Wan 3.0 Prime API provides access to Alibaba Cloud's all-in-one video model. It offers general, first-and-last-frame, and file or webpage generation. General generation accepts prompts with optional image, video, and audio references, while frame generation requires a first frame and allows an optional last frame. One asynchronous endpoint creates 2–30 second videos at 480P, 720P, or 1080P with optional output audio.
Generate from a prompt alone or add image, video, and audio references
General / reference lane
Use a prompt alone or add references, documents, or webpages
Frame lane
The first frame is required and the last frame is optional
Frame inputs cannot be mixed with reference images, videos, audio, files, or webpages in one request.
Enter a prompt or add at least one reference image, video, or audio item.
Upload up to 5 WAV/MP3 files, each 1–15 seconds and 15 MB; total duration up to 15 seconds.
WAV, MP3 (max 15MB, up to 5 audios, duration ≤ 15s)
0/5 audio items added. Uploaded files and URLs share the same limit.
Choose auto duration (-1) or an integer from 2 to 30 seconds. With reference video, input plus output duration cannot exceed 30 seconds.
1080P is the default and highest-priced resolution tier.
Generate an audio track by default. Turning it off does not change the price.
Add the provider watermark to the generated video.
Stored on the APIMart CDN
Transparent pricing with no hidden fees. Pay only for what you use.
| Variant | Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|---|
wan3.0-video-prime | 480P | 0.5143Credits(~$0.0514)/sec | 0.4886Credits(~$0.0489)/sec | 0.4629Credits(~$0.0463)/sec | 0.6429Credits(~$0.0643)/sec | 20% |
| 720P | 1.0286Credits(~$0.1029)/sec | 0.9771Credits(~$0.0977)/sec | 0.9257Credits(~$0.0926)/sec | 1.2857Credits(~$0.1286)/sec | 20% | |
| 1080P | 2.0571Credits(~$0.2057)/sec | 1.9543Credits(~$0.1954)/sec | 1.8514Credits(~$0.1851)/sec | 2.5714Credits(~$0.2571)/sec | 20% |
* Actual costs are subject to final output.
* Total cost = (reference video duration + generated video duration) × the selected model and resolution’s original per-second price × its actual payable percentage ÷ 100.
The Wan 3.0 Prime API supports general, first-and-last-frame, and file or webpage generation. Use a prompt alone or add image, video, and audio references; frame generation requires a first frame and keeps the last optional. Choose 2–30 seconds at 480P, 720P, or 1080P.
50K+
Active Users
99.9%
Uptime
2x
Faster
—
Cost Savings
Three entries, two material families, output controls, and reliable delivery
Production workflows across general, first-and-last-frame, and file or webpage generation
Submit and retrieve a video task in three clear steps
In the Wan 3.0 Prime API, choose general generation for prompts with optional references, frame generation with a required first and optional last frame, or file and webpage generation.
Configure the Wan 3.0 Prime API for 2–30 seconds at 480P, 720P, or 1080P, plus aspect ratio, output audio, watermark, and seed controls.
Submit the Wan 3.0 Prime API request and poll its task ID. When the task finishes, retrieve the video from APIMart storage. Stored results remain available after the upstream link expires.
Common questions about inputs, pricing, and task behavior
The Wan 3.0 Prime API provides APIMart access to Alibaba Cloud's all-in-one AI video model, identified as wan3.0-video-prime. Its interface has three entries and separates reference from first-and-last-frame materials.
The Wan 3.0 Prime API has three entries: general generation for prompts with optional image, video, and audio references; first-and-last-frame generation with a required first and optional last frame; and file or webpage generation.
The Wan 3.0 Prime API supports videos of 2–30 whole seconds. With reference videos, their total duration plus requested output must remain within 30 seconds. Set duration to -1 to let the model choose the output length automatically.
Wan 3.0 Prime uses its own live original per-second price and actual payable percentage for the selected resolution. Cost = (reference video duration + generated video duration) × original per-second price × payable percentage ÷ 100. Automatic duration shows an estimated range. See this page’s live pricing table for this model’s prices and discounts.
The Wan 3.0 Prime API defaults to 1080P, the highest-priced tier. Pass 480P or 720P when either better matches your quality and cost requirements.
No. The Wan 3.0 Prime API enables output audio by default; setting audio to false keeps the same per-second price. Reference audio separately guides generation.
No. The Wan 3.0 Prime API treats first and last frames as one family, while reference images, videos, audio, files, and links form another. Requests cannot mix them.
The Wan 3.0 Prime API supports Word, Excel, PowerPoint, PDF, TXT, Keynote, Pages, Numbers, and Markdown files up to 100MB and 50 pages, plus public webpages without login.
Sign up for APIMart, open the API Keys page in your dashboard and create a key. The same key calls the Alibaba Wan 3.0 Prime API and every other model on the platform, with pay-as-you-go billing and no subscription. Prices on this page are Gold member prices, 20% off; Platinum and Diamond members save up to 28%.
Send a generation request with the model set to wan3.0-video-prime and your prompt. The Wan 3.0 Prime API runs as an asynchronous task: it returns a task id right away, and you poll that task until the result is ready. Full parameters and code examples are in the APIMart docs (docs.apimart.ai).
Explore more models in the same category.

Gemini Omni 1.1 Flash
Gemini Omni 1.1 Flash is a multimodal video model officially released by Google that supports rapid generation, natural language editing, and cinematic-quality visual control. This page connects to the official service through APIMart’s unified video API and uses separate pricing and task logs.

MiniMax H3 Max
MiniMax H3 Max generates video from text and images at 480P, 768P or 1080P with 5–15 second clips, first/last frames, multimodal references and synced audio.

Grok Imagine Video
Grok Imagine Video 1.5 is xAI's official video model for text-to-video and image-to-video, animating still images from reference image URLs with high visual fidelity.

Wan 3.0 Video
Wan 3.0 is Alibaba's all-in-one video model for text-to-video, first-frame, first-and-last-frame and multimodal reference generation. It accepts image, video, audio and document references and outputs 2–30 second videos at 480P, 720P or 1080P.