by Meituan
Meituan has officially released and open-sourced LongCat-Flash-Chat, which utilizes an innovative Mixture of Experts (MoE) and "zero-computation expert" mechanism to achieve a total of 560B parameters, while only activating around 27B parameters per token as needed. At the same time, end-to-end optimization for agents (including a self-built evaluation set and multi-agent trajectory data) significantly enhances its performance in tool usage and complex task orchestration.
Meituan has officially released and open-sourced LongCat-Flash-Chat, which utilizes an innovative Mixture of Experts (MoE) and "zero-computation expert" mechanism to achieve a total of 560B parameters, while only activating around 27B parameters per token as needed. At the same time, end-to-end optimization for agents (including a self-built evaluation set and multi-agent trajectory data) significantly enhances its performance in tool usage and complex task orchestration.
On AIHubMix, LongCat-Flash-Chat costs $0.14 per million input tokens and $0.7 per million output tokens.
LongCat-Flash-Chat is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to LongCat-Flash-Chat — no other code changes needed.
LongCat-Flash-Chat is developed by Meituan. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Designed for agent development scenarios, it natively supports tool invocation…
Use LongCat-Flash-Chat via the AIHubMix unified API — one interface for every major LLM.