HappyHorse

Overview

HappyHorse is an Alibaba video model for text-to-video, image-to-video, reference-guided video generation, and video editing. Use this page when you are ready to call the API after trying the model in the APIXO playground.

Capability	Value
Model ID	`happyHorse`
Modes	`text-to-video`, `image-to-video`, `reference-to-video`, `video-edit`
Prompt	Required for `text-to-video`, `reference-to-video`, and `video-edit`; optional for `image-to-video`
Prompt length	Up to 2500 characters
Input images	Exactly 1 URL for `image-to-video`; 1-9 URLs for `reference-to-video`; 0-5 optional reference image URLs for `video-edit`
Input videos	Exactly 1 URL for `video-edit`
Aspect ratios	`16:9`, `9:16`, `1:1`, `4:3`, `3:4` for `text-to-video` and `reference-to-video`
Resolution tiers	`720p`, `1080p`
Duration	3-15 seconds for `text-to-video`, `image-to-video`, and `reference-to-video`

HappyHorse outputs video with audio by default. The public API does not expose a switch to fully disable generated audio. For video-edit, use audio_setting to choose automatic audio behavior or preserve the original input audio.

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/happyHorse`	Submit a generation or edit task
`GET`	`/statusTask/happyHorse?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request submits a text-to-video task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/happyHorse" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic rainy night in tokyo, slow dolly shot, reflective streets",
      "resolution": "720p",
      "ratio": "16:9",
      "duration": 5
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final video.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/happyHorse?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "PromptInvalid",
    "failMsg": "Prompt is invalid or rejected by provider",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const videoUrls = payload.resultUrls;

Request body

Text-to-video

{
  "request_type": "async",
  "input": {
    "mode": "text-to-video",
    "prompt": "a cinematic rainy night in tokyo, slow dolly shot, reflective streets",
    "resolution": "1080p",
    "ratio": "16:9",
    "duration": 5,
    "watermark": false
  }
}

Image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video",
    "image_urls": [
      "https://example.com/first-frame.png"
    ],
    "prompt": "animate the scene with a gentle camera move",
    "resolution": "720p",
    "duration": 5,
    "watermark": false
  }
}

Reference-to-video

{
  "request_type": "async",
  "input": {
    "mode": "reference-to-video",
    "prompt": "keep the character style consistent across all references",
    "image_urls": [
      "https://example.com/ref-1.png",
      "https://example.com/ref-2.png"
    ],
    "resolution": "1080p",
    "ratio": "16:9",
    "duration": 6,
    "watermark": false
  }
}

Video edit

{
  "request_type": "async",
  "input": {
    "mode": "video-edit",
    "video_urls": [
      "https://example.com/input.mp4"
    ],
    "image_urls": [
      "https://example.com/reference.png"
    ],
    "prompt": "change the scene to watercolor style",
    "resolution": "1080p",
    "audio_setting": "origin",
    "watermark": false
  }
}

Parameters

string

default:"async"

required

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

string

Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.

object

required

HappyHorse input parameters.

Show properties

string

required

Generation mode. Supported values: text-to-video, image-to-video, reference-to-video, video-edit.

string

Text prompt describing the video or edit. Required for text-to-video, reference-to-video, and video-edit; optional for image-to-video. Required prompts cannot be empty after trimming. Maximum 2500 characters.

string[]

Public image URLs. Required with exactly 1 URL for image-to-video; required with 1-9 URLs for reference-to-video; optional with 0-5 reference image URLs for video-edit.

string[]

Public video URLs. Required for video-edit; must contain exactly 1 URL.

string

default:"1080p"

Output resolution tier. Supported values: 720p, 1080p.

string

default:"16:9"

Output aspect ratio for text-to-video and reference-to-video. Supported values: 16:9, 9:16, 1:1, 4:3, 3:4.

integer

default:"5"

Output duration in seconds for text-to-video, image-to-video, and reference-to-video. Supports integers from 3 to 15. Not used for video-edit; the provider request for video-edit does not include duration.

string

default:"auto"

video-edit only. Supported values: auto, origin. Use origin when you want to preserve the original input audio.

boolean

default:"false"

Whether to add a watermark.

integer

Optional random seed. Supports integers from 0 to 2147483647. If omitted, the backend automatically generates a seed and sends it to the provider.

Response format

Submit task response

POST /generateTask/happyHorse returns a task ID when the task is accepted:

integer

API status code. 200 means the task was accepted.

string

Human-readable status message.

string

Unique task identifier used with the status endpoint.

Status response fields

string

Unique task identifier.

string

Current task state: processing, success, or failed.

string

JSON string containing generated video URLs in resultUrls. Present when state is success.

string

Machine-readable failure code. Present when state is failed.

string

Human-readable failure message. Present when state is failed.

integer

Task creation timestamp in Unix milliseconds.

integer

Task completion timestamp in Unix milliseconds. Present after completion.

integer

Processing duration in milliseconds. Present after successful completion when available.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/happyHorse" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "mode": "video-edit",
      "video_urls": [
        "https://example.com/input.mp4"
      ],
      "image_urls": [
        "https://example.com/reference.png"
      ],
      "prompt": "change the scene to watercolor style",
      "resolution": "1080p",
      "audio_setting": "origin",
      "watermark": false
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

HappyHorse is billed per second. The selected resolution determines the unit price.

Resolution	APIXO official price	Market reference
`720p`	`$0.125 / second`	`$0.1625 / second`
`1080p`	`$0.225 / second`	`$0.2875 / second`

Billing formulas:

Mode	Formula
`text-to-video`	`duration * unitPrice`
`image-to-video`	`duration * unitPrice`
`reference-to-video`	`duration * unitPrice`
`video-edit`	`(input video seconds + output video seconds) * unitPrice`

For video-edit, the backend probes the input video duration and does not send a public duration parameter to the provider. Billing uses the input video seconds plus the generated output video seconds; APIXO caps the billable input side at 15 seconds, and the generated output side is billed at the same capped duration. For current route and market comparison pricing, see Pricing.

Latency and polling

HappyHorse tasks are asynchronous. The backend does not enforce a fixed public latency SLA; actual time varies by mode, resolution, duration, prompt complexity, media fetch speed, and provider queue load.

Workflow	What affects latency	Recommended first poll	Poll interval
`text-to-video`	Resolution, duration, prompt complexity, queue load	30s after task creation	10s
`image-to-video`	Image fetch time, resolution, duration, queue load	30s after task creation	10s
`reference-to-video`	Number of references, resolution, duration, queue load	45s after task creation	10s-15s
`video-edit`	Input video fetch/probe time, input duration, references, queue load	60s after task creation	10s-15s

For production workloads, use callback mode to avoid frequent polling for long-running video jobs.

Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, mode, parameter, media URL shape, or provider rejection	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error	Retry with backoff
`502`	Upstream provider error	Retry with backoff
`504`	Upstream timeout	Retry or use callback mode for long-running jobs

Task failure codes

Fail code	Meaning	What to do
`PromptInvalid`	Prompt was invalid or rejected by the provider	Rewrite the prompt with clearer, policy-safe instructions
`SensitiveContent` / `SensitiveContentDetected`	Prompt, input media, or output failed safety checks	Change the prompt or media
`MissingParameter` / `BadRequest`	Required mode-specific fields are missing or malformed	Check `mode`, `prompt`, `image_urls`, `video_urls`, `resolution`, `ratio`, and `duration`
`RateLimited` / `RateLimitExceeded`	Provider or APIXO rate limit was reached	Retry with exponential backoff
`Timeout` / `Task TimeOut`	The provider did not finish in time	Retry, reduce input complexity, or use callback mode
`Unknown error`	Upstream failure could not be mapped to a known category	Retry with backoff or contact support with the `taskId`

Troubleshooting tips

Use public, direct, fetchable URLs for image_urls and video_urls.
For image-to-video, send exactly one image URL.
For reference-to-video, send 1-9 image URLs and include a non-empty prompt.
For video-edit, send exactly one video URL. Optional reference images are limited to 5.
Use ratio only with text-to-video and reference-to-video.
Use duration only with text-to-video, image-to-video, and reference-to-video; video-edit duration is determined from the input video and billed as input video seconds plus output video seconds.
Store result URLs promptly if your application needs long-term access.

See Error Codes for the full error reference.

Getting Started

Image Models

Video Models

Audio Models

Text & Utility Models

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-video

Image-to-video

Reference-to-video

Video edit

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Task failure codes

Troubleshooting tips

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-video

​Image-to-video

​Reference-to-video

​Video edit

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Task failure codes

​Troubleshooting tips

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-video

Image-to-video

Reference-to-video

Video edit

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Task failure codes

Troubleshooting tips

Related links