Parameters
| Name | Description | Type | Required | Enums |
|---|---|---|---|---|
| negative_prompt | Negative prompt describing unwanted content | string | No | - |
| prompt | Text prompt describing desired video modifications (supports Chinese and English, up to 5000 characters) | string | No | - |
| audio_setting | Audio handling mode (auto: intelligent decision based on prompt, origin: preserve original audio) | string | No | auto, origin |
| duration | Video duration in seconds (2-10 = truncate to specified length) | integer | No | 2, 3, 4, 5, 6, 7, 8, 9, 10 |
| prompt_extend | Enable intelligent prompt rewriting (improves quality for short prompts but increases processing time) | boolean | No | true, false |
| ratio | Video aspect ratio (defaults to input video ratio if not specified) | string | No | 16:9, 9:16, 1:1, 4:3, 3:4 |
| reference_images | Reference image URLs for style transfer (optional, max 4). Combined with video_url, the total media count must be ≤ 5 | string[] | No | - |
| resolution | Video resolution tier | string | No | 720P, 1080P |
| seed | Random seed for reproducibility (note: results may vary even with same seed) | integer | No | - |
| video_url | Input video URL (HTTP/HTTPS/OSS) or Base64 encoded data (required) | string | Yes | - |
Pricing
Unit: $/sec
| Dimension | Pricing |
|---|---|
| resolution: 720P | 0.1000 |
| resolution: 1080P | 0.1400 |
Related Models
- alibaba/wan2.7-image: Wan 2.7 Image is the standard text-to-image model with faster generation speed. Supports up to 2K resolution, thinking mode, sequential generation, and custom color themes. Does not support 4K.
- alibaba/wan2.7-image-pro: Wan 2.7 Image Pro is the professional text-to-image model supporting up to 4K resolution, thinking mode for enhanced reasoning, sequential multi-image generation, and custom color themes. Supports Chinese and English prompts up to 5000 characters.
- alibaba/wan2.7-image-edit: Wan 2.7 Image Edit is the standard image editing model with faster generation speed. Supports multi-image reference, interactive editing, sequential generation, and custom color themes. Max 2K output. Does not support 4K.
- alibaba/wan2.7-image-pro-edit: Wan 2.7 Image Pro Edit is the professional image editing model supporting multi-image reference generation, interactive bounding-box editing, sequential multi-image generation, and custom color themes. Supports 1-9 input images, max 2K output.
- alibaba/wan2.7-r2v: Wan 2.7 Reference-to-Video model generates videos from reference media (images and videos) with prompts. Requires at least one media parameter (reference_images, reference_videos, or first_frame_image). Supports multi-subject references, storyboard generation, and custom audio for voice cloning.
- alibaba/wan2.7-t2v: Wan 2.7 text-to-video model generates high-quality videos from text prompts using the new protocol (resolution+ratio instead of size). Supports multi-shot narrative, automatic dubbing, custom audio, 720P/1080P resolutions, and 2–15 second durations.
- alibaba/wan2.7-i2v: Wan 2.7 image-to-video model supports three task modes with flattened media parameters: first-frame generation, first-last-frame generation, and continuation. Parameter combination must conform to allowed mode combinations.
