LongCat-Next
We develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal inductive bias beyond the language paradigm.
text + image → text + image · made by Meituan LongCat
Sold by
Nobody in the catalogue publishes a price for this yet.
About
LongCat-Next — a text and images model from Meituan LongCat.
It takes text and images and returns text and images. It was published in March 2026. The catalogue files it under image. Its weights are published under MIT, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- Meituan LongCat
- Register
- model
- Takes
- text + image
- Returns
- text + image
- Published
- March 2026
- Parameters
- 74 billion · read from its own weights
- Licence
- mit
Known as 1 name
meituan-longcat/LongCat-Next