HappyHorse 1.0 turns a written description, one starting image or a group of reference images into a short video, 3 to 15 seconds long, in HD or Full HD. It suits social clips and bringing a still picture to life, with seven shapes from wide 21:9 to tall 9:21. You choose the opening frame but not the closing one.
Wan 3.0 Prime
by AlibabaReleased 27 August 2026
Wan 3.0 Prime is the quick version of full Wan 3.0. It turns a written description, or a first-frame image plus a description, into a video with sound, across the same range of low resolution to Full HD and 2 to 30 seconds. Use it to try ideas and refine your wording fast. It leaves out the reference-guided mode of full Wan 3.0, so move there when the final shot must follow reference material.
What it costs
You pay for what each request uses. No subscription, no minimum.
One second of video, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Second of video | 22,63 DA |
per second of video returned
- When you pay
- After the answer, from your balance. Nothing is held.
- Why it varies
- The length, the sound and the resolution.
- After each one
- The exact charge shows on the request.
Where your request runs
One company runs this model. OpenDunes sends every request to it.
In 720p: 46,60 DA a second with sound. In 1080p: 93,19 DA a second with sound.
You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.
Call it in code
Send the job, then ask for it until it is ready.
import os, time, requests
BASE = "https://opendunes.com/v1"
KEY = os.environ["OPENDUNES_API_KEY"]
H = {"Authorization": f"Bearer {KEY}"}
job = requests.post(f"{BASE}/videos", headers=H, json={
"model": "alibaba/wan-3.0-prime",
"prompt": "Sunrise over the dunes of Taghit, slow pan",
"duration": 8, "resolution": "1080p",
"generate_audio": False,
}).json()
while job["status"] not in ("completed", "failed"):
time.sleep(10)
job = requests.get(job["polling_url"], headers=H).json()
print(f"{BASE}/videos/{job['id']}/content")Runs this request once on your balance.
Parameters you can send
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_pseedpresence_penaltyStructured output
Get JSON you can parse instead of prose.
response_formatQuestions about Wan 3.0 Prime
How much does Wan 3.0 Prime cost in dinars?
About 22,63 DA per second of video.
Is Wan 3.0 Prime free? Can I try it?
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
What is Wan 3.0 Prime best for?
Wan 3.0 Prime is the quick version of full Wan 3.0. It turns a written description, or a first-frame image plus a description, into a video with sound, across the same range of low resolution to Full HD and 2 to 30 seconds. Use it to try ideas and refine your wording fast. It leaves out the reference-guided mode of full Wan 3.0, so move there when the final shot must follow reference material.
Wan 3.0 Prime or Wan 3.0?
Wan 3.0 costs 5,99 DA less for the same second of video.
How do I pay for Wan 3.0 Prime without an international card?
Deposit dinars with your Edahabia or CIB card. Every model, Wan 3.0 Prime included, is paid from that balance. No foreign card, no conversion.
Does Wan 3.0 Prime work in Arabic, French or Darja?
Alibaba names no languages for Wan 3.0 Prime. Arabic, French and Darja: not stated.
How long can a clip be, and does it make sound?
2 to 30 seconds. With sound.
Can it animate my photo, or make a vertical video?
From a first and a last frame. Vertical 9:16: yes.
Who makes Wan 3.0 Prime, and when was it released?
Alibaba. Released 27 August 2026.
Other Alibaba models, priced in dinars
See all Alibaba modelsHappyHorse 1.1 turns a written description, one starting image or a group of reference images into a video that lasts 3 to 15 seconds, in HD or Full HD, in seven shapes from 21:9 to 9:21. It is made for social clips and bringing a still picture to life, and it follows your description more closely than 1.0, with smoother motion and characters who stay recognisable from frame to frame.
Wan 2.6 makes video up to Full HD, 24 frames a second, from text, images, reference clips or audio, with sound effects, music and lip-sync created in the same pass. Its reference mode lets you carry a character's look and voice across to new scenes, and it can build a multi-shot story from a short description.
Wan 2.7 makes video with sound from a written description, a starting image with an optional closing image, or several reference images that shape the look of the scene. Clips run 2 to 10 seconds, in HD or Full HD. Its draw is control over both ends of a shot, which Wan 2.6 lacks.