← All models
Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.
Example
Details
- Accepts
- video
Pricing
- Price
- 12.5 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for reproducibility (0-2147483647). |
| promptrequired | string | Editing instruction or style transfer description. |
| duration | integerenum: 0, 2, 3, 4, 5, 6… | Output video duration in seconds. Default 0 means match input video duration. When set (2-10), truncates from the start. |
| video_urlrequired | string | URL of the input video to edit. Format: MP4, MOV. Duration: 2-10s. Max 100 MB. Max file size: 100.0MB, Min duration: 2s, Max duration: 10s, Timeout: 30.0s |
| resolution | stringenum: 720p, 1080p | Output video resolution tier. |
| aspect_ratio | — | Aspect ratio of the generated video. If not provided, uses the aspect ratio of the input video. |
| audio_setting | stringenum: auto, origin | Audio handling. 'auto': model decides whether to regenerate audio. 'origin': preserve original audio from input video. |
| reference_image_url | — | Reference image URL for reference-based editing. |
| enable_safety_checker | boolean | Enable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used for generation. |
| video | — | The edited video file. |
| actual_prompt | — | The actual prompt used if prompt rewriting was enabled. |