imagestring
Optional first-frame image URL for image-to-video.
Kling O3
30% OFF
kwaivgi/kling-video/o3Kling O3 by Kuaishou is a single entry point for Kling 3.0 Omni video: text, image, reference, and video-guided generation in Standard, Pro, or 4K quality, with optional native audio.
Try the model
Playground
Input
Text prompt for video generation or transformation. When using reference media, refer to them as @Image1, @Image2, and @Video1.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Optional first-frame image URL for image-to-video.
Optional reference video URL for video-to-video generation.
Additional Settings More
Customize your input with more control.
Generation quality tier. Allowed values: standard, pro, 4k.
Allowed values: image, video.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Optional end-frame image URL for image-to-video.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Optional reference image URLs.
Generated video duration in seconds. Allowed values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
Allowed values: 16:9, 9:16, 1:1.
Allowed values: customize, intelligent.
Enter a JSON array.
ResultIdle
Your output will appear here
Complete the inputs, then click Run.
Kling O3
A single endpoint for Kling O3: text-to-video, image-to-video (with optional end frame), reference images, and video reference in one schema. Pick the tier with resolution.
Pick an input mode
| Mode | Send |
|---|---|
| Text | prompt only |
| Frames | image, optional end_image |
| References | images (refer to them as @Image1, …) |
| Video reference | video, optional images |
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 2,500 characters. |
resolution | standard / pro / 4k | standard | Tier: standard, pro, or 4k; sets the per-second rate. |
image | image URL | — | Optional first frame. |
video | video URL | — | Optional reference video. |
keep_original_sound | boolean | true | Keep the reference video's audio track. |
character_orientation | image / video | — | video follows the reference video's orientation (better for complex moves, up to 30s); image follows the image (better for camera moves, up to 10s). |
end_image | image URL | — | Optional last frame. |
images | image URL[] | — | Reference images, referred to as @Image1, @Image2, … in the prompt. |
duration | 3–15 | 5 | Output length in seconds. |
aspect_ratio | 16:9 / 9:16 / 1:1 | 16:9 | Output frame shape. |
generate_audio | boolean | true | Generate native audio with the clip. |
shot_type | customize / intelligent | customize | customize follows your multi_prompt shot list; intelligent lets the model plan the cuts. |
multi_prompt | object[] | — | Optional list of shots, each with its own prompt and duration. |
Billing
You pay per output second. Standard: $0.112 with audio, $0.084 without. Pro: $0.14 with audio, $0.112 without. 4K: $0.42. With a reference video: $0.126 (standard) or $0.168 (pro).
| Output | standard | pro | 4k |
|---|---|---|---|
| 5s with audio | $0.56 | $0.70 | $2.10 |
| 5s without audio | $0.42 | $0.56 | $2.10 |
| 5s with reference video | $0.63 | $0.84 | $2.10 |
| 10s with audio | $1.12 | $1.40 | $4.20 |
Failed runs are not charged.
Prompting
- Describe subject, action, camera move, and light in order.
- For several shots, use
multi_promptwith one entry per shot. - Refer to references as @Image1, @Video1.
Limits
- Clips are 3–15 seconds.
Also on SandBase
Related: kwaivgi/kling-video/o3/pro/text-to-video (single-mode endpoint), kwaivgi/kling-video/o3/pro/image-to-video (single-mode endpoint).
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "kwaivgi/kling-video/o3",
"image": "https://static.sandbase.ai/examples/mirrored/f77b827ca02a-TNErq9yD7ZxGRATjfAqnh_EIgJSN67.png",
"video": "https://static.sandbase.ai/examples/mirrored/f1ecbb471a16-hklvF__w53diz6Rve7f5__JuDW2xl0mr6sJ_Kjz3Vxe_vidoeook--1-_1.mp4",
"prompt": "Based on @Video1, make the character from @Image1 dance.",
"duration": 5,
"shot_type": "customize",
"resolution": "standard",
"aspect_ratio": "16:9",
"generate_audio": true,
"keep_original_sound": true,
"character_orientation": "image"
}
SANDBASE_JSON
)
run_id=$(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"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
videostring
Optional reference video URL for video-to-video generation.
imagesarray
Optional reference image URLs.
promptstringrequired
Text prompt for video generation or transformation. When using reference media, refer to them as @Image1, @Image2, and @Video1.
durationinteger
Generated video duration in seconds.
Default: 5
Possible values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
end_imagestring
Optional end-frame image URL for image-to-video.
shot_typestring
Default: "customize"
Possible values: "customize", "intelligent"
resolutionstring
Generation quality tier.
Default: "standard"
Possible values: "standard", "pro", "4k"
aspect_ratiostring
Default: "16:9"
Possible values: "16:9", "9:16", "1:1"
multi_promptarray
generate_audioboolean
Default: true
keep_original_soundboolean
Default: true
character_orientationstring
Possible values: "image", "video"
{
"model": "kwaivgi/kling-video/o3",
"image": "https://static.sandbase.ai/examples/mirrored/f77b827ca02a-TNErq9yD7ZxGRATjfAqnh_EIgJSN67.png",
"video": "https://static.sandbase.ai/examples/mirrored/f1ecbb471a16-hklvF__w53diz6Rve7f5__JuDW2xl0mr6sJ_Kjz3Vxe_vidoeook--1-_1.mp4",
"prompt": "Based on @Video1, make the character from @Image1 dance.",
"duration": 5,
"shot_type": "customize",
"resolution": "standard",
"aspect_ratio": "16:9",
"generate_audio": true,
"keep_original_sound": true,
"character_orientation": "image"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
No example output has been published yet. Use Playground → Result → JSON after a completed run to inspect your response.