Alibaba video generation and editing

WAN 2.7 API

Generate and edit WAN 2.7 video with synced audio.

WAN 2.7 supports prompt-based generation, first/last-frame animation, multi-reference generation, and instruction-based video editing with native audio. Run it through the same task, polling, callback, and credit balance used by the rest of your model stack.

Try playground

720p/1080p

Resolution

2-15s

Duration

Text, image, reference, edit

Input modes

Alibaba

wan-2.7-text-to-videoasync task

720p/1080p

Resolution

2-15s

Duration

Text, image, reference, edit

Input modes

Model capabilities

Built for production API workflows, not one-off demos.

Use WAN 2.7 from the same platform surface as the rest of your video and image stack: API keys, credits, logs, webhooks, and docs stay consistent across providers.

Text-to-video generation

Create clips from prompts with configurable aspect ratio, duration, and reference audio.

Image-to-video animation

Drive motion from first and last frame images, with optional driving audio.

Reference-to-video generation

Blend reference images and videos (up to 5 combined) into a guided scene with a reference voice.

Video editing

Edit a source video with text instructions and a reference image, preserving or regenerating audio.

Resolution control

Choose 720p for efficient generation or 1080p for higher-fidelity output.

API workflow

Submit tasks, track progress, and return generated assets.

Choose input type

Use text, first/last-frame images, references, or a source video.

Set resolution and duration

Pick 720p or 1080p and a target duration per mode.

Route output to your app

Use task IDs, logs, and callbacks for operational delivery.

POST /v1/videos/generations

curl -X POST https://api.aivideoapi.ai/v1/videos/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan-2.7-text-to-video",
    "input": {
      "prompt": "A cinematic tracking shot through a rainy neon street at night",
      "resolution": "1080p",
      "aspect_ratio": "16:9",
      "duration": 5
    }
  }'

What teams build

Prompt-to-video tests

Product reveals with audio

First/last-frame animation

Reference character generation

Instruction-based video edits

Ad creative batches

Frequently asked questions

Answers about the WAN 2.7 API.

What is the WAN 2.7 API?

WAN 2.7 is Alibaba's video generation and editing model. The AI Video API exposes it through one HTTP endpoint (POST /v1/videos/generations) with credits, webhooks, and logs shared across all supported video models.

Which WAN 2.7 modes are supported?

Four: text-to-video (wan-2.7-text-to-video), image-to-video (wan-2.7-image-to-video), reference-to-video (wan-2.7-reference-to-video), and video editing (wan-2.7-video-edit).

How much does the WAN 2.7 API cost?

Pricing is per second by resolution: 720p is 24 credits/s and 1080p is 40 credits/s. For video editing, duration=0 bills by the full input video length; a value of 2-10 bills by that clip length.

Can I receive a webhook when generation finishes?

Yes. Pass a callback_url when creating the task and the platform will POST the completed result (or error) to that URL. Status is also pollable via GET /v1/tasks/{taskId}.

Pricing and usage

Clear model options with shared credits.

720p

24 credits/s

Efficient generation

1080p

40 credits/s

Higher-fidelity output

Text/image/reference

Billed by duration

Output seconds × rate

Video edit

By input length

duration=0 bills the full input video

Start building with WAN 2.7 in AI Video API.

Create one API key, use one credit balance, and switch between video and image models without provider-specific plumbing.

Read docs