LLM
GA
Open source
LongCat-Flash-Omni
Open-weight omni-modal understanding
Release2026-03
Context131K
Max output—
Parameters560B
Local / VRAM640–800 GB
LicenseOpen source
Overview
LongCat-Flash-Omni is a model in the LLM category from Meituan (LongCat). It was released in 2026-03. The vendor is based in China. Best for: Open-weight omni-modal understanding.
Strengths
- MIT
- Audio/video/vision
- Strong Chinese
Limits
- Heavy hardware
- Text-only output
Specifications
| Vendor | Meituan (LongCat) |
|---|---|
| Category | LLM |
| Release | 2026-03 |
| Status | GA |
| License | Open source |
| License name | MIT |
| Commercial use | Allowed |
| Parameters | 560B |
| Active parameters | 27B |
| Architecture | MoE omni-modal |
| Context window | 131K |
| Input modalities | Text, Image, Video, Audio |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 640–800 GB |
| System RAM | 768–1536 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | Medium |
| Vendor country | China |
| Vendor type | Open lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 640–800 GB. Approximate system RAM: 768–1536 GB. API access is available.