Video

Vidu Q4 Preview API

Vidu Q4 API on APIMart (model ID viduq4-preview, often written viduq4): ShengShu's Vidu Q4 Preview turns one first frame, or 1–15 reference images with up to 3 reference audio clips, into 3–16 second videos at up to 4K with native audio. It is the newest model in the Vidu API family on APIMart.

Image to VideoReference to Video3–16 SecondsUp to 4K

Get API Key API Docs

Service Highlights

Official Discounts
Pay-as-you-go
Fast & Low Latency

Input

Model

Generation mode

First Frame

Prompt

Resolution

Duration5s

Audio

Seed

Output

Video link valid for 72 hours

Pricing Details

Transparent pricing with no hidden fees. Pay only for what you use.

Variant	Tier	GoldCurrent price	Platinum	Diamond	Official	Your savings
`viduq4-preview`	540p	0.448Credits(~$0.0448)/sec	0.4256Credits(~$0.0426)/sec	0.4032Credits(~$0.0403)/sec	0.56Credits(~$0.056)/sec	20%
	720p	0.912Credits(~$0.0912)/sec	0.8664Credits(~$0.0866)/sec	0.8208Credits(~$0.0821)/sec	1.14Credits(~$0.114)/sec	20%
	1080p	1.024Credits(~$0.1024)/sec	0.9728Credits(~$0.0973)/sec	0.9216Credits(~$0.0922)/sec	1.28Credits(~$0.128)/sec	20%
	2K	1.624Credits(~$0.1624)/sec	1.5428Credits(~$0.1543)/sec	1.4616Credits(~$0.1462)/sec	2.03Credits(~$0.203)/sec	20%
	4K	3.328Credits(~$0.3328)/sec	3.1616Credits(~$0.3162)/sec	2.9952Credits(~$0.2995)/sec	4.16Credits(~$0.416)/sec	20%

* Actual costs are subject to final output.

Vidu Q4 API: animate images and references in up to 4K

Generate Vidu Q4 videos online in the playground above or call the Vidu Q4 API from your app. Start from one first frame with an optional prompt, or combine 1–15 reference images, a prompt and up to 3 MP3 clips. Choose 3–16 seconds and 540p to 4K; audio is on by default at the same price.

Vidu Q4 Preview API capabilities

Explore Vidu Q4 inputs, output controls, and the asynchronous API workflow

Vidu first-frame and reference inputs

Give Vidu one first frame for I2V or 1–15 reference images for R2V. Accepted formats are PNG, JPEG, and WEBP, up to 50 MB each; text-only input and end frames are not supported.

Prompts for Vidu generation

Guide Vidu with an API prompt of up to 20,000 characters describing action, camera movement, or a scene. Vidu prompts are optional for I2V and required for R2V.

Vidu resolution options

Set the Vidu Q4 API resolution to 540p, 720p, 1080p, 2K, or 4K. The API defaults to 720p; match the resolution to your intended placement and budget.

Vidu clip duration

Request Vidu clips of 3–16 seconds using an integer duration; the default is 5 seconds. Start with a short draft to review movement before requesting a longer clip.

Audio in Vidu

Vidu generates audio by default; disable it through the API for silent output at the same price. Vidu R2V also accepts up to 3 MP3 references, each 3–12 seconds and up to 50 MB, without a material surcharge.

Vidu seed control

Supply an integer seed in your Vidu request when exploring related outputs. For a random result, omit seed or use 0; review the generated motion before publishing.

Vidu API task workflow

Submit a Vidu API request to POST /v1/videos/generations and save the task_id. Query GET /v1/tasks/{task_id} for the original task until completed or failed, without submitting another generation.

Vidu API billing

Vidu API pricing uses duration multiplied by the selected resolution's current per-second rate in both modes. Vidu reference images, reference audio, and generated audio carry no surcharge. Check live account pricing; failed tasks are fully refunded.

Vidu Q4 API use cases

Plan Vidu workflows around an approved first frame or reference materials

Product and brand clips with Vidu

Animate a product photograph with the Vidu API to create a short promotional shot. Check product details and brand suitability in each Vidu clip before use.

Social content with Vidu

Use Vidu to turn a selected image into a 3–16 second social opening. Match the resolution to the destination and choose audio or silent output, then review the Vidu result for your audience.

Vidu storyboards and pitches

Explore scene and camera direction with Vidu, using a storyboard frame or reference images with a prompt. Review each Vidu clip before adding it to a finished edit.

Vidu character motion studies

Guide Vidu with character references, a required prompt, and optional MP3 clips through the API. Check identity, movement, and suitability in the Vidu output before use.

Education and explainers with Vidu

Animate a prepared illustration with Vidu for a short teaching segment. Check the Vidu visuals for accuracy, and add verified narration or captions during editing.

Vidu game concept previews

Connect the Vidu API to an internal concept-review tool and animate an environment image with suggested movement. Use Vidu clips for mood exploration, then review them with your creative team.

How to Get a Vidu Q4 API Key and Start

Three steps to your first Vidu Q4 video on APIMart.

Sign up and add funds

Create an APIMart account and top up your balance. It works for every model on the platform, including the Vidu API.

→

Create your API key

Generate an API key in your dashboard. The same key calls Vidu Q4 and every other model on APIMart.

→

Send your first request

POST /v1/videos/generations with model viduq4-preview, then poll GET /v1/tasks/{task_id} until the video is ready.

Start Creating

Vidu Q4 API Example: Image to Video and Reference to Video

Call Vidu Q4 Preview on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint to get the video URL.

1
Authenticate Vidu Q4 API requests
Save your APIMart key in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
2
Submit a Vidu Q4 task
POST /v1/videos/generations with model viduq4-preview and the inputs shown in the example. The task ID is in data[0].task_id.
3
Get the Vidu Q4 video
Poll GET /v1/tasks/{task_id} until status is completed, then read the video URL from data.result.videos[0].url[0]. Results are kept for 72 hours, so download them in time.
See the Vidu Q4 Preview API reference for every parameter, input rule and response field.

POST /v1/videos/generations

curl -X POST https://api.apimart.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "viduq4-preview",
    "prompt": "The camera slowly pushes in as the person turns and smiles",
    "image_urls": [
      "https://example.com/first-frame.png"
    ],
    "duration": 5,
    "resolution": "720p",
    "audio": true
  }'

import os
import time
import requests

API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}

# 1. Submit the generation task
payload = {
  "model": "viduq4-preview",
  "prompt": "The camera slowly pushes in as the person turns and smiles",
  "image_urls": [
    "https://example.com/first-frame.png"
  ],
  "duration": 5,
  "resolution": "720p",
  "audio": True
}
resp = requests.post(f"{API_BASE}/v1/videos/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]

# 2. Poll the task until it finishes
for _ in range(200):
    task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
    task_resp.raise_for_status()
    task = task_resp.json()["data"]
    if task["status"] == "completed":
        print(task["result"]["videos"][0]["url"][0])
        break
    if task["status"] == "failed":
        raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
    time.sleep(10)
else:
    raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")

curl -X POST https://api.apimart.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "viduq4-preview",
    "prompt": "The character from image 1 walks through the street from image 2 at sunset, natural dialogue and city sounds",
    "image_urls": [
      "https://example.com/character.png",
      "https://example.com/scene.png"
    ],
    "duration": 8,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }'

TASK_ID="task_xxx"  # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
  -H "Authorization: Bearer $APIMART_API_KEY"

Vidu Q4 API Parameters

Parameter	Type	Required	Default	Description
`model`	string	Required	Default: —	Use viduq4-preview.
`prompt`	string	Optional	Default: —	Up to 20,000 characters. Optional for image to video, required for reference to video.
`image_urls`	string[]	Optional	Default: —	Public URLs or Base64 data URLs. One image for image to video, 1–15 images for reference to video.
`image_with_roles`	object[]	Optional	Default: —	Images with roles: first_frame, or reference_image for reference to video.
`first_frame_image`	string	Optional	Default: —	First frame for image to video only. Do not combine with other images or audio.
`audio_urls`	string[]	Optional	Default: —	Up to 3 MP3 reference clips, 3–12 seconds each, for reference to video only.
`duration`	integer	Optional	Default: 5	Clip length in seconds: 3–16. Default 5.
`resolution`	string	Optional	Default: 720p	Output resolution: 540p, 720p, 1080p, 2K or 4K. Default 720p.
`aspect_ratio`	string	Optional	Default: 16:9	1:1, 9:16, 16:9, 3:4 or 4:3 for reference to video. Default 16:9; ignored for image to video.
`audio`	boolean	Optional	Default: true	Generate dialogue and sound effects. Default true; false returns a silent video.
`seed`	integer	Optional	Default: —	Integer seed that controls randomness. Omit it for a random seed.

Vidu API Model Family

Compare every Vidu video model on APIMart. One API key calls all of them, billed per second of video.

Model	Best for	Resolution	Duration
Vidu Q4 Preview APIThis page	Newest generation: animate a first frame, or combine 1–15 reference images with up to 3 audio clips	540p – 4K	3–16s
Vidu Q3 Pro API	Text-to-video, image-to-video and first-last frame, with audio on by default	540p / 720p / 1080p	1–16s
Vidu Q3 Turbo API	Same modes as Vidu Q3 Pro at the lowest per-second rate in the Vidu series	540p / 720p / 1080p	1–16s
Vidu Q3 API	Everyday reference-to-video from 1–7 images, with smart multi-angle camera switching	540p / 720p / 1080p	3–16s
Vidu Q3 Mix API	Premium reference-to-video from 1–7 images, with stronger smart transitions and short motion effects	720p / 1080p	1–16s

Vidu Q4 Preview API FAQ

Practical answers about Vidu inputs, API parameters, pricing, and results

What is Vidu Q4 Preview?

Vidu Q4 Preview is the newest Vidu video model from ShengShu on APIMart, also searched as Vidu Q4, viduq4 or Vidu AI Q4. Its API ID is viduq4-preview. It animates one first frame or follows 1–15 reference images, with optional reference audio, and outputs 3–16 second clips at up to 4K.

When was Vidu Q4 released?

ShengShu launched Vidu Q4 Preview on October 7, 2026, and no date has been announced for a full Vidu Q4 release. On APIMart, the Vidu Q4 API calls Vidu Q4 Preview with model ID viduq4-preview.

Is Vidu Q4 Preview the same as the Vidu Q4 API?

Yes. Vidu Q4 Preview is the version of Vidu Q4 available today, and the Vidu Q4 API on APIMart calls it with model ID viduq4-preview. Send the model ID exactly as written, in lowercase.

Does Vidu Q4 Preview support text-to-video?

No. The Vidu Q4 Preview API needs one first frame for I2V or 1–15 images for R2V. Vidu R2V may also use up to 3 reference audio clips. Text-only generation and first-and-last-frame control are not supported.

How do I choose first-frame or reference inputs for Vidu Q4?

For Vidu I2V, use first_frame_image, role first_frame, or one unmarked image without reference audio. For Vidu R2V, use role reference_image (alias reference), multiple images, or reference audio with unmarked images. Never mix an explicit first frame with references or reference audio. Image URLs and image_with_roles share a 15-image R2V limit. Each PNG, JPEG/JPG, or WEBP image must be at most 50 MB; a base64 request must be under 20 MB.

Does the Vidu Q4 API require a prompt?

A prompt is optional for Vidu I2V and required for Vidu R2V, with a 20,000-character limit in either mode. Describe the action, scene, and how the supplied references should inform the video.

What is the maximum video length of Vidu Q4, and which resolutions does it support?

Vidu Q4 Preview videos can be up to 16 seconds long: set any integer duration from 3 to 16 seconds (default 5). Output is 540p, 720p, 1080p, 2K or 4K (default 720p). For Vidu R2V, choose 1:1, 9:16, 16:9, 3:4, or 4:3; the default is 16:9. aspect_ratio takes precedence over its size alias. I2V ignores both fields and follows the first-frame image.

How do audio and seed work in Vidu?

Vidu audio defaults to true; false produces silent output at the same price. R2V accepts 0–3 MP3 references, each 3–12 seconds and up to 50 MB. Upstream checks their format and duration; an invalid clip may cause a refunded task failure. Vidu seed accepts an integer; omit it or use 0 for random.

How much does the Vidu Q4 API cost?

Vidu Q4 is billed per second of output at the selected resolution. As of November 4, 2026, Gold member rates are 540p $0.0448, 720p $0.0912, 1080p $0.1024, 2K $0.1624 and 4K $0.3328 per second, so a 5-second 720p clip costs about $0.46. Videos with or without audio cost the same, and reference images or audio add no separate fee. The pricing table shows live rates.

Am I charged if a Vidu Q4 task fails?

No. Parameter errors, such as mixing a first frame with reference images or exceeding the image or audio limits, return HTTP 400 at submission without creating a task or charging. If a task fails during generation, for example because of an invalid reference audio file, it is fully refunded automatically.

How do I get a Vidu Q4 API key?

Sign up on APIMart, add funds and create a key on the API Keys page. The same key calls Vidu Q4, the Vidu Q3 models and every other model on APIMart, with pay-as-you-go billing and no subscription.

How do I retrieve a Vidu Q4 video through the API?

The Vidu generation API at POST /v1/videos/generations returns a task_id. Poll GET /v1/tasks/{task_id} every 5–10 seconds until completed or failed. Find completed video URLs in data.result.videos[0].url[0].

How long are Vidu Q4 videos kept?

Generated videos are kept for 72 hours, so download them in time. If a status query times out, the task has not necessarily failed; keep querying the original task ID instead of submitting a new one.

Can I try Vidu Q4 online?

Yes. Sign in to APIMart, create an API key and add funds, then use the generator at the top of this page to create Vidu Q4 videos in your browser. Playground runs call the same API and are billed per second at the same rates, and finished videos appear in your recent generations.

Vidu Q4 vs Vidu Q3: which should I use?

Use Vidu Q4 for up to 4K output, 1–15 reference images or reference audio. Vidu Q4 needs an image, so use Vidu Q3 Pro or Q3 Turbo for text-to-video or first-and-last-frame clips. For reference-to-video with 1–7 images, Vidu Q3 costs less per second than Vidu Q4, and Vidu Q3 Mix supports clips as short as 1 second.

Vidu Q4 vs Seedance 2.5 vs Kling 4.0: which should I use?

Use Vidu Q4 for up to 4K output from a first frame or up to 15 reference images; it costs $0.0912 per second at 720p for Gold members as of November 5, 2026, but has no text-to-video and clips stop at 16 seconds. Use Seedance 2.5 for up to 30 seconds at up to 1080p with text to video, video editing and extension, and up to 50 references. Use Kling 4.0 for 3–30 second clips at 720p or 1080p with stereo audio always on, plus editing and extension. Rates for Seedance 2.5 and Kling 4.0 are on their model pages.

Related Models

Explore more models in the same category.

View All Models →