Wan 3.0 API (Wan 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 | 480P | 0.3288Credits(~$0.0329)/sec | 0.3124Credits(~$0.0312)/sec | 0.2959Credits(~$0.0296)/sec | 0.411Credits(~$0.0411)/sec | 20% |
| 720P | 0.6575Credits(~$0.0658)/sec | 0.6246Credits(~$0.0625)/sec | 0.5918Credits(~$0.0592)/sec | 0.8219Credits(~$0.0822)/sec | 20% | |
| 1080P | 1.315Credits(~$0.1315)/sec | 1.2493Credits(~$0.1249)/sec | 1.1835Credits(~$0.1184)/sec | 1.6438Credits(~$0.1644)/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 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 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 API for 2–30 seconds at 480P, 720P, or 1080P, plus aspect ratio, output audio, watermark, and seed controls.
Submit the Wan 3.0 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 API provides APIMart access to Alibaba Cloud's all-in-one AI video model, identified as wan3.0-video. Its interface has three entries and separates reference from first-and-last-frame materials.
The Wan 3.0 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 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 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 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 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 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 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 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 and your prompt. The Wan 3.0 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.

Seedance 2.5
Seedance 2.5 is ByteDance's audio-video model for text-to-video, multimodal reference, editing, extension and first-last-frame control. Generate up to 30 seconds in one job with up to 30 images, 10 videos and 10 audio clips as references, at up to 1080p.

Flux 3 Video
FLUX 3 Video by Black Forest Labs supports text-to-video, image-to-video with ordered keyframes and video continuation. It generates 5–20 second HD or FHD clips with synchronized audio in seven aspect ratios.

MiniMax H3
MiniMax H3 is MiniMax's video model for text-to-video, image-to-video with first and last frames, and multimodal reference-to-video using images, videos and audio. It outputs 4–15 second clips at 2K or 768P with an audio track.

Gemini Omni Flash Preview
gemini-omni-flash-preview is a multimodal video generation and editing model launched by Google.