API Free WeekHundreds of APIs are free to call this week.Browse free APIs

Vidu Q4 Reference to Video

vidu/q4/reference-to-video

Vidu Q4 Preview by Shengshu builds a 3 to 16 second video at up to 4K from up to 12 reference images and 3 voice clips, keeping characters, products, and voices consistent across the clip.

Base price
$0.47USD / run
Execution
async
Model type
video
Input fields
8
Production route

Try the model

Playground

Open playground
Input
Text prompt for video generation, max 5000 characters. Refer to references by position: [@reference_image_1], [@reference_image_2], ... for images and [reference_audio_1], [reference_audio_2], ... for audio clips.

PNG, JPEG, WebP, or GIF · 20 MiB maximum each · up to 12

URLs of 1 to 12 reference images (png, jpeg, jpg, webp) used to keep characters, products, objects, or locations consistent.
URLs of up to 3 mp3 reference audio clips (3-12 seconds each, max 50 MB) used to keep voices consistent.
The aspect ratio of the output video. Allowed values: 16:9, 9:16, 4:3, 3:4, 1:1.
Whether to generate audio (dialogue and sound effects) with the video. When false, the output video is silent.
Output video resolution. Sets the per-second rate. Allowed values: 540p, 720p, 1080p, 2K, 4K.
316
Duration of the video in seconds (3-16) Range: 3 to 16.
Random seed for reproducibility. If None, a random seed is chosen.
OutputExample

Examples

Select an example to load its inputs and result into the playground.

Model card

Specifications

Pricing

Base price
$0.47 / run

Context & modalities

Input
Schema-defined
Output
video

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
Vidu
Model ID
vidu/q4/reference-to-video
Execution
async
Base URL
https://api.sandbase.ai
API
Unified Run API
Endpoint
/v1/run

API README

Vidu Q4 Reference to Video

Vidu Q4 Preview reference-to-video: build a 3–16 second clip at up to 4K from up to 12 reference images and 3 voice clips, keeping characters, products, and voices consistent.

Fields

FieldTypeDefaultNotes
promptstring, required—Up to 5,000 characters. Tag references as [@reference_image_1] and [reference_audio_1].
reference_image_urlsimage URL[], required—1–12 images of characters, products, objects, or locations.
reference_audio_urlsaudio URL[]—Up to 3 mp3 clips, 3–12 seconds each, for voice consistency.
aspect_ratio16:9 / 9:16 / 4:3 / 3:4 / 1:116:9Output frame shape.
audiobooleantrueGenerate dialogue and sound effects. Same price on or off.
resolution540p / 720p / 1080p / 2K / 4K720pSets the per-second rate.
durationinteger 3–165Output length in seconds.
seedintegerrandomFix it to compare prompt changes.

Billing

You pay for output seconds: $0.045 at 540p, $0.095 at 720p, $0.12 at 1080p, $0.19 at 2K, $0.39 at 4K.

Output540p720p1080p2K4K
3s$0.135$0.285$0.36$0.57$1.17
5s (default)$0.225$0.475$0.60$0.95$1.95
8s$0.36$0.76$0.96$1.52$3.12
16s$0.72$1.52$1.92$3.04$6.24

Failed runs are not charged.

Prompting

  • Refer to each reference by its position in the list, for example [@reference_image_2] holds the product.
  • Describe subject, action, camera, and sound. Put spoken lines in quotes.

Also on SandBase

vidu/q4/image-to-video animates a single first frame. Vidu Q3 endpoints such as vidu/q3/reference-to-video/mix remain available.

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
vidu/q4/reference-to-video
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "vidu/q4/reference-to-video",
  "audio": true,
  "prompt": "[@reference_image_1] walks along the beach at sunset holding [@reference_image_2], then turns to the camera and smiles.",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "reference_image_urls": [
    "https://storage.googleapis.com/falserverless/web-examples/vidu/new-examples/reference1.png",
    "https://storage.googleapis.com/falserverless/web-examples/vidu/new-examples/reference2.png"
  ]
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All image & video models
ModelTypeDefault priceReleased
ViduVideo$0.47 / runOct 7, 2026
ViduVideo$0.47 / runOct 7, 2026
ViduVideo$0.77 / runApr 8, 2026
ViduVideo$0.39 / runFeb 6, 2026
ViduVideo$0.39 / runFeb 6, 2026
ViduVideo$0.77 / runJan 31, 2026

Questions

FAQ

How do I call Vidu Q4 Reference to Video through SandBase?

Create a SandBase API key, then send requests with the model ID "vidu/q4/reference-to-video" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

Do I need a separate Vidu account?

No. One SandBase API key and balance gives you access to Vidu Q4 Reference to Video and the other models in the catalog; you do not need to sign up with Vidu separately.