Wan 2.6
Summary
Wan 2.6 is a proprietary video generation model from Alibaba (Qwen), released on 3 Dec 2025. It accepts text and images and generates video, with a 400K-token context window.
Video model for text- and image-to-video with audio input and synchronized sound
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | 3 Dec 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 400K (400,000 tokens) [models.dev] |
| Input | Text and images [models.dev] |
| Output | Video [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
Wan 2.6 API pricing by provider
USD per million tokens. Sorted by input price.
We do not currently track a paid API listing for this model.
Frequently asked questions
What is the context window of Wan 2.6?
Wan 2.6 has a context window of 400,000 tokens (400K), according to models.dev.
Is Wan 2.6 open source?
No. Wan 2.6 is a proprietary model; Alibaba (Qwen) has not released its weights.
When was Wan 2.6 released?
Alibaba (Qwen) released Wan 2.6 on 3 Dec 2025, according to models.dev.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Veo 3.1 Fast | Google DeepMind | 15 Oct 2025 | 400K | – | – | Closed |
| Veo 3.1 Lite | Google DeepMind | 31 Mar 2026 | 400K | – | – | Closed |
| Seedance 2.5 | ByteDance Seed | 31 Jul 2026 | – | – | – | Closed |
| MiniMax H3 Max | MiniMax | 26 Aug 2026 | – | – | – | Closed |
| Seedance 2.0 | ByteDance Seed | 12 Feb 2026 | 4K | – | – | Closed |
| Grok Imagine Video | xAI | 28 Jan 2026 | 1K | – | – | Closed |
Change history
- Added to the directory