LongCat Video Avatar 1.6

Released
2026-11-15
Last refreshed
2026-11-17
Status
Researched today
Open sourceCommercial use: permittedMultimodal

LongCat Video Avatar 1.6 is a released general LLM work model with open-source; evaluate it while provider pricing coverage matures.

Meituan releases · 3 in the last 12 months · this family litChangelog →
Specifications
Released
2026-11-15
Specialization
video-generation
Openness
Open source
License
MITOSI-approvedPermitted
Weights
Available
Code
Unknown
Created by

Chinese technology company whose in-house AI team builds the LongCat language-model family.

Beijing, China
Website
Pricing

No tracked provider pricing is available yet.

About

LongCat Video Avatar 1.6 is Meituan's open audio-driven avatar video model. The maker's release notes date the release to November 15, 2026. It builds on version 1.5 to improve lip synchronization, facial and body motion, and visual consistency in long videos, including examples over ten minutes. The checkpoint includes task-specific DMD and on-policy-distillation LoRA adapters, with eight-step inference and an optional INT8 backbone. The model card explicitly licenses the weights under MIT.

Providers

No active provider routes are tracked for this model yet.

Capabilities

VisionMultimodalAudio

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

meituan-longcat/LongCat-Video-Avatar-1.6