Wan 2.6

HappyHorse 1.1 is Alibaba's closed-weight cinematic video generation model, producing clips of 3-15 seconds with synchronized audio and multilingual lip-synced dialogue generated in a single pass. It generates video from a text prompt, a single starting image, or a set of reference images, and supports video editing of existing clips, at output resolutions of 480p, 720p, and 1080p. It improves on HappyHorse 1.0 with stronger prompt adherence, smoother motion, and more consistent characters across frames, and previously topped the Artificial Analysis video arena anonymously before Alibaba was revealed as its maker.

Qwen3.8-27B is Alibaba's compact, deployment-friendly open-weight model from the Qwen3.8 generation, released under Apache 2.0. It is a 27.8-billion-parameter dense model using a hybrid decoder that alternates Gated DeltaNet linear attention with grouped-query full attention, with native text, image, and video understanding, a 262,144-token context window, and configurable reasoning effort toggled on or off per request. It targets coding, professional work, research, and long-horizon agentic tasks in a footprint small enough to self-host on high-end consumer hardware.

Qwen3.8-Max is Alibaba's flagship sparse mixture-of-experts model, with 2.4 trillion total parameters and approximately 95 billion active per forward pass, accepting text, image, and video input and returning text with a 1M-token context window. Hybrid thinking mode is enabled by default with three reasoning-effort tiers, and pricing is flat across the full context window with no long-prompt surcharge. Target workloads include software engineering, long-horizon agentic work, office productivity, and visual tasks such as turning screenshots or design files into working pages.

Wan 2.7 is Alibaba Tongyi Lab's flagship video generation model, offering text-to-video, image-to-video, reference-to-video, and instruction-based video editing through one endpoint. It supports first-and-last-frame control, up to 5 reference images, videos, and audio clips for consistent subject and voice identity, native synchronized audio (ambient sound, lip-synced dialogue, music), connected multi-shot generation, and clips of 2-15 seconds at up to 1080P.

Wan 3.0 is Alibaba Tongyi Lab's all-in-one multimodal video generation model for longer, reference-heavy, production-oriented work. One endpoint covers text-to-video, first- and last-frame image-to-video, reference-driven generation (up to 10 images, 5 videos, and 5 audio clips), localized video editing, and temporal extension, with documents and public webpages accepted as additional inputs. It generates 2-30 second clips at 480P, 720P, or 1080P with native synchronized audio on by default. API access only; no open weights.