profilbild von swork1
swork1vor 1 Monat

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

Profilbild von Cupsey
Cupseyvor 1 Monat

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

Profilbild von Sam Sung
Sam Sungvor 1 Monat

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

Profilbild von Adam Cohen
Adam Cohenvor 1 Monat

@daltonc All hosted in US

Profilbild von Sam Sung
Sam Sungvor 1 Monat

@daltonc awesome thanks!

Profilbild von Yash
Yashvor 1 Monat

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

Ähnliche Videos