Seedance 2.5 is live — 30-second cinematic video with native audio & real-person references

Vidu Q3 API — Async Video Generation in One Endpoint

The Vidu Q3 API turns text or up to two images into a 1 to 16 second clip at 540p, 720p, or 1080p. One endpoint covers text-to-video, image-to-video, and first/last-frame transitions, audio built in.

Highlights
1–16 s · 540p–1080p · first / last frame control
Best for
Anime, transitions, image animation
Input
Text, plus up to 2 images
Output
Video, optional audio
Input

≤ 2000 chars · required when image_urls is empty

Default 720p

Ignored when image_urls is set

5

1 to 16 · default 5

Default on

[-1, 4294967295] · -1 means random

Result

Try one of these prompts

What is the Vidu Q3 API?

Vidu Q3 is Vidu's async video generation model, offered on reAPI as two variants — viduq3-pro and viduq3-turbo — that share one endpoint and one parameter shape. The mode follows the number of images you send: none for text-to-video, one for image-to-video, two for a first/last-frame transition, with output running 1 to 16 seconds at 540p, 720p or 1080p and audio on by default. Billing is per second, at a rate set by variant and resolution.

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Animate a single still with the Vidu Q3 API

Pass one image and a motion prompt. The Vidu Q3 API returns a 1 to 16 second clip from the same endpoint as your text-to-video calls — no model swap, no extra integration. The aspect ratio of your output matches the source frame automatically.

Generate a clip

Smooth transitions between two frames with the Vidu Q3 API

Send two images and the Vidu Q3 API interpolates motion from the first frame to the last. Skip storyboarding and stitch keyframes directly into a finished shot — useful for transformations, day-to-night reveals, and product before/after spots.

Text-to-video with built-in audio via the Vidu Q3 API

Describe the scene, pick an aspect ratio, and the Vidu Q3 API returns a clip with dialogue and sound effects already mixed in. No timeline, no second TTS pipeline, no syncing pass on top of the render.

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost
$0.184184 credits

One 5-second sample at the cheapest tier.

Testing budget guide
Add credits
$10
≈ 54 tests
$50
≈ 271 tests
$100
≈ 543 tests
ModelCategoryPrice
viduq3-pro540p
$0.065
65 credits · 1 second
720p
$0.138
138 credits · 1 second
1080p
$0.148
148 credits · 1 second
viduq3-turbo540p
$0.037
37 credits · 1 second
720p
$0.056
56 credits · 1 second
1080p
$0.065
65 credits · 1 second

Why reAPI

One endpoint, three modes

The Vidu Q3 API picks its mode from the count of image_urls you send. Zero gives you text-to-video, one gives image-to-video, two gives first/last-frame interpolation — all on the same /api/v1/videos/generations call, with the same authentication and the same task polling pattern.

Pricing by resolution × seconds

The Vidu Q3 API charges per second and resolution only. Turbo undercuts Pro at every tier. See current 540p / 720p / 1080p rates in the pricing table on this page. Mode never shifts the rate, audio is included, and failed Vidu Q3 API jobs refund automatically.

Audio built into the Vidu Q3 API

Audio is on by default — dialogue, ambience, and effects ship inside the same MP4. Set audio to false in the Vidu Q3 API request body when you want a silent clip; the per-second rate stays the same either way.

Ship the Vidu Q3 API in three steps

  1. step 01

    Create an API key

    Sign up and grab a key from the dashboard. Free credits cover your first Vidu Q3 API calls — no card required.

    Open
  2. step 02

    Submit a video task

    POST to /api/v1/videos/generations with model = viduq3-pro or viduq3-turbo. The Vidu Q3 API returns a task ID immediately so your worker can move on.

    Open
  3. step 03

    Poll the result

    GET /api/v1/tasks/:id until status is completed. Download the Vidu Q3 API output and ship it.

    Open
docs/api/viduq3

API reference

Drop-in code and the full parameter table.

curl -X POST https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "viduq3-pro",
    "prompt": "A kitten playing piano, slow camera push-in",
    "duration": 8,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

The Vidu Q3 API is an async video generation endpoint with two variants — viduq3-pro and viduq3-turbo. One request body covers text-to-video, image-to-video, and first/last-frame interpolation; the Vidu Q3 API auto-routes the mode by how many images you attach.

start building

Ready to ship?

Try it in the playground or grab an API key to integrate now.