Video

Wan 2.5

Wan 2.5 generates short videos from text prompts or one reference image, with optional audio reference input, 480p/720p/1080p resolution, 5 or 10 second duration, and prompt expansion enabled by default.

Start creating API Docs

Text, image, or optional audio

480p / 720p / 1080p

5 or 10 seconds

Prompt expansion

Generated preview

Wan 2.5

Start now

Create with Wan 2.5

Loading workspace...

Authentication & Integration

Checking API access...

Sign in to claim free credits and create with this model.

Integrate with AI

Copy a prompt for your AI assistant to install APIXO MCP, read the live schema, and wire this model into your app.

Endpoints

POSThttps://api.apixo.ai/api/v1/generateTask/wan-2-5-videoCreate task

GEThttps://api.apixo.ai/api/v1/statusTask/wan-2-5-video?taskId={taskId}Poll status

Request body

request_type

async

Use callback with callback_url for webhooks.

input

object

Mode, prompt, references, size, duration, and audio settings.

Parameters

request_typerequired

Typeselect

Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback

callback_urlconditional

Typetext

Public HTTPS URL for callback delivery.Only in request_type=callback

moderequired

Typeselect

Choose text-to-video or image-to-video. Image-to-video requires exactly one reference image.text-to-video · image-to-video

promptrequired

Typestring

Describe the desired video. Text-to-video requires a prompt; image-to-video can use a prompt to guide the animation.

resolutionrequired

Typeselect

Choose 480p for low-cost drafts, 720p for balanced output, or 1080p for higher quality.480p · 720p · 1080p

durationrequired

Typeselect

Wan 2.5 supports 5 or 10 second outputs.5 · 10

aspect_ratioconditional

Typeselect

Aspect ratio applies to text-to-video. Omit it for image-to-video.16:9 · 9:16 · 1:1 · 4:3 · 3:4Only in mode=text-to-video

watermarkoptional

Typeboolean

Add a watermark to the generated output when enabled.

enable_prompt_expansionoptional

Typeboolean

Let the model expand and optimize the prompt before generation.

negative_promptoptional

Typestring

Describe what to avoid in the video.

seedoptional

Typetext

Optional seed for reproducible generations.

Parameter	Type	Required	Description
`request_type`	select	required	Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback
`callback_url`	text	conditional	Public HTTPS URL for callback delivery.Only in request_type=callback
`mode`	select	required	Choose text-to-video or image-to-video. Image-to-video requires exactly one reference image.text-to-video · image-to-video
`prompt`	string	required	Describe the desired video. Text-to-video requires a prompt; image-to-video can use a prompt to guide the animation.
`resolution`	select	required	Choose 480p for low-cost drafts, 720p for balanced output, or 1080p for higher quality.480p · 720p · 1080p
`duration`	select	required	Wan 2.5 supports 5 or 10 second outputs.5 · 10
`aspect_ratio`	select	conditional	Aspect ratio applies to text-to-video. Omit it for image-to-video.16:9 · 9:16 · 1:1 · 4:3 · 3:4Only in mode=text-to-video
`watermark`	boolean	optional	Add a watermark to the generated output when enabled.
`enable_prompt_expansion`	boolean	optional	Let the model expand and optimize the prompt before generation.
`negative_prompt`	string	optional	Describe what to avoid in the video.
`seed`	text	optional	Optional seed for reproducible generations.

File parameters (URL arrays)

image_urls[mode=image-to-video]Upload exactly one reference image for image-to-video. The source image should be at most 20 MB.Only in mode=image-to-video

audio_urlsOptional MP3 or WAV audio reference. Wan 2.5 accepts exactly one audio URL, up to 15 MB, with 3-30 seconds recommended.

Example (cURL)

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-2-5-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a serene mountain landscape with moving clouds and gentle breeze",
      "resolution": "720p",
      "duration": 5,
      "aspect_ratio": "16:9",
      "negative_prompt": "low quality, blurry",
      "enable_prompt_expansion": true
    }
  }'

Full API documentation

Wan 2.5 Tips

Create video generation with Wan 2.5

Use Wan 2.5 through APIXO to try prompts, inspect examples, compare costs, and keep useful settings ready for future generations.

Create

Start with an idea

Pick a model, tune the settings, and create in one place.

Write an idea

Describe what you want to make.

Use an example

Start from a ready-made style.

Adjust the look

Tune the key settings quickly.

Create

Generate when everything feels right.

Keep results

Save what you want to revisit.

Try again

Make the next version faster.

Wan 2.5 API Technical Specs

Current Wan 2.5 capabilities and important creation limits.

Wan 2.5 Modes

Text-to-video and image-to-video

Wan 2.5 Output

Text, image, or optional audio

Wan 2.5 Controls

480p / 720p / 1080p / 5 or 10 seconds

Wan 2.5 Latency

Typically 40-250 seconds

Alibaba Video API

Key Wan 2.5 capabilities

Wan 2.5 video generation

Use Wan 2.5 for Text-to-video and image-to-video creation with simple controls for prompts, references, and output settings.

Wan 2.5 reference control

Upload supported reference assets where available, then keep refining the same idea on the model page.

Wan 2.5 generation status

Keep track of longer video generations while the result is being prepared.

What can you build with Wan 2.5?

Wan 2.5 product videos

Create product reveals, ecommerce ads, launch clips, and campaign motion assets.

Wan 2.5 social creative

Generate short videos for social channels and iterate quickly across prompt, duration, resolution, and ratio settings.

Wan 2.5 storyboard workflows

Use text prompts and references to validate scenes, shots, and motion ideas before committing production budget.

Read FAQ

Wan 2.5 notes and questions

Text-to-video prompt length must be between 1 and 1500 characters. Image-to-video can use an optional prompt for motion guidance.

Image-to-video requires exactly one reference image URL.

Audio input is optional, must use audio_urls, and supports exactly one MP3 or WAV file up to 15 MB.

Duration must be 5 or 10 seconds.

Text-to-video supports 16:9, 9:16, and 1:1 at every resolution; 4:3 and 3:4 require 720p or 1080p.

Negative prompt supports up to 500 characters.

Yes. Use the Create tab to try prompts, upload supported inputs, and adjust settings directly in the browser.

APIXO

Create with Wan 2.5

Write a prompt, adjust the style, and generate your next image in one place.

Start creating View API docs