Wan 3.0 Video Pro Spicy brings the Wan 3.0 contract - 2-30 second clips with native audio, first/last-frame control, and rich reference materials - to 1080P, 2K, and 4K output on a relaxed-moderation route for adult-oriented creative work.
Wan 3.0 Pro Spicy T2V on APIPod renders 2 to 30 second clips with native audio at 1080P, 2K, or 4K on a relaxed-moderation upstream built for mature-theme creative work. Set prompt_extend to false to keep generation close to your literal prompt.
Wan 3.0 Pro Spicy I2V on APIPod animates a first frame (optionally with a last frame) into a 2 to 30 second clip with native audio at 1080P, 2K, or 4K on a relaxed-moderation upstream.
Wan 3.0 Pro Spicy R2V on APIPod generates 2 to 30 second clips guided by reference images, videos, audios, and a file or link, with native audio at 1080P, 2K, or 4K on a relaxed-moderation upstream. Reference video seconds are billed together with output seconds.
18+Wan 3.0 Pro Spicy API · T2V · I2V · R2V
Wan 3.0 Pro Spicy renders Alibaba’s Wan 3.0 video model at 1080P, 2K or 4K with relaxed moderation for adult (18+) work: 2–30 second clips with native audio, from text, keyframes or up to 20 references. Made for the big screen — and for re-cutting one master into every format you ship.
Pixel plate
Drawn to scale: one 4K frame holds four 1080P frames. Pick a print to see what you are paying for, then switch on the vertical cut to see how much a widescreen master still gives a 9:16 feed.
Estimated cost
$4.50
(0 s reference + 15 s output) × $0.30/s
Frame sizes are 16:9 references; the output size follows the aspect ratio you request. Prices are APIPod’s live list prices for the Wan 3.0 Pro Spicy models. Failed tasks are refunded automatically.
Delivery
Resolution is a delivery decision. Pay for 4K when the screen, the crop or the client needs it — and not before.
1080P
Social posts, ads and in-app video. Pro 1080P is the entry point of the tier; for cheaper drafts at the same size, stay on Wan 3.0 Spicy.
2K
Landing-page heroes, YouTube and laptop screens, where 1080P starts to look soft at full width.
4K
Living-room screens, events and festival projection — and the master you crop into vertical, square and close-up cuts.
Edit decision list
Pick the model by what you bring to set: a prompt, a pair of keyframes or a box of references. All three take resolution 1080P, 2K or 4K, plus the same duration, aspect_ratio, generate_audio and prompt_extend fields.
| Model ID | Input | Limits | Use it for |
|---|---|---|---|
| wan3.0-pro-spicy-t2v | Prompt only | prompt up to 20,000 characters | Large-format scenes written from scratch. |
| wan3.0-pro-spicy-i2v | Prompt + first frame, optional last frame | image_urls: 1–2 | Taking a locked look or product still to the big screen. |
| wan3.0-pro-spicy-r2v | Prompt + references named in the prompt | 10 images · 5 videos · 5 audio · 1 file · 1 link | Consistent characters, wardrobe and voices in 4K. |
Spec sheet
Pro Spicy is the Spicy route rendered for large screens. Everything except resolution and price carries over.
| Spec | Wan 3.0 | Wan 3.0 Spicy | Wan 3.0 Pro Spicy |
|---|---|---|---|
| Moderation | Standard upstream review | Relaxed, for adult (18+) work | Relaxed, for adult (18+) work |
| Resolution | 480P · 720P · 1080P | 480P · 720P · 1080P | 1080P · 2K · 4K |
| Clip length | 2–30 s, or -1 for smart length | 2–30 s, or -1 for smart length | 2–30 s, or -1 for smart length |
| Audio | Native, generated with the picture | Native, generated with the picture | Native, generated with the picture |
| References (R2V) | 10 images · 5 videos · 5 audio · file · link | 10 images · 5 videos · 5 audio · file · link | 10 images · 5 videos · 5 audio · file · link |
| prompt_extend | Not available | Supported — set false for literal prompts | Supported — set false for literal prompts |
| Keyframes (I2V) | image_urls: first + optional last | image_urls: first + optional last | image_urls only: first + optional last |
| Availability | All APIPod regions | Not in mainland China, Hong Kong or Macau | Not in mainland China, Hong Kong or Macau |
Call sheet
The same asynchronous /v1/videos/generations endpoint as every video model on APIPod. This example casts a performer video and two stills into a 15-second 4K scene; the reference video’s seconds are billed alongside the output.
curl https://api.apipod.ai/v1/videos/generations \
-H "Authorization: Bearer $APIPOD_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan3.0-pro-spicy-r2v",
"prompt": "Video 1 walks into a candlelit study wearing the coat from Image 1 and sets Image 2 on the desk. Slow dolly-in, 50mm, deep shadows, rain against tall windows.",
"reference_images": ["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260408/sjuytr/wan-r2v-object-girl.jpg", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260129/qpzxps/wan-r2v-object4.png"],
"reference_videos": ["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260129/qigswt/wan-r2v-role2.mp4"],
"resolution": "4K",
"aspect_ratio": "16:9",
"duration": 15
}'
# → { "code": 200, "data": { "task_id": "…", "status": "pending" } }
curl https://api.apipod.ai/v1/videos/status/$TASK_ID \
-H "Authorization: Bearer $APIPOD_API_KEY"Shot list
Wide vistas, fine texture and low light — the detail 4K is for. Starting points for adult-oriented genre work; copy one and recast it.
Epic warT2V · 4K · 16:9 · 20 s
Dawn over a frozen river; two cavalry lines charge across the ice from opposite banks. An ultra-wide crane shot descends into the clash — hooves breaking the ice, steam from the horses’ breath, banners torn by wind. Steel-blue grade, roaring score.
Neo-noirR2V · 2K · 12 s
Image 1 as the detective in a rain-soaked trench coat under a single sodium streetlamp; a macro pass over water beading on leather, then a rack focus to her eyes. She says: “Everyone in this city owes somebody.” Deep blacks, amber highlights.
Gothic romanceT2V · 4K · 16:9 · 15 s
A candlelit ballroom in a ruined palace; a woman in a black lace gown and a masked stranger circle each other, close enough to feel each other breathe. Slow 85mm orbit, wax dripping, dust in the candlelight. Crimson and gold, string quartet.
ChaseT2V · 4K · 25 s · one take
Aerial chase over red dunes at golden hour; a dust-caked motorcycle outruns a wall of sandstorm. The drone drops from 300 metres to tyre height in one continuous move, sand spraying across the lens. Engine roar, wind, distant thunder.
Questions
Wan 3.0 Pro Spicy is the high-resolution tier of Wan 3.0 Spicy on APIPod: the same relaxed-moderation Wan 3.0 video model, rendered at 1080P, 2K or 4K for adult (18+) work. It covers text-to-video, keyframe-to-video and reference-to-video in 2–30 second clips with native audio, through three models: wan3.0-pro-spicy-t2v, wan3.0-pro-spicy-i2v and wan3.0-pro-spicy-r2v.
Resolution tiers and price. Wan 3.0 Spicy renders 480P, 720P and 1080P; Pro Spicy renders 1080P, 2K and 4K. Modes, reference limits, clip length, audio and moderation are identical. One request detail differs: Pro Spicy takes keyframes only through image_urls (first frame, optional last frame).
Yes. Set resolution to 4K and you get a 4K-class master — for a 16:9 frame that is about 3840 × 2160, four times the pixels of 1080P. The exact frame size follows the aspect ratio you request.
Yes. A centred 9:16 crop of a 16:9 4K frame is about 1215 × 2160 — still wider than a native 1080 × 1920 vertical render — so one generation gives you a widescreen master and a sharp vertical cut. From a 1080P master the same crop is only about 608 × 1080.
Per second: the resolution’s rate × (reference video seconds + output seconds). 4K carries the highest rate in the tier, so lock the shot on Wan 3.0 Spicy or at 1080P first. Audio on or off costs the same, and failed tasks are refunded automatically.
Any whole number of seconds from 2 to 30 in a single pass, at every resolution including 4K. Pass duration -1 to let the model choose; it is reserved at 30 seconds and settled at the actual length.
Everywhere APIPod operates except mainland China, Hong Kong and Macau, where Spicy pages are unavailable and API requests are rejected. Use is limited to adults aged 18 and over.
Create a key, call wan3.0-pro-spicy-t2v and screen your first 4K take. Same API and the same key as every other model on APIPod.
Get an API key