Vidu Q3 Pro
Vidu Q3 Pro text-to-video, image-to-video and start-end frame video. Pass image_url for a first-frame image, add image_end_url for start-end frame generation, or omit both for pure text-to-video.
This model does not support reference images. For reference-image video generation use viduq3_turbo_reference — passing image_urls here returns an error.
Pricing — per second of generated video, in tokens (USD at $0.02/token):
| resolution | tokens/s | USD/s |
|---|---|---|
| 540p | 2.25 | $0.045 |
| 720p | 5 | $0.10 |
| 1080p | 6 | $0.12 |
Example: an 8s 720p video costs 40 tokens.
Returns an img_uuid; poll GET /api/v1/jobs/detail (or use custom_callback_url) to get the generated video.
Headers
Body
Model name. Must be viduq3_pro.
viduq3_pro Text prompt describing the video.
Optional first-frame image URL. If provided, runs image-to-video; otherwise text-to-video.
Optional last-frame image URL. Pass together with image_url for start-end frame video generation.
Video duration in seconds (1-16). Defaults to 5.
1 <= x <= 16Output resolution.
540p, 720p, 1080p Aspect ratio for text-to-video.
Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt.
"https://your-server.com/goenhance/callback"
