kwaivgi/kling-video/o3/pro/reference-to-video
Kling Video O3 Pro is KwaiVGI's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runkwaivgi/kling-video/o3/pro/reference-to-videoInput Schema
9 parameters · 2 required · 7 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | Image to use as the first frame of the video. |
prompt | string | Required | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. · Max length: 2500 |
images | string[] | Optional | Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video. |
duration | integer | Optional | Video duration in seconds (3-15s). · Options: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 · Default: 5 3456789101112131415 |
end_image | string | Optional | Image to use as the last frame of the video. |
shot_type | string | Optional | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. · Options: customize, intelligent · Default: "customize" customizeintelligent |
aspect_ratio | string | Optional | The aspect ratio of the generated image. · Options: 16:9, 9:16, 1:1 16:99:161:1 |
multi_prompt | object[] | Optional | List of prompts for multi-shot video generation. |
generate_audio | boolean | Optional | Whether to generate native audio for the video. · Default: false |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "kwaivgi/kling-video/o3/pro/reference-to-video",
"image": "https://static.sandbase.ai/examples/mirrored/ec18b1edee80-myilPNN_WYdJCmpTy4Sjr_6XNBi9Mm.png",
"prompt": "@Element1 and @Element2 enters the scene from two sides. Elephant starts to play with the ball",
"duration": 8,
"shot_type": "customize",
"generate_audio": false
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Kling Video O3 Pro
Kling Video O3 Pro is a multi-reference video-generation route in the Kling Video O3 family. It turns written scene direction plus supplied visual references into a multi-second sequence with controlled subject action, camera movement, shot structure, and optional synchronized sound.
The Pro route is intended for creators who need dependable temporal continuity across a directed clip. Prompts can describe staging, motion, lens behavior, atmosphere, and audio cues; multi-prompt controls can divide the sequence into several shots while reference inputs keep important visual elements anchored.
Highlights
- Multi-reference continuity. Uses reference imagery to carry subjects and visual identity through the generated sequence.
- Multi-shot direction. Supports structured prompt segments for sequences that need more than one planned shot.
- Native audio option. Can generate sound together with the visible action when the route exposes audio generation.
- Professional-detail output. Uses the Pro route when finer visual fidelity is more important than the lower-cost Standard tier.
Pricing
| Configuration | Billing unit | Price |
|---|---|---|
| 3 seconds | Without generated audio | $0.336 |
| 3 seconds | With generated audio | $0.420 |
| 4 seconds | Without generated audio | $0.448 |
| 4 seconds | With generated audio | $0.560 |
| 5 seconds | Without generated audio | $0.560 |
| 5 seconds | With generated audio | $0.700 |
| 6 seconds | Without generated audio | $0.672 |
| 6 seconds | With generated audio | $0.840 |
| 7 seconds | Without generated audio | $0.784 |
| 7 seconds | With generated audio | $0.980 |
| 8 seconds | Without generated audio | $0.896 |
| 8 seconds | With generated audio | $1.120 |
| 9 seconds | Without generated audio | $1.008 |
| 9 seconds | With generated audio | $1.260 |
| 10 seconds | Without generated audio | $1.120 |
| 10 seconds | With generated audio | $1.400 |
| 11 seconds | Without generated audio | $1.232 |
| 11 seconds | With generated audio | $1.540 |
| 12 seconds | Without generated audio | $1.344 |
| 12 seconds | With generated audio | $1.680 |
| 13 seconds | Without generated audio | $1.456 |
| 13 seconds | With generated audio | $1.820 |
| 14 seconds | Without generated audio | $1.568 |
| 14 seconds | With generated audio | $1.960 |
| 15 seconds | Without generated audio | $1.680 |
| 15 seconds | With generated audio | $2.100 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The project needs creating a directed video sequence | The goal is a different media task or endpoint |
| The available inputs match the required local schema | Required source media or permissions are unavailable |
| The brief can specify subject, composition, style, and delivery | The result must be deterministic at pixel or sample level |
| The supported formats and controls match final placement | Delivery requires unsupported dimensions, codecs, or duration |
| An asynchronous generated result fits the workflow | A live, frame-synchronous, or real-time response is mandatory |
Prompt Guide
Write the request as a production brief: identify the main subject or source material, state the intended transformation, describe composition or timing, and finish with style, atmosphere, and delivery constraints. Keep preservation requirements separate from requested changes, and use only fields exposed by this route.
{
"prompt": "A cinematic, precisely directed scene with clear subject action, camera movement, lighting, and atmosphere",
"image": "https://example.com/reference.jpg",
"images": [
"https://example.com/reference.jpg"
],
"duration": 3,
"end_image": "https://example.com/reference.jpg"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | kwaivgi/kling-video/o3/pro/reference-to-video |
| Input fields | image (string)<br>images (array)<br>prompt (string)<br>duration (integer; 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15)<br>end_image (string)<br>shot_type (string; customize, intelligent)<br>aspect_ratio (string; 16:9, 9:16, 1:1)<br>multi_prompt (array)<br>generate_audio (boolean) |
| Required input | prompt, image |
| Output fields | url, content_type |
| Execution | Asynchronous job |
Related Models
kwaivgi/kling-video/o3/pro/image-to-videokwaivgi/kling-video/o3/standard/reference-to-videokwaivgi/kling-video/o3/standard/text-to-video

