Models
HappyHorse 1.0 Reference-to-Video
Model Overview
Direct supply
Video GenHappyHorse 1.0 reference-to-video: generation that stays consistent with the reference images, 720P/1080P.
Input Modalities
Text
Output Modalities
Video
Recommended for
For video generation tasks, supporting video generation mode.
Capabilities
Video generation
Generates video from a text prompt or an image
Supported Modes
Video Generation
Model Pricing
15% off
Pay-as-you-go
Priced per spec
HappyHorse 1.0 Reference-to-Video is priced per spec — each tier bills at its own rate, resolved from the request.
720P$0.134$0.114per second
1080P$0.239$0.203per second
Indicative pricing — final cost is confirmed at request time.
API Code Example
HTTP
import requests
resp = requests.post(
"https://api.modelsite.ai/api/v1/services/aigc/video-generation/video-synthesis",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"input": {
"media": [
{
"type": "reference_image",
"url": "https://example.com/input.png"
}
],
"prompt": "A cat playing the piano"
},
"model": "happyhorse-1.0-r2v"
},
)
print(resp.json())
# The task id is at output.task_id in the response; poll it until the video is ready.
task_id = resp.json()["output"]["task_id"]
poll = requests.get(
f"https://api.modelsite.ai/api/v1/tasks/{task_id}",
headers={"Authorization": "Bearer YOUR_API_KEY"},
)
print(poll.json())