How much does Happy Horse cost on varg?

Happy Horse costs from $0.42 per run on varg (from $0.14/s on the cheapest route). varg charges the provider's price with no markup, from one credit balance. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.

How do I call the Happy Horse API?

Send POST https://api.varg.ai/v2/tools/video/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model": "happy_horse". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.

Can I use Happy Horse from Claude, ChatGPT or Cursor?

Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs Happy Horse with call_tool, passing tool "video" and "model": "happy_horse".

How long does a Happy Horse request take?

Typically about 3 min on the fastest route, by the catalog's estimate. The API answers at once with a job id, so nothing waits on an open connection while it runs.

Video · Text to video · Image to video · Video to video

Happy Horse API

Alibaba video generation. Expressive character motion.

Price: From $0.42 per run from $0.14/s
Typical time: ~3 min
Model id: happy_horse

Happy Horse runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.

POST /v2/tools/video/call

curl -X POST https://api.varg.ai/v2/tools/video/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "happy_horse",
  "prompt": "a cute cat playing with a ball of yarn in a sunny garden, cinematic",
  "aspect_ratio": "16:9",
  "duration": 5
}'

Try it in the Playground Get an API key

Real outputa cute cat playing with a ball of yarn in a sunny garden, cinematic

Happy Horse pricing

From $0.42 per run. Prices are in US dollars and are the provider's own, with no markup. Happy Horse has 4 routes: "model": "happy_horse" picks one automatically, or pass a route key as "model" to pin it. For the exact price of a request, send the same body to POST https://api.varg.ai/v2/estimate.

fal from $0.14/s
fal:alibaba/happy-horse/text-to-video
Text to video Alibaba Happy Horse 1.0 text-to-video — 1080p video with synchronized native audio and multilingual lip-sync from text prompts.
Resolution 720p
$0.14/s
Resolution 1080p
$0.28/s
Minimum charge
$0.42
Most one request can cost
$4.20
Typical time
~3 min
fal from $0.14/s
fal:alibaba/happy-horse/image-to-video
Image to video Alibaba Happy Horse 1.0 image-to-video — animate a first frame into 1080p video with synchronized native audio.
Resolution 720p
$0.14/s
Resolution 1080p
$0.28/s
Minimum charge
$0.42
Most one request can cost
$4.20
Typical time
~3 min
fal from $0.14/s
fal:alibaba/happy-horse/reference-to-video
Image to video Alibaba Happy Horse 1.0 reference-to-video — up to 9 reference images for subject consistency, 1080p video with synchronized native audio.
Resolution 720p
$0.14/s
Resolution 1080p
$0.28/s
Minimum charge
$0.42
Most one request can cost
$4.20
Typical time
~3 min
fal from $0.28/s
fal:alibaba/happy-horse/video-edit
Video to video Alibaba Happy Horse 1.0 video-edit — natural-language video editing with up to 5 reference images. Output preserves source aspect ratio, duration capped at 15s.
Resolution 720p
$0.28/s
Resolution 1080p
$0.56/s
Minimum charge
$0.84
Most one request can cost
$8.40
Typical time
~3 min

Happy Horse inputs

The JSON body of the request. Media inputs are URLs: upload a local file with POST /v2/files and pass the URL it returns. Full JSON Schema, no key needed: api.varg.ai/v2/tools/video?model=happy_horse

Happy Horse request fields
Field	What it does
`model` string required	`happy_horse` picks a route automatically. To pin one, pass a route key from Pricing above.
`prompt` string	—
`files` array of { url }	—
`aspect_ratio` string	Allowed e.g. 16:9 \| 9:16 \| 1:1 \| 4:3 \| 3:4 \| 21:9 \| auto
`resolution` string	Quality tier. Supported by this model: 720p, 1080p. Unsupported tiers fall back to the nearest available. Allowed 480p \| 720p \| 1080p \| 4k
`audio` boolean	Native audio track request. Not supported by this model — ignored if sent.
`duration` integer	Length in seconds. Supported by this model's routes: fal: integer 3-15. A non-numeric value such as "auto" is routed to a route whose schema accepts it; when none does, the request is rejected. Allowed 3–15

Provider options

Optional, under provider_options.<provider>. Only the options of the provider that runs the job apply; pin a route to choose it.

`provider_options.fal`

Happy Horse options for fal
Field	What it does
`prompt` string	Text prompt describing the desired video. Max 2500 characters.
`image_urls` array of URL strings	—
`reference_image_urls` array of URL strings	—
`seed` integer	Random seed for reproducibility Allowed 0–2147483647
`duration` integer	Output video duration in seconds (3-15) Allowed 3–15
`resolution` string	Allowed 720p \| 1080p
`aspect_ratio` string	Allowed 16:9 \| 9:16 \| 1:1 \| 4:3 \| 3:4
`enable_safety_checker` boolean	Enable content moderation for input and output
`image_url` string (URL)	URL of the first frame image. Formats: JPEG, JPG, PNG, BMP, WEBP. Dimensions must be at least 300px. Aspect ratio must be between 1:2.5 and 2.5:1. Max 10 MB.
`video_url` string (URL)	URL of the source video to edit. Formats: MP4, MOV (H.264 recommended). Duration: 3-60 s. Longer side <= 2160 px, shorter side >= 320 px. Aspect ratio between 1:2.5 and 2.5:1. Frame rate > 8 fps. Max 100 MB. The output video preserves the source aspect ratio. Output duration matches the input video, capped at 15 s (longer inputs are truncated to the first 15 s).
`audio_setting` string	Allowed auto \| origin

Call the Happy Horse API

POST https://api.varg.ai/v2/tools/video/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away.

1. Send the request

cURL

curl -X POST https://api.varg.ai/v2/tools/video/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "happy_horse",
  "prompt": "a cute cat playing with a ball of yarn in a sunny garden, cinematic",
  "aspect_ratio": "16:9",
  "duration": 5
}'

JavaScript

const headers = {
  Authorization: `Bearer ${process.env.VARG_API_KEY}`,
  'Content-Type': 'application/json',
}

const res = await fetch('https://api.varg.ai/v2/tools/video/call', {
  method: 'POST',
  headers,
  body: JSON.stringify({
    "model": "happy_horse",
    "prompt": "a cute cat playing with a ball of yarn in a sunny garden, cinematic",
    "aspect_ratio": "16:9",
    "duration": 5
  }),
})
const job = await res.json() // { id: "job_…", status: "queued" }

Python

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['VARG_API_KEY']}"}

job = requests.post(
    "https://api.varg.ai/v2/tools/video/call",
    headers=headers,
    json={
      "model": "happy_horse",
      "prompt": "a cute cat playing with a ball of yarn in a sunny garden, cinematic",
      "aspect_ratio": "16:9",
      "duration": 5
    },
).json()  # {"id": "job_…", "status": "queued"}

2. Get the result

Poll the job until its status is completed, failed or cancelled; Happy Horse typically takes about 3 min. The result is at output.outputs[0].url.

GET /v2/jobs/{id}

curl https://api.varg.ai/v2/jobs/$JOB_ID \
  -H "Authorization: Bearer $VARG_API_KEY"

# Poll until "status" is completed, failed or cancelled.
# The result is in output.outputs[0].url

JavaScript

let current = job
while (!['completed', 'failed', 'cancelled'].includes(current.status)) {
  await new Promise((resolve) => setTimeout(resolve, 3000))
  current = await (await fetch(`https://api.varg.ai/v2/jobs/${current.id}`, { headers })).json()
}
console.log(current.output?.outputs?.[0]?.url)

Python

import time

while job["status"] not in ("completed", "failed", "cancelled"):
    time.sleep(3)
    job = requests.get(f"https://api.varg.ai/v2/jobs/{job['id']}", headers=headers).json()

print(job["output"]["outputs"][0]["url"])

Or take a webhook instead of polling

Add options.webhook_url and varg POSTs the finished job to it.

request body

{
  "model": "happy_horse",
  "prompt": "a cute cat playing with a ball of yarn in a sunny garden, cinematic",
  "aspect_ratio": "16:9",
  "duration": 5,
  "options": {
    "webhook_url": "https://your-app.com/varg-webhook"
  }
}

From Claude, ChatGPT or Cursor (MCP)

The varg MCP server, https://mcp.varg.ai/mcp, runs Happy Horse with call_tool. Sign in with varg, no API key to paste. How to connect it

call_tool

{
  "tool": "video",
  "input": {
    "model": "happy_horse",
    "prompt": "a cute cat playing with a ball of yarn in a sunny garden, cinematic",
    "aspect_ratio": "16:9",
    "duration": 5
  },
  "wait": true
}

Happy Horse API: questions

How much does Happy Horse cost on varg?: Happy Horse costs from $0.42 per run on varg (from $0.14/s on the cheapest route). varg charges the provider's price with no markup, from one credit balance. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
How do I call the Happy Horse API?: Send POST https://api.varg.ai/v2/tools/video/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model": "happy_horse". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
Can I use Happy Horse from Claude, ChatGPT or Cursor?: Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs Happy Horse with call_tool, passing tool "video" and "model": "happy_horse".
How long does a Happy Horse request take?: Typically about 3 min on the fastest route, by the catalog's estimate. The API answers at once with a job id, so nothing waits on an open connection while it runs.

For AI agents: this page as Markdown is varg.ai/models/happy_horse.md, and every model is listed in varg.ai/models/llms.txt.