# Wan 2.6 > Wan 2.6 is available on Artifio.ai — a unified AI workspace with a single pay-as-you-go wallet. - Canonical page: https://artifio.ai/models/wan-2-6-text-to-video - Run it: https://artifio.ai/create/wan-2-6-text-to-video - Modality: prompt to video - Model brand: Wan - Pricing: from about $0.350 per generation (exact cost shown in the workspace before you confirm; varies with selected options) - Typical generation time: ~800s (catalogue estimate) - Full pricing table: https://artifio.ai/pricing/models ## About Wan 2.6 Wan 2.6 is the December 2025 generation of Alibaba's Wan visual model family, announced by the company on December 16, 2025. The release upgraded the text-to-video model (Wan2.6-T2V) alongside image-to-video, a new reference-to-video mode, and two image models. Alibaba's headline change for this generation is multi-shot storytelling: instead of producing one continuous shot, the model can cut between shots while keeping characters and scenes visually consistent, and it pairs the footage with synchronized audio in the same pass. The Wan line started in the open: Wan 2.1 was published as an open-source suite with 1.3B and 14B parameter models, and Wan 2.2 followed under Apache 2.0 on GitHub. Wan 2.6 is a hosted service instead, offered through Alibaba Cloud's Model Studio, the Wan website, and the Qwen app. On Artifio it runs in the same workspace as 100+ other models, billed per generation rather than per subscription. ## Features - Generates 720p or 1080p video at 30 fps from a text prompt, with audio produced in the same pass. - Clip length options of 5, 10, or 15 seconds, triple the 5-second ceiling of the open Wan 2.1 and 2.2 releases. - Multi-shot narrative generation: one prompt can yield a sequence of cuts with consistent characters and scenery. - Improved audio-visual synchronization and audio-to-video generation, which Alibaba says delivers more realistic scenes with richer sound effects. - Supports multi-person dialogue within a scene, a capability Alibaba flags as new for this generation. - Part of a five-model 2.6 release covering text-to-video, image-to-video, reference-to-video, and two image models. ## What people use it for - Short social clips where dialogue and sound effects need to land in one generation instead of a separate audio pass. - Storyboard-style multi-shot sequences for ads, trailers, and pitch previsualization. - Narrative scenes with more than one speaking character. - Sound-driven mood pieces that lean on the model's audio-to-video generation. ## Reported strengths - Native audio, including dialogue and sound effects, is generated with the video rather than layered on afterwards. - The 15-second ceiling and multi-shot cutting give it more narrative room than most single-shot video models. - 1080p at 30 fps is available on every duration option, not reserved for a premium tier. ## Reported limitations - Output tops out at 1080p; there is no 4K video option in the hosted specs. - It has been overtaken on the Artificial Analysis text-to-video arena: as of July 2026 it holds an Elo of 1028, well below Wan 2.7 at 1102 and the June 2026 Wan 2.7 checkpoint at 1160. - Unlike Wan 2.1 and 2.2, no open weights have been published for Wan 2.6; the Wan GitHub organization's newest open release is still Wan 2.2. - Durations come from a fixed menu of 5, 10, or 15 seconds rather than an arbitrary length. ## Sources 1. Alibaba unveils Wan2.6 series enabling everyone to star in videos (Alibaba Cloud): https://www.alibabacloud.com/blog/alibaba-unveils-wan2-6-series-enabling-everyone-to-star-in-videos_602742 2. Video generation, Alibaba Cloud Model Studio documentation (Alibaba Cloud): https://www.alibabacloud.com/help/en/model-studio/use-video-generation 3. Text to video leaderboard (Artificial Analysis): https://artificialanalysis.ai/video/leaderboard/text-to-video 4. Wan2.2: open and advanced large-scale video generative models (GitHub (Wan-Video)): https://github.com/Wan-Video/Wan2.2 5. Wan: open and advanced large-scale video generative models (arXiv): https://arxiv.org/abs/2503.20314 --- About Artifio.ai: 100+ AI image, video, and audio models in one workspace with a single shared wallet — no per-model subscriptions. This is the markdown rendition of https://artifio.ai/models/wan-2-6-text-to-video for AI assistants and crawlers; the HTML page is canonical.