Independent third-party resource
LongCat is Meituan’s open-source AI model family — language models, image generation, video, and text-to-speech.
Not affiliated with, endorsed by, or sponsored by Meituan or LongCat.
Each overview separates verified source material from future independent testing.
A model documented in the meituan-longcat GitHub organization and exposed through the LongCat publisher API platform.
A 560-billion-parameter Mixture-of-Experts language model with dynamic computation, averaging 27B activated parameters per token. Built for high-throughput chat and agentic tasks.
A 6-billion-parameter bilingual image generation and editing model covering all 8,105 standard Chinese characters, with open-source SOTA on image editing benchmarks.
A 560B-parameter open-source omni-modal model with 27B activated, excelling at real-time audio-visual interaction — text, image, audio, and video in a single end-to-end framework.
Practical setup and usage guides, published with source references.
Independent test records with methodology and limitations disclosed.
Task-focused comparisons designed to explain trade-offs.
Source-linked updates about the LongCat ecosystem.