Name: Happy Horse 1.1 API
Brand: Alibaba Cloud

Overview

What is Happy Horse 1.1?

Happy Horse 1.1 is an AI video generation model designed for speed, visual quality, and predictable pricing. Unlike models that charge per clip with hidden minimum durations or resolution tiers buried in fine print, Happy Horse bills at a flat per-second rate.

The 1.1 update builds on its predecessor with tighter temporal consistency (frames that actually look like they belong to the same scene), improved handling of complex motion paths, and better colour fidelity at both supported resolutions. The result is generated footage that holds up under close inspection rather than falling apart on the fifth frame.

Technical specifications

Specification	Detail
Model version	Happy Horse 1.1
Output resolutions	720p (1280×720) · 1080p (1920×1080)
Pricing — 720p	$0.182 per second of generated video
Pricing — 1080p	$0.234 per second of generated video
Billing model	Per-second
Input format	Text prompt (natural language)
Output format	MP4 (H.264)
Key improvements over 1.0	Temporal consistency, colour fidelity, complex motion handling

What it does well

Dual resolution output

Generate at 720p for fast iteration and content testing, then switch to 1080p for final delivery without changing your prompt or workflow.

Temporal consistency

Frames are modelled to maintain subject identity and scene coherence across the full clip, reducing the jitter and drift that makes AI video feel artificial.

Colour fidelity

Version 1.1 ships with improved colour reproduction across both tiers, reducing washed-out midtones that affected the original release.

Motion control

Describe camera movement, subject direction, and pacing in natural language. The model translates intent into motion without requiring keyframe inputs.

API Pricing

720p: $0.182 per second
1080p: $0.234 per second

Where it fits

Happy Horse 1.1 is a general-purpose video generation model, but it earns its keep in a few specific situations more than others.

Social and short-form content

Generate b-roll, background loops, and motion graphics for social platforms at 720p. The per-second pricing is kind to high-volume workflows where you're producing dozens of short clips every week.

Product marketing and explainers

Create polished 1080p clips for landing pages, ad campaigns, or product demos without booking a shoot. Iterate on messaging quickly without reshooting from scratch.

Developer integrations and SaaS products

Embed video generation inside your own app using the API. The predictable per-second cost makes it easier to price your product's video features and forecast your AI spend.

Prototyping and concept visualisation

Sketch a scene with a text prompt before committing budget to a live production. Generate at 720p for speed during ideation, then step up to 1080p once the concept is locked.

‍

Use cases

Short-form social media clips are a documented fit for Happy Horse 1.1, including vertical content for TikTok, Instagram Reels, and YouTube Shorts.

E-commerce product ads are another stated use case, especially turning product images into short animated ads with synchronized audio.

Marketing and brand campaign assets are also documented uses, including teasers, launch creatives, and multilingual campaign materials.

Short-drama or story-driven scenes are cited as a fit as well, with the model described as suitable for short narrative clips and multi-shot storytelling.

How to use Happy Horse 1.1 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to alibaba/happyhorse-1-1.

import requests, time

headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
    "https://api.aimlapi.com/v2/video/generations",
    headers=headers,
    json={
      "model": "alibaba/happyhorse-1-1",
      "prompt": "A serene timelapse of clouds over a mountain range"
    },
).json()
gid = job["id"]

while True:
    res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json()
    if res.get("status") in ("completed", "error"):
        break
    time.sleep(5)
print(res["video"]["url"])

const headers = {
  Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
  "Content-Type": "application/json",
};
const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "alibaba/happyhorse-1-1",
    "prompt": "A serene timelapse of clouds over a mountain range"
  }),
})).json();

let res;
do {
  await new Promise((r) => setTimeout(r, 5000));
  res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json();
} while (!["completed", "error"].includes(res.status));
console.log(res.video.url);

# submit the generation — the response contains the job "id"
curl -X POST https://api.aimlapi.com/v2/video/generations \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"alibaba/happyhorse-1-1","prompt":"A serene timelapse of clouds over a mountain range"}'

# then poll until status is "completed" — video.url holds the result
curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"

OpenAI-compatible — swap the base URL and it works with your existing SDK.