HappyHorse Series

POST

tasks

HappyHorse Series

curl --request POST \
  --url https://api.qingbo.ai/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "image_urls": [
    "<string>"
  ],
  "first_frame_image": "<string>",
  "video_urls": [
    "<string>"
  ],
  "resolution": "<string>",
  "duration": 123,
  "aspect_ratio": "<string>",
  "seed": 123,
  "audio_setting": "<string>",
  "watermark": true
}
'

import requests

url = "https://api.qingbo.ai/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "first_frame_image": "<string>",
    "video_urls": ["<string>"],
    "resolution": "<string>",
    "duration": 123,
    "aspect_ratio": "<string>",
    "seed": 123,
    "audio_setting": "<string>",
    "watermark": True
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    image_urls: ['<string>'],
    first_frame_image: '<string>',
    video_urls: ['<string>'],
    resolution: '<string>',
    duration: 123,
    aspect_ratio: '<string>',
    seed: 123,
    audio_setting: '<string>',
    watermark: true
  })
};

fetch('https://api.qingbo.ai/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.qingbo.ai/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"first_frame_image\": \"<string>\",\n  \"video_urls\": [\n    \"<string>\"\n  ],\n  \"resolution\": \"<string>\",\n  \"duration\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"seed\": 123,\n  \"audio_setting\": \"<string>\",\n  \"watermark\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.qingbo.ai/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"first_frame_image\": \"<string>\",\n  \"video_urls\": [\n    \"<string>\"\n  ],\n  \"resolution\": \"<string>\",\n  \"duration\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"seed\": 123,\n  \"audio_setting\": \"<string>\",\n  \"watermark\": true\n}")
  .asString();

HappyHorse is a video model line with natively synchronized audio. This page covers two models: happyhorse-1.0 supports both generate and edit, producing video from text, a first frame or reference images, and rewriting a source video; happyhorse-1.1 does generate only and is the reference-image tier on the same input set. Both share POST /v1/tasks and take almost the same parameters — they differ in actions, video input and audio handling.

Quick start

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: hh-t2v-001" \
  -d '{
    "model": "happyhorse-1.1",
    "action": "generate",
    "prompt": "A Shiba Inu in a spacesuit walking on the moon, cinematic lighting",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "duration": 5
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1.1",
    "action": "generate",
    "prompt": "The character slowly walks toward the camera",
    "first_frame_image": "https://cdn.example.com/portrait.jpg",
    "resolution": "1080p",
    "duration": 8
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1.0",
    "action": "generate",
    "prompt": "Keep the character consistent, running through a forest",
    "image_urls": [
      "https://cdn.example.com/char-1.jpg",
      "https://cdn.example.com/char-2.jpg"
    ],
    "resolution": "1080p",
    "duration": 6
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1.0",
    "action": "edit",
    "prompt": "Change the scene to a snowy day, keep the character motion",
    "video_urls": ["https://cdn.example.com/source.mp4"],
    "image_urls": ["https://cdn.example.com/style.jpg"],
    "audio_setting": "origin",
    "resolution": "1080p",
    "duration": 0
  }'

A successful submission returns a task_id. Poll GET /v1/tasks/{task_id} for the result, wait inside the call with Prefer: wait, or configure a webhook.

Request parameters

string

required

One of two: happyhorse-1.0 or happyhorse-1.1.

string

default:"generate"

generate — generate a video. Both models support it
edit — rewrite a source video; requires video_urls. Only happyhorse-1.0 supports it

string

Description of the video, or the edit instruction. Optional when a first frame or reference images are supplied, but useful to guide camera and motion.

string[]

Reference image URLs, used as subject / style references for a new scene. On happyhorse-1.0 they may accompany video_urls under edit as style references.

string

First-frame image URL. With it set, the aspect ratio follows the image and aspect_ratio has no effect.

string[]

Source video URLs. Only the edit action on happyhorse-1.0 takes it: exactly one clip, 6–15 seconds, and it is required.

string

Output resolution: 720p or 1080p.

integer

Output length in seconds, any integer 3–15.The edit action on happyhorse-1.0 follows the source video length: 0 means “use the source video length”, and any other value leaves the output length unchanged.

string

Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4. With a first frame or a source video present, the aspect ratio follows the input asset.

integer

Random seed. The same request with the same seed produces similar results.

string

Audio handling, effective only for the edit action on happyhorse-1.0: auto generates audio, origin keeps the original track.

boolean

default:"false"

Whether to add a watermark to the output. Both models take it.

See Submit Task for callback_url, callback_events, Prefer: wait, Idempotency-Key, and the maximum-cost header. Neither model supports n, quality, generate_audio or audio_urls. Any other parameter returns 400 and is not billed.

Limits

Model ID	Condition	Limit
Both models	Per task	This model produces one result per task; n is not supported
`happyhorse-1.0`	`action: "edit"`	Video edit needs one 6-15 s source video; the output length follows the source and duration has no effect
`happyhorse-1.0`	`action: "generate"`	generate does not take a source video; use edit
`happyhorse-1.1`	Video input	Does not take `video_urls` and has no `edit` action

Pricing

Both models are billed by resolution tier × seconds. price_config.video_prices is keyed by resolution, and happyhorse-1.0 additionally keys by action (edit_720p / edit_1080p), so editing and generation settle on their own tiers.

Model ID	Billing dimensions	Billed seconds
`happyhorse-1.0` (`generate`)	Resolution tier × seconds	The requested `duration`
`happyhorse-1.0` (`edit`)	Action × resolution tier × seconds	The source video length (6–15 s)
`happyhorse-1.1`	Resolution tier × seconds	The requested `duration`

Because edit output follows the source video, billed seconds come from the source video length and duration plays no part. How input seconds are read, and what happens when they cannot be read, is in Video Generation Overview. You are only billed for a successfully generated video. Failed and cancelled tasks, and tasks that return no usable video, are refunded in full. The final charge is the cost field on the task response — an integer quota at 500,000 quota = 1 USD, not dollars.

Unit prices are not listed here. They track upstream changes; this section covers billing dimensions only.Live rates: the price_config field of GET /v1/models, or the console’s Model Market. What one call cost: the cost field on the task response (integer quota, 500,000 quota = 1 USD).

Response

Completed task

{
  "task_id": "task-wave1775285160b950328499",
  "model": "happyhorse-1.1",
  "action": "generate",
  "status": "completed",
  "progress": "100%",
  "created_at": 1775285160,
  "completed_at": 1775285305,
  "billing_status": "settled",
  "cost": 483750,
  "result": {
    "videos": [
      {
        "expires_at": 1775544360,
        "url": ["https://cdn.example.com/result.mp4"]
      }
    ]
  },
  "urls": {
    "get": "https://api.qingbo.ai/v1/tasks/task-wave1775285160b950328499",
    "cancel": "https://api.qingbo.ai/v1/tasks/task-wave1775285160b950328499/cancel"
  }
}

Generated videos are returned in result.videos; url is an array and expires_at is when the video link expires. See Query Task Status for the full field reference.

Available models

Model ID	Actions	Resolution	Duration (s)	Media inputs accepted
`happyhorse-1.0`	`generate` `edit`	`720p` `1080p`	`3`–`15`; `edit` follows the source length	`image_urls` · `first_frame_image` · `video_urls` (`edit` only, one clip 6–15 s)
`happyhorse-1.1`	`generate`	`720p` `1080p`	`3`–`15`	`image_urls` · `first_frame_image`

Both models support the five aspect ratios 16:9, 9:16, 1:1, 4:3 and 3:4. happyhorse-1.0 outputs natively synchronized audio; happyhorse-1.1 targets reference-image generation.

HappyHorse Series

curl --request POST \
  --url https://api.qingbo.ai/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "image_urls": [
    "<string>"
  ],
  "first_frame_image": "<string>",
  "video_urls": [
    "<string>"
  ],
  "resolution": "<string>",
  "duration": 123,
  "aspect_ratio": "<string>",
  "seed": 123,
  "audio_setting": "<string>",
  "watermark": true
}
'

import requests

url = "https://api.qingbo.ai/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "first_frame_image": "<string>",
    "video_urls": ["<string>"],
    "resolution": "<string>",
    "duration": 123,
    "aspect_ratio": "<string>",
    "seed": 123,
    "audio_setting": "<string>",
    "watermark": True
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    image_urls: ['<string>'],
    first_frame_image: '<string>',
    video_urls: ['<string>'],
    resolution: '<string>',
    duration: 123,
    aspect_ratio: '<string>',
    seed: 123,
    audio_setting: '<string>',
    watermark: true
  })
};

fetch('https://api.qingbo.ai/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.qingbo.ai/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"first_frame_image\": \"<string>\",\n  \"video_urls\": [\n    \"<string>\"\n  ],\n  \"resolution\": \"<string>\",\n  \"duration\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"seed\": 123,\n  \"audio_setting\": \"<string>\",\n  \"watermark\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.qingbo.ai/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"first_frame_image\": \"<string>\",\n  \"video_urls\": [\n    \"<string>\"\n  ],\n  \"resolution\": \"<string>\",\n  \"duration\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"seed\": 123,\n  \"audio_setting\": \"<string>\",\n  \"watermark\": true\n}")
  .asString();

Text Generation

Image Generation

Video Generation

Audio

Tools & Embeddings

Task Management

Account & Usage

Quick start

Request parameters

Limits

Pricing

Response

Available models

​Quick start

​Request parameters

​Limits

​Pricing

​Response

​Available models

​Related

Quick start

Request parameters

Limits

Pricing

Response

Available models

Related