Shengshu: Vidu Q3 Mix

Vidu Q3 Mix builds a video from supplied visual references and a written direction. It suits scenes assembled around several reference elements, where the goal is to combine those inputs into one moving composition.

Compare models

viduq3-mix

AvailableShengshuVideoAsync

Price: From $0.12
Modalities: Video

About Vidu Q3 Mix

Vidu Q3 Mix builds a video from several supplied visual references plus a written direction, combining those elements into one moving composition. It belongs to the Q3 generation, which Vidu documents with simultaneous audio and video output, and offers reference-to-video only. Use it for scenes assembled from distinct pieces, such as a character, a prop, and a location.

Where it works well

Several references can feed one clip, so a character, object, and setting are combined in a single generation.
It supports the 540p, 720p, and 1080p range used across Vidu's newer models.
Clips can be longer than in the Q2 series, per Vidu's documented range for Q3.

When to choose another model

No text-only, image-to-video, or frame-pair inputs exist on this variant.
Combining many references makes outcomes harder to predict, so expect several attempts to settle the composition.
Use plain Vidu Q3 if you only have one subject; Mix adds nothing then.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Reference to videoTokenLab endpoint

POST/v1/videos/generations

curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "reference-to-video",
  "output_audio": false,
  "model": "viduq3-mix",
  "prompt": "Cinematic sunrise over a calm lake with gentle camera motion.",
  "image_urls": [
    "https://example.com/reference.jpg"
  ]
}'

Parameters

Reference to video

Parameter	Values and limits	Default	Notes
`duration`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`image_url`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`image_urls`	Inputs: ≥ 1, ≤ 7	Not provided	Image aliases share a total of one to seven reference images. Do not add the limits together.
`output_audio`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`reference_images`	Inputs: ≥ 1, ≤ 7	Not provided	Image aliases share a total of one to seven reference images. Do not add the limits together.
`resolution`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.

Use this model for reference-to-video generation.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Reference to video · 720p

per second

Official price: $0.12
Verified price: —
Discount: —

Reference to video · 1080p

per second

Official price: $0.145
Verified price: —
Discount: —

	Official priceper second	Verified priceper second	Discount
Reference to video · 720p	$0.12	—	—
Reference to video · 1080p	$0.145	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 3:09 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Use cases

Assembling a scene from parts
Provide a character sheet, a prop, and a location image, and direct how they interact.
Ad concepts with multiple elements
Combine product, presenter, and background references into a short spot, then direct the action in the prompt for a first ad concept.
Game and animation previs
Show how an existing character moves through a new environment, using the character sheet and a location image as references.
Mood films
Merge several reference images into one coherent clip with its own sound.

Prompt examples

The astronaut from image one walks through the greenhouse from image two, carrying the lantern from image three, slow tracking shot.

Combine the chef, the market stall, and the copper pot references: the chef lifts the lid and steam fills the frame.

Place the girl and the paper kite in the empty stadium, evening light, she releases the kite and it rises.

FAQ

What is Vidu Q3 Mix?

It is a Q3-generation reference-to-video model. It combines multiple supplied visual elements and a text direction into one video, with sound handled as part of the same generation.

How is Mix different from Vidu Q3?

Both are reference-driven. Mix is positioned for scenes assembled around several references at once, while base Q3 centers on keeping a recognizable subject in a new shot.

Does it support audio?

Yes. Vidu documents simultaneous audio and video output for viduq3-mix, so plan the soundtrack as part of the prompt rather than adding it afterward in an editor.

Can I start from text only?

No. Only reference-to-video is listed for this model, so you must supply reference images. Use Vidu Q3 Pro or Turbo for scenes that start from a text description alone.

How much does Vidu Q3 Mix cost?

On TokenLab, Vidu Q3 Mix costs $0.12-$0.145 per second. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Vidu Q3 Mix use?

Use https://api.tokenlab.sh/v1/videos/generations for Vidu Q3 Mix. The request example below shows the matching code shape.

Which operations does Vidu Q3 Mix support?

Vidu Q3 Mix supports Reference to video. Select an operation above to see its endpoint and request example.