LongCat-Flash
Meituan IncLanguage modeling/generationQuestion answeringChatCode generationQuantitative reasoningInstruction interpretationOpen weights
The LongCat-Flash model is an open-weights language modeling/generation model from Meituan Inc with 560000000000.0 parameters.
About LongCat-Flash
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming from the need for scalable efficiency, LongCat-Flash adopts two novel d
LLM pricing & performance
Full LLM page →LongCat-Flash is available via API — live cost, context, and benchmark data:
Input / 1M
—
Output / 1M
—
Context
—
Tokens/sec
—
LMArena (Chatbot Arena) Elo: 1421.9
Details
- Provider
- Meituan Inc
- Task
- Language modeling/generation,Question answering,Chat,Code generation,Quantitative reasoning,Instruction interpretation
- Parameters
- 560000000000.0
- Released
- 2025-09-01
- Open weights
- Yes