CatchCase

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...

  • Context window: 1M tokens
  • Max output: 262K tokens
  • Reads: text
  • Writes: text