⌘K

Wan 2.5 Text-to-Video Preview

wan25_t2v_preview

Wan2.5 Text-to-Video Preview is Alibaba's preview video generation model that creates videos from text prompts via the mainland China (Beijing) endpoint.

Authentication

authorization string required

All APIs require authentication via Bearer Token.

Get API Key:

Visit API Key Management Page to get your API Key

Usage:

Add to request header:

Authorization: Bearer YOUR_API_KEY

Parameters

model string required

Model ID to use for the request

Value: wan25_t2v_preview

input object required

Input parameters for the generation request

prompt string required

Text prompt used to describe the expected elements, motion, style, and visual characteristics in the generated video. Supports Chinese and English.

Example: A kitten running in the moonlight

negative_prompt string

Negative prompt describing what should not appear in the generated video.

audio_url string

Optional audio file URL used for sound-synchronized video generation.

parameters object

Generation parameters

size string

Specifies the output video size in width*height format.

Common options: 832*480, 1280*720, 1920*1080

Default: 1280*720

duration integer

Duration of the generated video in seconds. The duration directly affects billing costs.

Common options: 5, 10

Default: 5

prompt_extend boolean

Whether to enable intelligent prompt rewriting. When enabled, a large model rewrites and enriches the prompt before video generation.

Options: true, false

Default: true

watermark boolean

Whether to add a watermark identifier to the generated video.

Options: false, true

Default: false

seed integer

Random seed. If not specified, the system automatically generates a random seed.

Range: 0 - 2147483647

Response

The create request returns a task ID immediately. Poll the task endpoint until the task reaches completed or failed.