ShengshuvideoOperational

Vidu Q3 Mix API

Vidu's premium reference-to-video: up to 7 images, consistent subjects

shengshu/vidu-q3-mix/reference-to-video

FromUp to −9%

$0.11/s$0.12

per second of video · 720p

Open in Studio API

Try Vidu Q3 Mix

Runs on your balance at the price shown on the button. Results are saved to your account.

Open full-screen Studio

Prompt*

Type @ to point at a reference image0/5000

Reference images*

Up to 7 images for characters, products, style or scene. Refer to them in the prompt as @Image1, @Image2…

Aspect ratio

Output frame shape.

Resolution

Output resolution. Higher resolutions cost more per second.

Duration

Length of the generated clip in seconds (3–15s). You pay per second.

Estimated cost…

Create a free account with Google or email — pay only for what you generate.

Your video will appear here

Write a prompt, pick your settings and hit Run. You only pay for successful generations.

What is Vidu Q3 Mix?

Vidu Q3 Mix turns up to 7 reference images — characters, products, places — into 3–15 second 720p or 1080p videos with audio, keeping every subject consistent.

7 references

Characters, products, places

720p / 1080p

Premium quality

Audio included

Dialogue and effects

3–15 seconds

Pay per second

Your subjects, in motion

Attach up to seven reference images and describe the action. Q3 Mix keeps faces, outfits and products on-model and adds smart camera switching and sound.

Vidu Q3 Mix pricing

Pay per second of video. No subscription. Failed generations are refunded automatically.

Tier	Official price	Cheaper Gen.	You save
720p audio included	~~$0.12~~/s	$0.11/s	−8%
1080p audio included	~~$0.145~~/s	$0.132/s	−9%

Official price: Vidu API list price for viduq3-mix at $0.005 per credit (720p 24 credits = $0.12 / s, 1080p 29 = $0.145; audio included). Prices verified 2026-10-16.

Specifications

Resolutions: 720p · 1080p
Duration: 3–15 s
Aspect ratios: 16:9 · 9:16 · 1:1 · 4:3 · 3:4
References: 1–7 images
Released: Apr 13, 2026

Use Vidu Q3 Mix via API

One request to start a job, one to fetch the result. Same shape for every model.

Full API reference

import os, time, requests

API = "https://cheapergen.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['CHEAPERGEN_API_KEY']}"}

# 1. Submit the job
job = requests.post(f"{API}/run/shengshu/vidu-q3-mix/reference-to-video", headers=headers, json={
    "prompt": "@Image1 walks through the market from @Image2 holding the bag from @Image3, handheld tracking shot",
    "reference_image_urls": [
        "https://cdn.cheapergen.ai/samples/reference-1.jpg",
        "https://cdn.cheapergen.ai/samples/reference-2.jpg",
        "https://cdn.cheapergen.ai/samples/reference-3.jpg"
    ],
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5
}).json()

# 2. Poll until it finishes (or pass "webhook_url" and skip polling)
while job["status"] in ("queued", "running"):
    time.sleep(3)
    job = requests.get(f"{API}/generations/{job['id']}", headers=headers).json()

print(job["status"], job["output"]["video"]["url"] if job["status"] == "succeeded" else job["error"])

const API = "https://cheapergen.com/api/v1";
const headers = {
  Authorization: `Bearer ${process.env.CHEAPERGEN_API_KEY}`,
  "Content-Type": "application/json",
};

// 1. Submit the job
let job = await fetch(`${API}/run/shengshu/vidu-q3-mix/reference-to-video`, {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "@Image1 walks through the market from @Image2 holding the bag from @Image3, handheld tracking shot",
    "reference_image_urls": [
      "https://cdn.cheapergen.ai/samples/reference-1.jpg",
      "https://cdn.cheapergen.ai/samples/reference-2.jpg",
      "https://cdn.cheapergen.ai/samples/reference-3.jpg"
    ],
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5
  }),
}).then((r) => r.json());

// 2. Poll until it finishes (or pass webhook_url and skip polling)
while (job.status === "queued" || job.status === "running") {
  await new Promise((r) => setTimeout(r, 3000));
  job = await fetch(`${API}/generations/${job.id}`, { headers }).then((r) => r.json());
}

console.log(job.status === "succeeded" ? job.output.video.url : job.error);

curl -X POST https://cheapergen.com/api/v1/run/shengshu/vidu-q3-mix/reference-to-video \
  -H "Authorization: Bearer $CHEAPERGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "prompt": "@Image1 walks through the market from @Image2 holding the bag from @Image3, handheld tracking shot",
  "reference_image_urls": [
    "https://cdn.cheapergen.ai/samples/reference-1.jpg",
    "https://cdn.cheapergen.ai/samples/reference-2.jpg",
    "https://cdn.cheapergen.ai/samples/reference-3.jpg"
  ],
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": 5
}'

Reference to Video

shengshu/vidu-q3-mix/reference-to-video

Example prompts

Hit “Try it” to load a prompt into the playground above.

Reference to Video
@Image1 unboxes the sneakers from @Image2 at a desk and grins at the camera
Try it
Reference to Video
@Image1 and @Image2 dance together in the ballroom from @Image3, slow orbit
Try it

Vidu Q3 Mix FAQ

Vidu Q3 Mix is billed per second of output video at the selected resolution. Audio is included at no extra cost, and failed generations are never charged.

Yes. Requests run on Shengshu's Vidu Q3 Mix through official API channels, at a lower price than Vidu's own list price.

Attach 1–7 images and mention them in the prompt as @Image1, @Image2… Describe the action and camera; appearance comes from the images.

Yes, subject to Vidu's terms of use and our Terms of Service.

Related models

Shengshu

NewUp to −6%

ViduQ4

Image · Reference → Video

from$0.113/s$0.12

Vidu's newest model — up to 4K, 15 reference images and voice references

Shengshu

Best valueUp to −5%

ViduQ3 Turbo

Text · Image → Video

from$0.033/s$0.035

Fast, low-cost Vidu Q3 with audio, 1–16 s

Kuaishou

NewUp to −12%

Kling3.0 Omni

Text · Image · Reference → Video

from$0.074/s$0.084

Kling 3.0 with multi-image references for consistent characters

Vidu Q3 Mix is developed by Shengshu. Cheaper Gen. provides API access through official upstream endpoints and does not own the model. Trademarks belong to their respective owners. · Markdown · OpenAPI