LongCat Video Models by Meituan
Meituan releases · 3 in the last 12 months · this family litChangelog →
1 model2026
Last refreshed 2026-11-17. Next refresh: weekly.
Capabilities
VisionAll models
MultimodalAll models
About
Meituan LongCat's open video and audio-driven avatar models, with MIT-licensed Avatar 1.6 weights.
Decision facts
- Best fit
- video generationvision and multimodal work
- Capability starting point
- LongCat Video Avatar 1.6 with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- LongCat
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
LongCat Video Avatar 1.6Current
Use when the workload needs video generation, multimodal inputs, and audio.
2026-11video generationmultimodal inputsaudio
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| LongCat Video Avatar 1.6 | Use when the workload needs video generation, multimodal inputs, and audio. | 2026-11 | video generationmultimodal inputsaudio | Current |
Release Timeline
1 release group2026-11
1 current
LongCat Video Avatar 1.6
Currentvideo generationmultimodal inputsaudio
Specifications(1 models)
| Model | Released | Vision | Multimodal |
|---|---|---|---|
| LongCat Video Avatar 1.6 | 2026-11 | Yes | Yes |