What is Wan 3.0 Prime (wan3.0-video-prime)?

Wan 3.0 Prime is a model in Alibaba's Wan 3.0 video series. On APIMart its ID is wan3.0-video-prime. It creates 2 to 30 second videos at up to 1080P from text, first and last frames, or image, video, audio, document and webpage references, with audio on by default.

What is the difference between Wan 3.0 Prime and Wan 3.0?

Both models accept exactly the same parameters, so you switch by changing only the model field. Wan 3.0 Prime is billed at its own per-second price, which is currently higher than wan3.0-video at every resolution. Alibaba has not published a quality or speed comparison, and APIMart does not guarantee one, so test both with your own prompts.

Should I use Wan 3.0 Prime or Wan 3.0?

Start with Wan 3.0 (wan3.0-video) for most work, because it costs less per second. Try Wan 3.0 Prime when you want to compare a second Wan 3.0 model on the same request. Some providers describe Prime as a faster-delivery tier; check the results and generation times on your own workload before switching.

What parameters does the Wan 3.0 Prime API support?

model and prompt are required unless you send media. Optional fields: duration (2–30 or -1, default 5), resolution (480P, 720P or 1080P, default 1080P), size (adaptive, 16:9, 4:3, 1:1, 3:4 or 9:16), audio (default true), seed, watermark, nsfw_check, generation_type, image_urls, image_with_roles, video_urls, audio_urls or audio_url, and file_url or link_url.

Can Wan 3.0 Prime do first and last frame image to video?

Yes. Send one image in image_urls for the first frame, or two for first and last frames, or label them with image_with_roles. With images only and no other media, the first image is the first frame and the second is the last frame.

Can I mix frames and reference inputs in one request?

No. Frame inputs (first_frame, last_frame) and reference inputs (images, videos, audio, file_url and link_url) cannot be combined. A mixed request returns HTTP 400 before a task is created and is not billed. Use generation_type to tell the model how to treat bare image_urls.

How long can a Wan 3.0 Prime video be?

Set duration from 2 to 30 seconds, or -1 to let the model decide; the default is 5. When the request includes a reference video, the reference and the generated video together stay within 30 seconds.

How long does a Wan 3.0 Prime task take?

Generation usually takes a few minutes and longer for long or high-resolution clips. Poll GET /v1/tasks/{task_id} every 5–10 seconds until status is completed, then read data.result.videos[0].url[0] and save the file to your own storage.

How do I call the Wan 3.0 Prime API?

POST to /v1/videos/generations with model wan3.0-video-prime and your prompt, duration, resolution and size, then read the task ID from data[0].task_id. The request format and the docs page are the same as for Wan 3.0.

How much does the Wan 3.0 Prime API cost per second?

Wan 3.0 Prime is billed per second of video, and the rate depends on resolution. Audio does not change the price. See the pricing table on this page; Gold members save 20%, and Platinum and Diamond members save up to 28%.

Is Wan 3.0 Prime free or open source?

No. APIMart has no free quota for Wan 3.0 Prime; you pay for each completed task. Alibaba offers Wan 3.0 Prime as a hosted API and has not released its weights.

How do I get a Wan 3.0 Prime API key?

Sign up for APIMart, add balance and create a key on the API Keys page. Send it as Authorization: Bearer . The same key works for every Wan model and the rest of the APIMart catalog.

Back to models

Video

Wan 3.0 Prime API

Wan 3.0 Prime API (wan3.0-video-prime) on APIMart is the Prime model in Alibaba's Wan 3.0 series. It accepts exactly the same parameters as wan3.0-video: a prompt, first and last frames, or image, video, audio, document and webpage references, for 2 to 30 second video at 480P, 720P or 1080P with audio on by default. It has its own model ID and per-second price.

Same Inputs as Wan 3.0Up to 30 Seconds480P / 720P / 1080POwn Model and Price

Get API Key API Docs

Service Highlights

Official Discounts
Pay-as-you-go
Fast & Low Latency

Input

Model

Generation Mode

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.

Prompt*118/20000

Enter a prompt or add at least one reference image, video, or audio item.

Optional Reference MaterialsImages, videos, and audio are all optional. Reference materials cannot be combined with first or last frames.

Reference Images

0/10

Reference Videos

0/5 · 0.0/15s

Reference Audio

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)

Audio URLs

0/5 audio items added. Uploaded files and URLs share the same limit.

Content Moderation

Duration

Auto duration (-1)

Choose auto duration (-1) or an integer from 2 to 30 seconds. With reference video, input plus output duration cannot exceed 30 seconds.

Resolution

1080P is the default and highest-priced resolution tier.

Aspect Ratio

Seed

Generate Audio

Generate an audio track by default. Turning it off does not change the price.