Meituan: LongCat 2.0
LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...
Everything else
| Max output | 262K |
|---|---|
| Input / 1M | $0.3 |
| Output / 1M | $1.20 |
| Cache read / 1M | $0.006 |
| Cache write / 1M | — |
| 1M in + 1M out | $1.50 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | optional |
| Open weights | yes |
| Released | 2026-07-20 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | meituan/longcat-2.0 |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.