Skip to main content
Alibaba logo

Wan 3.0

ReadyVideoby Alibaba

Overview

About this model

Wan 3.0 generates video from text prompts, served on EcoHash.

Specifications

Model details

Provider
Alibaba
Modality
Video

Modalities: text, image, audio, video → video

API

Call it in code

One OpenAI-compatible API. Swap the model id and you're done.

import time

import requests

BASE_URL = "https://api.ecohash.com/v1"
HEADERS = {"Authorization": "Bearer YOUR_API_KEY"}

job = requests.post(
    f"{BASE_URL}/video/generations",
    headers=HEADERS,
    json={
        "model": "wan3.0-video",
        "prompt": "A sunset over mountains, cinematic",
        # Self-hosted engines size the clip from these fields.
        # Provider-served engines take "resolution" and "duration" instead.
        "num_frames": 49,
        "fps": 16,
        "width": 720,
        "height": 480,
    },
).json()

while True:
    status = requests.get(
        f"{BASE_URL}/video/jobs/{job['id']}", headers=HEADERS
    ).json()
    if status["status"] in ("completed", "failed"):
        break
    time.sleep(5)

video_url = status.get("url")  # pre-signed, valid 24h

Start building

Grab an API key and call this model in minutes.