Wan 3.0 Video Prime
wan / 3-0-video-prime

Wan 3.0 Video Prime is a high-speed AI video generation model from Alibaba's Wan model family. It delivers core capabilities aligned with Wan 3.0 Video while offering faster end-to-end generation, with multimodal references across audio, image, text, and video and video generation up to 30 seconds.

Pricing: 12.2 credits/s for 480P ($0.0612/s), 25.2 credits/s for 720P ($0.126/s), and 50.4 credits/s for 1080P ($0.252/s), all 10% below official pricing. Note: The billing rule is (input video duration + output video duration) × unit price. High-tier top-ups (+10% bonus) provide an additional 10% reduction in effective pricing.
Input
Start Frame
End Frame

Click to upload or drag and drop images. Single side: [240, 8000] px; aspect ratio ≤ 8:1

Images: JPEG/JPG/PNG/WebP/BMP, Max 20MB

Text prompt used to describe the desired video content. Supports both Chinese and English, with a maximum length of 20,000 characters.

0/20000

Click to upload or drag and drop

Supported formats: JPEG, PNG, WEBP, BMP Maximum file size: 20MB; Maximum files: 10

Maximum 10 images. Mapped in array order to Image1, Image2, ... in the prompt. Specifications are the same as first_frame_url. Cannot be used together with first frame / last frame.

Click to upload or drag and drop

Supported formats: MP4, QUICKTIME Maximum file size: 100MB; Maximum files: 5

Maximum 5 clips. Each clip: 1–15s; total combined duration ≤ 15s. Mapped in array order to Video1, Video2, ... in the prompt. Formats: mp4, mov. Single side: [240, 4096] px; aspect ratio ≤ 8:1; file size per clip ≤ 100MB. Additionally, on the output side: total input video duration + output duration (duration parameter) must not exceed 30 seconds.

Click to upload or drag and drop

Supported formats: MPEG, WAV, X-WAV Maximum file size: 15MB; Maximum files: 5

Maximum 5 clips. Each clip: 1–15s; total combined duration ≤ 15s. Mapped in array order to Audio1, Audio2, ... in the prompt. Formats: wav, mp3; file size ≤ 15MB per clip. When not used as the sole media input, it is still recommended to pair with images or videos.

Text
0 / 1
No items yet. Click Add to start.

Maximum 1 publicly accessible webpage (no login required). Cannot be used together with reference_file_urls, nor with first frame / last frame.

Text
0 / 1
No items yet. Click Add to start.

Maximum 1 file. Cannot be used together with reference_link_urls, nor with first frame / last frame. Supported formats: docx, doc, xlsx, xls, pptx, ppt, pdf, txt, key, pages, numbers, md. File size ≤ 100MB. For file types such as pdf, docx, ppt, key, pages, etc., page count ≤ 50 pages.

Preset resolution levels for video generation.

Aspect ratio for generated video. "Adaptive" auto-recommends a ratio based on input media proportions and intent.

Duration of the generated video, in seconds. When no video input is provided, the value must be an integer in the range of [2, 30]. When a video input is provided, the total duration of the input video plus the output video must not exceed 30 seconds. Passing -1 enables smart duration mode, where the model automatically recommends an appropriate duration based on the input.

Whether the output video includes audio. true (default): Includes audio; false: No audio track.

Random seed for result reproducibility.0<=x<= 2147483647

A configurable parameter. Defaults to true in the Playground.

There is no guarantee that everything can be filtered out; if you are not satisfied with the results, you will need to make your own arrangements.
Output
output typevideo
Examples

Explore different use cases and parameter configurations

README

Complete guide to using wan/3-0-video-prime

Wan 3.0 Video Prime API for Fast Multimodal Video Generation

Original image
FeatureWan 3.0 Video PrimeWan 3.0 Video
Video Generation✓✓
Generation SpeedFasterStandard
Four-Modal ReferenceAudio, Image, Text, VideoAudio, Image, Text, Video
Maximum DurationUp to 30 secondsUp to 30 seconds
Audio-Visual Generation✓✓
Core Model CapabilitiesAligned with Wan 3.0 VideoStandard
Best ForFast API workflows, SaaS & high-volume generationStandard video generation
Kie.ai Model IDwan/3-0-video-primewan/3-0-video
Price per Second (480P / 720P / 1080P)12.2 / 25.2 / 50.4 credits ($0.0612 / $0.126 / $0.252)8 / 16 / 32 credits ($0.04 / $0.08 / $0.16)
When to ChooseSomeone is waiting on the result and speed matters mostBatch or background jobs where cost matters more than speed

Wan 3.0 Video Prime API provides access to the high-speed version of Wan 3.0 Video. It offers core capabilities aligned with standard Wan 3.0 Video while significantly improving end-to-end generation speed.

Main difference is generation speed. Wan 3.0 Video Prime supports core capabilities aligned with Wan 3.0 Video, including four-modal references and videos up to 30 seconds, while offering significantly faster end-to-end generation.

Yes. Wan 3.0 Video Prime is optimized for faster video generation while retaining core capabilities of standard Wan 3.0 Video, making it a strong option for production apps and high-volume workflows.

Wan 3.0 Video Prime supports four-modal references across audio, image, text, and video. Developers can combine these inputs to guide characters, scenes, motion, sound, and other creative details.

Reference mode takes up to 10 images (JPEG, PNG, BMP or WebP, each side 240–8,000 px, up to 20MB), up to 5 videos (MP4 or MOV, 1–15 seconds each and 15 seconds combined, up to 100MB each) and up to 5 audio clips (WAV or MP3, 1–15 seconds each and 15 seconds combined, up to 15MB), referred to in the prompt as Image1, Video1 and Audio1. Output is 480P, 720P or 1080P (default 1080P), with an aspect ratio of adaptive (the default), 16:9, 4:3, 1:1, 3:4 or 9:16.

Wan 3.0 Video Prime supports video generation up to 30 seconds, giving developers more room for longer scenes, marketing content, storytelling, and complete video sequences.

Create a Kie AI account, get your API key, and select Wan3.0-Video-Prime API. Follow the API documentation to configure inputs, send generation requests, and integrate Wan video generation into your application.

Wan 3.0 Video Prime API costs 12.2 credits/s at 480P ($0.0612/s), 25.2 credits/s at 720P ($0.126/s) and 50.4 credits/s at 1080P ($0.252/s) on Kie AI, 10% below official pricing. The standard Wan 3.0 Video costs 8, 16 and 32 credits/s ($0.04, $0.08 and $0.16/s) at the same resolutions. Billed seconds are the input video duration plus the output video duration, so a 10-second 1080P video without a reference video costs 504 credits ($2.52). Prices may be updated; the pricing card at the top of this page always shows the current rate.

No. Kie AI has no subscription or unlimited plan: credits are pay-as-you-go and never expire, and each Wan 3.0 Video Prime video is billed per second at the rates above. By default an account can submit up to 20 new generation requests every 10 seconds, which typically allows 100+ tasks running at the same time; requests above that limit return code 429 and are not queued.

Alibaba provides Wan 3.0 through Alibaba Cloud Model Studio. As of November 2026, Alibaba's official Wan-Video GitHub and Wan-AI Hugging Face pages publish open weights for Wan 2.1 and Wan 2.2 under Apache 2.0, but none for Wan 3.0, so there are no official Wan 3.0 weights to run locally. Kie AI offers Wan 3.0 Video Prime as a hosted API; if you need an open-weight model, the Wan 2.2 API runs the open-source A14B models.