Vidu Q3 Series

POST

tasks

Vidu Q3 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>"
  ],
  "duration": 123,
  "resolution": "<string>",
  "aspect_ratio": "<string>",
  "generate_audio": true,
  "seed": 123
}
'

import requests

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

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "duration": 123,
    "resolution": "<string>",
    "aspect_ratio": "<string>",
    "generate_audio": True,
    "seed": 123
}
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>'],
    duration: 123,
    resolution: '<string>',
    aspect_ratio: '<string>',
    generate_audio: true,
    seed: 123
  })
};

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  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"generate_audio\": true,\n  \"seed\": 123\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  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"generate_audio\": true,\n  \"seed\": 123\n}")
  .asString();

ShengShu Technology’s Vidu Q3 line. This page covers vidu-q3, vidu-q3-mix, vidu-q3-pro and vidu-q3-turbo: all four go through the same task endpoint, all four have generate as their only action, and all four are billed by resolution tier and seconds. They differ in whether reference images are required, which resolutions they offer, and whether they produce audio. The first two are reference-to-video (image_urls is required, and the characters and style come from those images); the other two do text-to-video as well as start-frame and first-and-last-frame video, with native audio on by default. For 2k / 4k output, more reference images (up to 15) or reference audio, use Vidu Q4 Preview; it does not do text-only or first-and-last-frame video.

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: vidu-demo-001" \
  -d '{
    "model": "vidu-q3",
    "action": "generate",
    "prompt": "Keep the character consistent, running through a forest, camera following",
    "image_urls": ["https://cdn.example.com/character.jpg"],
    "duration": 5,
    "resolution": "1080p"
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vidu-q3-mix",
    "action": "generate",
    "prompt": "The character sits down in this room and picks up the cup on the table",
    "image_urls": [
      "https://cdn.example.com/character.jpg",
      "https://cdn.example.com/scene.jpg",
      "https://cdn.example.com/cup.jpg"
    ],
    "duration": 8,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vidu-q3-pro",
    "action": "generate",
    "prompt": "A coastal observatory at sunrise, static camera, waves breaking on the rocks",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vidu-q3-turbo",
    "action": "generate",
    "prompt": "The camera moves slowly from the room out to the street",
    "image_urls": [
      "https://cdn.example.com/start.jpg",
      "https://cdn.example.com/end.jpg"
    ],
    "duration": 5,
    "resolution": "720p"
  }'

A successful submission returns a task_id. Retrieve the result with GET /v1/tasks/{task_id}, wait inline with Prefer: wait, or configure a webhook.

Request parameters

string

required

One of vidu-q3, vidu-q3-mix, vidu-q3-pro or vidu-q3-turbo.

string

default:"generate"

generate is the only action of all four models. The mode is not selected by action but by how many images image_urls carries: for vidu-q3-pro and vidu-q3-turbo, none is text-to-video, one is a start frame and two are first and last frame. vidu-q3 and vidu-q3-mix always need reference images.

string

Description of the video — motion, camera, mood; with reference images the appearance comes from the images. Required for vidu-q3 and vidu-q3-mix, and for vidu-q3-pro / vidu-q3-turbo when image_urls is not sent.

string[]

Image URLs.

vidu-q3, vidu-q3-mix: reference images, required, 1–7; they decide characters, subjects, props and style
vidu-q3-pro, vidu-q3-turbo: optional, at most 2 — one image is the start frame, two are the first and last frame

integer

Clip length in seconds, an integer.

vidu-q3: 3 to 16
vidu-q3-mix: 1 to 16
vidu-q3-pro, vidu-q3-turbo: 1 to 16, default 5

string

Output resolution.

vidu-q3, vidu-q3-pro, vidu-q3-turbo: 540p, 720p or 1080p
vidu-q3-mix: 720p or 1080p

All four models default to 720p.

string

Frame ratio: 16:9, 9:16, 4:3, 3:4, 1:1. vidu-q3, vidu-q3-pro and vidu-q3-turbo use 16:9 when it is omitted. vidu-q3-pro and vidu-q3-turbo do not take this parameter together with image_urls; the ratio then comes from the input image.

boolean

default:"true"

Whether to generate audio (dialogue and sound effects). Accepted by vidu-q3-pro and vidu-q3-turbo only; set it to false for a silent clip.

integer

Random seed. The same parameters with the same seed produce similar, though not identical, results.

The shared callback_url, callback_events, Prefer: wait, Idempotency-Key and cost-cap headers are documented in Submit Task. None of the four models accepts first_frame_image, last_frame_image (frames are expressed through image_urls), video_urls, audio_urls, n, negative_prompt or quality, and generate_audio is accepted by vidu-q3-pro and vidu-q3-turbo only. Anything beyond the parameters above returns 400 and is not billed.

Limits

Model	Condition	Limit
`vidu-q3` `vidu-q3-mix`	Per request	This model produces one result per task; n is not supported
`vidu-q3` `vidu-q3-mix`	Per request	`image_urls` is required, up to 7 images
`vidu-q3-pro` `vidu-q3-turbo`	Per request	One video per task; at most 2 images (1 = start frame, 2 = first and last frame).
`vidu-q3-pro` `vidu-q3-turbo`	`image_urls` sent	With input images the aspect ratio follows the image; aspect_ratio cannot be sent.

Pricing

Billed by resolution tier times seconds: the resolution sets the per-second rate, duration sets the number of seconds, and their product is the cost of the call — known before you submit. The four models have different per-second rates, and within a model a higher resolution costs more. generate_audio, seed, the aspect ratio and the number of reference images do not affect the price. Without resolution the 720p default tier applies.

Per-model rates are in price_config on GET /v1/models, and in the console’s Model Market.What a single call actually cost is the cost field on the task response — an integer quota at 500,000 quota = 1 USD.

You are only billed for a video that is produced. Failed and cancelled tasks, and tasks that return no usable video, are refunded in full.

Response

Task completed

{
  "task_id": "task-wave1788769966b950814242",
  "model": "vidu-q3-pro",
  "action": "generate",
  "status": "completed",
  "progress": "100%",
  "created_at": 1788769966,
  "completed_at": 1788770002,
  "result": {
    "videos": [
      {
        "url": ["https://cdn.example.com/result.mp4"],
        "expires_at": 1789089508
      }
    ]
  },
  "billing_status": "settled",
  "cost": 31500,
  "urls": {
    "get": "https://api.qingbo.ai/v1/tasks/task-wave1788769966b950814242",
    "cancel": "https://api.qingbo.ai/v1/tasks/task-wave1788769966b950814242/cancel"
  }
}

result.videos holds the generated video and expires_at is when the link stops working (Unix seconds) — copy the file to your own storage before then. Full field reference in Query Task Status.

Available models

Model ID	Resolutions	Duration (s)	Image input	Notes
`vidu-q3`	`540p` `720p` `1080p`	3–16	1–7 reference images, required	Reference-to-video that keeps referenced subjects consistent, multi-shot cutting
`vidu-q3-mix`	`720p` `1080p`	1–16	1–7 reference images, required	Blends several references into one coherent clip
`vidu-q3-pro`	`540p` `720p` `1080p`	1–16	Optional, at most 2	Text / start frame / first and last frame, audio on by default
`vidu-q3-turbo`	`540p` `720p` `1080p`	1–16	Optional, at most 2	Same capabilities as Pro, faster tier at a lower rate

Vidu Q3 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>"
  ],
  "duration": 123,
  "resolution": "<string>",
  "aspect_ratio": "<string>",
  "generate_audio": true,
  "seed": 123
}
'

import requests

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

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "duration": 123,
    "resolution": "<string>",
    "aspect_ratio": "<string>",
    "generate_audio": True,
    "seed": 123
}
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>'],
    duration: 123,
    resolution: '<string>',
    aspect_ratio: '<string>',
    generate_audio: true,
    seed: 123
  })
};

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  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"generate_audio\": true,\n  \"seed\": 123\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  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"generate_audio\": true,\n  \"seed\": 123\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