Wan API
Video APIWan API brings multiple AI video workflows into one production path, including text-to-video, image-to-video, video-to-video, video editing, animation, and reference-to-video generation.
Use Wan 2.7 for high-quality 720p and 1080p generation, then switch between text, image, video, and reference modes based on the exact input your product or campaign needs.
Lowest cost starts at $0.04/s
480P: 8 credits/s - Text/Image to Video - Output seconds × 8
720P: 16 credits/s - Text/Image to Video - Output seconds × 16
1080P: 32 credits/s - Text/Image to Video - Output seconds × 32
USD estimates use $0.005/credit with the best annual plan. Final billing follows the selected Wan model, resolution, duration, and input type.
Core request fields
Use model-specific payloads for prompt, source media, resolution, aspect ratio, duration, callback, and generation options.
{
"model": "wan/3-0-video",
"input": {
"prompt": "Under the moonlight, a little cat is running on the roof. In the distance, the neon lights are flashing, giving a cinematic feel. The camera movement is smooth.",
"resolution": "480P",
"aspect_ratio": "adaptive",
"duration": 5,
"audio": true
}
}Use Wan 3.0 Video for generation
The playground, request sample, request fields, and pricing on this page follow the selected model type.
View detailed API docsOpen the full API documentation for endpoints, authentication, task polling, and payload details. /models/wan.md
promptstringText prompt, supporting both Chinese and English. Up to 20,000 characters; excess characters will be truncated automatically. Required for text-to-video generation; for other modes, it is recommended to provide it together with media. In reference mode, use Image1/Video1/Audio1 to reference the provided media.first_frame_urlstringURL of the first-frame image. Up to 1 image, used strictly as the first frame of the video. Used for first-frame-to-video / first-and-last-frame-to-video generation. Cannot be provided together with `reference_*_urls`.last_frame_urlstringURL of the last-frame image. Used with first_frame_url for first-and-last-frame generation; the same image limits apply.reference_image_urlsarrayReference images for the all-purpose reference mode, with up to 10 images. Correspond to Image1, Image2, … in the prompt according to array order. Specifications are the same as `first_frame_url`. Cannot be provided together with the first-frame/last-frame parameters.reference_video_urlsarrayReference videos for the all-purpose reference mode, with up to 5 clips. Each clip must be 1–15 seconds, with a total duration ≤ 15 seconds. Correspond to Video1, Video2, … according to array order.reference_audio_urlsarrayReference audio for the all-purpose reference mode, with up to 5 clips. Each clip must be 1–15 seconds, with a total duration ≤ 15 seconds. Correspond to Audio1, Audio2, … according to array order. Formats: wav, mp3; ≤ 15MB. Audio should not be used alone as the only media input; pairing it with an image or video is still recommended.reference_file_urlsarrayFile-to-video generation. Up to 1 file. Cannot be provided together with `reference_link_urls`, or with the first-frame/last-frame parameters.reference_link_urlsarrayLink-to-video generation. Up to 1 publicly accessible webpage that does not require login. Cannot be provided together with `reference_file_urls`, or with the first-frame/last-frame parameters.resolutionenumOutput resolution. Default: **1080P**. (480P, 720P, 1080P)aspect_ratioenumOutput aspect ratio. `adaptive` (default) automatically selects the ratio based on the input media and intent. (adaptive, 16:9, 4:3, 1:1, 3:4, 9:16)durationnumberOutput video duration in seconds. Default: 5. Without video input, the range is [2, 30]. With reference videos: input video duration + output duration ≤ 30. Pass `-1` to use an intelligent duration determined by the model. This studio requires a fixed duration of 2–30 seconds so the price can be calculated before submission; automatic duration (-1) is disabled.audiobooleanWhether the output video includes an audio track. Default: true.seednumberRandom seed used to reproduce results. If omitted, a random seed will be used.What Wan API adds to your video workflow
The page follows the same API-first structure as the reference: test a Wan model, understand the fields, then move into integration.
Text-to-video generation
Turn prompts into cinematic clips with controllable resolution, aspect ratio, duration, negative prompt, seed, and prompt extension options.
Image-to-video motion
Animate still images into short videos while preserving subject context, composition, and visual style.
Video editing workflows
Use source clips and reference images to change outfits, objects, style, or motion while keeping the surrounding scene coherent.
Reference-to-video control
Combine reference images, videos, first frames, and voice inputs to guide characters, motion, timing, and scene layout.
From Wan playground test to production request
A compact path for teams that want to validate Wan output before connecting generation to an app or content pipeline.
1. Choose a Wan mode
Select text-to-video, image-to-video, video edit, reference-to-video, or an older Wan workflow that matches your source input.
2. Submit generation
Call the API with your account key, model ID, prompt, media URLs, resolution, duration, aspect ratio, and callback settings.
3. Poll and use
Track the task until it succeeds, then retrieve the generated video URL for your app, campaign, or automation.
What you can create with Wan API
Use the API when your product needs repeatable AI video output across several input styles, not just a one-off generation.
Built for real Wan API workflows
Account-gated execution
Users sign in, submit jobs, and consume credits through the existing SdanceAI generation flow.
Flexible source media
Wan workflows can accept prompt-only requests or media-driven requests with images, videos, first frames, references, and audio where supported.
Resolution-aware cost
Choose 720p for iteration and 1080p when a selected concept is ready for a sharper final render.
Wan API questions
What is Wan API best for?
It is best for teams that need several AI video workflows in one integration, including text-to-video, image-to-video, video editing, video-to-video, animation, and reference-guided generation.
Which Wan models are available on this page?
The page follows the configured Wan family, including Wan 2.7 text-to-video, image-to-video, video edit, reference-to-video, Wan 2.6 workflows, Wan 2.5 workflows, and Wan 2.2 animation modes.
What is the difference between text-to-video and image-to-video?
Text-to-video starts from a prompt only. Image-to-video uses a source image so the generated clip can preserve the subject, framing, or visual style from the input.
When should I use Wan 2.7 Reference to Video?
Use Reference to Video when you need tighter control from reference images, reference videos, first frames, or voice input rather than relying only on a written prompt.
Does Wan API support 1080p output?
Wan 2.7 entries on this page include 720p and 1080p pricing rows. Choose the resolution that matches your quality and cost target.
Can I edit an existing video?
Yes. Use Wan 2.7 Video Edit or another video-input workflow when you want to modify a source clip with prompts and references.
Can I use negative prompts?
Supported Wan request schemas include negative prompt fields for reducing blur, distortion, low quality output, and other unwanted details.
Where can I test Wan before integrating?
Use the playground on this page to test the model, prompt, media URLs, resolution, duration, and API payload behavior before moving into production.
How should I manage cost?
Start with lower resolution and shorter clips for prompt exploration, then switch to 1080p or longer durations only after the direction is validated.
Can I use Wan API for commercial projects?
This page is configured for production video workflows. For commercial use, review your account plan, credit balance, model availability, and applicable content policy requirements.
Turn Wan into your video workflow
Open the generator, test a Wan prompt or reference workflow, then use the API docs when you are ready to connect Wan to production.