Video

Wan 2.7

Wan 2.7 generates and edits video from text, images, reference media, or source clips, with 720p/1080p output, flexible duration control, optional audio references, and async polling or callback delivery.

Start creating API Docs

Generated preview

Wan 2.7

Start now

Create with Wan 2.7

Loading workspace...

Wan 2.7 is billed per second. Unit price depends on mode and resolution, while video-edit uses billable seconds derived from input and output duration.

Text-to-Video

Resolution

720p

APIXO official price

$0.10 / second

Billing formula

duration * unitPrice

Text-to-Video

Resolution

1080p

APIXO official price

$0.15 / second

Billing formula

duration * unitPrice

Image-to-Video

Resolution

720p

APIXO official price

$0.10 / second

Billing formula

duration * unitPrice

Image-to-Video

Resolution

1080p

APIXO official price

$0.15 / second

Billing formula

duration * unitPrice

Reference-to-Video

Resolution

720p

APIXO official price

$0.15 / second

Billing formula

duration * unitPrice

Reference-to-Video

Resolution

1080p

APIXO official price

$0.24 / second

Billing formula

duration * unitPrice

Video Edit

Resolution

720p

APIXO official price

$0.10 / second

Billing formula

billableSeconds * unitPrice

Video Edit

Resolution

1080p

APIXO official price

$0.15 / second

Billing formula

billableSeconds * unitPrice

ModeResolutionAPIXO official priceBilling formula

Text-to-Video720p$0.10 / secondduration * unitPrice

Text-to-Video1080p$0.15 / secondduration * unitPrice

Image-to-Video720p$0.10 / secondduration * unitPrice

Image-to-Video1080p$0.15 / secondduration * unitPrice

Reference-to-Video720p$0.15 / secondduration * unitPrice

Reference-to-Video1080p$0.24 / secondduration * unitPrice

Video Edit720p$0.10 / secondbillableSeconds * unitPrice

Video Edit1080p$0.15 / secondbillableSeconds * unitPrice

Text-to-video and image-to-video are billed as duration times the selected resolution rate.
Reference-to-video uses higher per-second rates and supports 2-15 seconds, or 2-10 seconds when a reference video is used.
Video-edit uses billableSeconds times the selected resolution rate; when duration is 0, billableSeconds is cappedInputDuration times 2.
Use audio_urls for public audio input. Do not use the legacy audio_url field.

For video-edit, the Create tab may show no exact estimate because billable seconds depend on the uploaded input video duration.

Example: text-to-video at 720p for 5 seconds costs 5 x $0.10 = $0.50.

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-2-7-videoCreate task

GEThttps://api.apixo.ai/api/v1/statusTask/wan-2-7-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, image-to-video, reference-guided video, or video-edit workflow.text-to-video · image-to-video · reference-to-video · video-edit

promptconditional

Typestring

Required for text-to-video and reference-to-video. Optional for image-to-video and video-edit.

resolutionrequired

Typeselect

Choose the output resolution tier. Higher resolution costs more per generated second.720p · 1080p

ratioconditional

Typeselect

Supported for text-to-video and reference-to-video, optional for video-edit, and not supported for image-to-video.16:9 · 9:16 · 1:1 · 4:3 · 3:4Only in mode=text-to-video | reference-to-video | video-edit

durationrequired

Typeselect

Text and image modes support 2-15 seconds. Reference mode supports 2-15 seconds, or 2-10 seconds when using reference videos. Video-edit supports 0 or 2-10 seconds.0 · 2 · 3 · 4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15

negative_promptoptional

Typestring

Optional prompt describing what to avoid in the generated video.

prompt_extendoptional

Typeboolean

Enable prompt rewriting before generation. This can improve short prompts but may increase latency.

audio_settingconditional

Typeselect

Video-edit only. Auto lets Wan 2.7 decide whether to regenerate audio; origin keeps the source audio when supported.auto · originOnly in mode=video-edit

watermarkoptional

Typeboolean

Add a bottom-right watermark to the generated output when enabled.

seedoptional

Typetext

Optional random seed from 0 to 2147483647.

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, image-to-video, reference-guided video, or video-edit workflow.text-to-video · image-to-video · reference-to-video · video-edit
`prompt`	string	conditional	Required for text-to-video and reference-to-video. Optional for image-to-video and video-edit.
`resolution`	select	required	Choose the output resolution tier. Higher resolution costs more per generated second.720p · 1080p
`ratio`	select	conditional	Supported for text-to-video and reference-to-video, optional for video-edit, and not supported for image-to-video.16:9 · 9:16 · 1:1 · 4:3 · 3:4Only in mode=text-to-video \| reference-to-video \| video-edit
`duration`	select	required	Text and image modes support 2-15 seconds. Reference mode supports 2-15 seconds, or 2-10 seconds when using reference videos. Video-edit supports 0 or 2-10 seconds.0 · 2 · 3 · 4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15
`negative_prompt`	string	optional	Optional prompt describing what to avoid in the generated video.
`prompt_extend`	boolean	optional	Enable prompt rewriting before generation. This can improve short prompts but may increase latency.
`audio_setting`	select	conditional	Video-edit only. Auto lets Wan 2.7 decide whether to regenerate audio; origin keeps the source audio when supported.auto · originOnly in mode=video-edit
`watermark`	boolean	optional	Add a bottom-right watermark to the generated output when enabled.
`seed`	text	optional	Optional random seed from 0 to 2147483647.

File parameters (URL arrays)

image_urls[mode=image-to-video | reference-to-video | video-edit]Image-to-video supports first and optional last frame images. Reference-to-video accepts image references. Video-edit accepts up to four reference images.Only in mode=image-to-video | reference-to-video | video-edit

video_urls[mode=image-to-video | reference-to-video | video-edit]Image-to-video can use one continuation clip, reference-to-video can use reference clips, and video-edit requires exactly one input video.Only in mode=image-to-video | reference-to-video | video-edit

audio_urls[mode=text-to-video | image-to-video | reference-to-video]Optional public WAV or MP3 audio input. Reference-to-video audio references must match the reference item count when provided.Only in mode=text-to-video | image-to-video | reference-to-video

Example (cURL)

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-2-7-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic rainy night in tokyo",
      "resolution": "1080p",
      "ratio": "16:9",
      "duration": 5
    }
  }'

Full API documentation

Wan 2.7 Tips

Create video generation with Wan 2.7

Use Wan 2.7 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 2.7 API Technical Specs

Current Wan 2.7 capabilities and important creation limits.

Wan 2.7 Modes

Text-to-video, image-to-video, reference-to-video, and video-edit

Wan 2.7 Output

Video output

Wan 2.7 Controls

Prompt and mode settings

Wan 2.7 Latency

First poll after 60-90 seconds

Alibaba Video API

Key Wan 2.7 capabilities

Wan 2.7 video generation

Use Wan 2.7 for Text-to-video, image-to-video, reference-to-video, and video-edit creation with simple controls for prompts, references, and output settings.

Wan 2.7 reference control

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

Wan 2.7 generation status

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

What can you build with Wan 2.7?

Wan 2.7 product videos

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

Wan 2.7 social creative

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

Wan 2.7 storyboard workflows

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

Read FAQ

Wan 2.7 notes and questions

Prompt is required for text-to-video and reference-to-video, and optional for image-to-video and video-edit.

Image-to-video requires image_urls or video_urls. If video_urls is provided, audio_urls is not allowed for that mode.

Reference-to-video requires 1-5 total reference items across image_urls and video_urls.

When reference-to-video includes audio_urls, the audio count must match the total reference item count.

Video-edit requires exactly one input video and accepts up to four optional reference images.

Ratio is not supported for image-to-video, but is available for text-to-video, reference-to-video, and video-edit.

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

APIXO

Create with Wan 2.7

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

Start creating View API docs