Shengshu: Vidu Q3 Pro

Vidu Q3 Pro supports text-led scenes, image animation, and transitions between planned frames. It is useful for audiovisual shots where a creator wants to define both the starting composition and the sequence that follows.

Compare models

viduq3-pro

AvailableShengshuVideoAsync

Price: From $0.10
Modalities: Video

About Vidu Q3 Pro

Vidu Q3 Pro is the most flexible video model in Shengshu's Q3 line, covering text-to-video, image-to-video, and start-to-end frame generation. Vidu's model map documents simultaneous audio and video output and smart scene cuts for it, with 540p to 1080p resolutions. Choose it when one shot needs both a planned opening composition and a following sequence with sound.

Where it works well

Text, image, and frame-pair inputs in one model cover most ways of starting a clip.
Vidu documents audio generated together with the picture, so a clip can leave the model with sound.
Smart scene cuts, as described in Vidu's model map, allow multi-shot results from one prompt.
Longer clips than the Q2 series are documented for Q3.

When to choose another model

It takes no reference-to-video input; the Q3 base and Mix variants cover subject references.
For quick low-cost drafts, Q3 Turbo is the better fit.
Scene cuts and generated audio may need prompt iteration to match your intent.

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.

Image to videoStart and end frames to videoText 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 '{
  "aspect_ratio": "16:9",
  "duration": 5,
  "operation": "text-to-video",
  "output_audio": true,
  "resolution": "720p",
  "model": "viduq3-pro",
  "prompt": "Cinematic sunrise over a calm lake with gentle camera motion."
}'

Parameters

Image to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	文生视频: 16:9 / 9:16 / 3:4 / 4:3 / 1:1；图生/首尾帧: 官方未公开独立 aspect_ratio（按输入图比例约束）. The omitted-field default is not verified.
`audio`	true, false	Not provided	Not provided
`bgm`	false	Not provided	Not provided
`duration`	Not provided	Not provided	1-16s. The omitted-field default is not verified.
`end_image`	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`	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.
`operation`	Not provided	Not provided	Not provided
`output_audio`	true, false	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`Required	540p, 720p, 1080p	Not provided	Not provided
`start_image`	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.

Audio generation defaults to true; set output_audio or audio to false for silent output. BGM is not a separate supported control for Q3.

Start and end frames to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	文生视频: 16:9 / 9:16 / 3:4 / 4:3 / 1:1；图生/首尾帧: 官方未公开独立 aspect_ratio（按输入图比例约束）. The omitted-field default is not verified.
`audio`	true, false	Not provided	Not provided
`bgm`	false	Not provided	Not provided
`duration`	Not provided	Not provided	1-16s. The omitted-field default is not verified.
`end_image`	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`	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.
`operation`	Not provided	Not provided	Not provided
`output_audio`	true, false	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`Required	540p, 720p, 1080p	Not provided	Not provided
`start_image`	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.

Audio generation defaults to true; set output_audio or audio to false for silent output. BGM is not a separate supported control for Q3.

Text to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	文生视频: 16:9 / 9:16 / 3:4 / 4:3 / 1:1；图生/首尾帧: 官方未公开独立 aspect_ratio（按输入图比例约束）. The omitted-field default is not verified.
`audio`	true, false	Not provided	Not provided
`bgm`	false	Not provided	Not provided
`duration`	Not provided	Not provided	1-16s. The omitted-field default is not verified.
`end_image`	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`	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.
`operation`	Not provided	Not provided	Not provided
`output_audio`	true, false	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`Required	540p, 720p, 1080p	Not provided	Not provided
`start_image`	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.

Audio generation defaults to true; set output_audio or audio to false for silent output. BGM is not a separate supported control for Q3.

Use TokenLab create endpoint and follow returned poll_url; if you need a fixed status path, use `/v1/tasks/{id}`.

Audio generation defaults to true; set output_audio or audio to false for silent output. BGM is not a separate supported control for Q3.

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.

Text to video / Image to video / Start and end frames to video · 540p

per second

Official price: $0.045
Verified price: —
Discount: —

Text to video / Image to video / Start and end frames to video · 720p

per second

Official price: $0.10
Verified price: —
Discount: —

Text to video / Image to video / Start and end frames to video · 1080p

per second

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

	Official priceper second	Verified priceper second	Discount
Text to video / Image to video / Start and end frames to video · 540p	$0.045	—	—
Text to video / Image to video / Start and end frames to video · 720p	$0.10	—	—
Text to video / Image to video / Start and end frames to video · 1080p	$0.12	—	—

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, 2:02 PM UTC

Metrics appear once privacy and data volume thresholds are met.

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

Open in Console

Open Vidu Q3 Pro in Console with a prompt ready to edit or send.

Help me create with viduq3-pro using text-to-video at /v1/videos/generations. Show the result, status, and cost.

Use cases

Best for

Text to Video

Audio-visual shots
Create a clip with sound already in it, such as a street scene with ambient noise.
Planned opening frame
Start from an approved image and ask for the next few seconds of action.
Two-frame transitions
Define the start and the end composition and let the model build the movement between.
Multi-shot promos
Describe a short sequence and let the model place cuts within it.

Prompt examples

Two chefs argue in a busy kitchen, camera cuts to a close-up of the sizzling pan, clattering pans and shouting in the background.

From this empty beach frame to this sunset frame, waves roll in and gulls call.

A cyclist rides through morning fog in a forest, slow orbit, birdsong and tire hum.

FAQ

What is Vidu Q3 Pro?

It is the full-featured Q3 video model from Shengshu, with text-to-video, image-to-video, and start-to-end frame operations, and output at 540p, 720p, and 1080p, suited to final delivery.

Does it generate audio?

Yes, per Vidu's documentation: the model map lists simultaneous audio and video output for viduq3-pro. Describe the sounds you want directly in the prompt alongside the visuals.

How does it differ from Q3 Turbo?

Turbo is the rapid-iteration tier for the same kinds of tasks. Pro is the version to use for the clip you intend to deliver, once the idea has been tested.

What are smart scene cuts?

Vidu's model map notes that Q3 Pro can introduce cuts between shots within a clip, so a single prompt can produce a short multi-shot sequence.

Should I use Q3 Pro instead of Q2 Pro?

If you need audio, text prompts, or longer clips, yes. Q2 Pro remains an option when you need reference-to-video, which Q3 Pro does not offer.

How much does Vidu Q3 Pro cost?

On TokenLab, Vidu Q3 Pro costs $0.045-$0.12 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 Pro use?

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

Which operations does Vidu Q3 Pro support?

Vidu Q3 Pro supports Image to video, Start and end frames to video, Text to video. Select an operation above to see its endpoint and request example.