imagestringrequired
URL of the start frame image.
Kling O3 Pro Image to Video
30% OFF
kwaivgi/kling-video/o3/pro/image-to-videoKling O3 Pro Image to Video by Kuaishou animates a start image, optionally toward an end image, into a 3-15 second 1080p video with optional native audio.
Try the model
Playground
Input
Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of the start frame image.
This field is required.
Additional Settings More
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of the end frame image (optional).
Video duration in seconds (3-15s). Allowed values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
Whether to generate native audio for the video.
List of prompts for multi-shot video generation.
The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. Allowed values: customize, intelligent.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "image": "https://static.sandbase.ai/examples/c6322fde-5914-45ea-9f6e-c5fe4046e468/input/75bc0aa2-3ce0-4abc-bf6a-8aa52557b53d.png", "prompt": "The character walks forward slowly, with the camera following from behind." }
Human preference
Arena
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
- Leaderboard
- Image to Video
- Rank
- #12 of 29
- Elo
- 1020 ±19
- Gap to #1
- −110
Image-to-video arena (silent): people pick the better of two clips animated from the same image, without seeing the model names; audio is not judged.
- #7FLUX 3 Max1058±19
- #8Grok Imagine Video 1.51054±19
- #9FLUX 31036±19
- #10HappyHorse-1.11024±19
- #11Gemini Omni Flash 1.11022±19
- #12Kling 3.0 Omni 1080p (Pro)1020±19
- #13HappyHorse-1.01014±19
- #14Grok Imagine Video 1.5 Lite1003±19
- #15Kling 3.0 1080p (Pro)1000
- #16PixVerse V6966±19
Also measured as Kling 3.0 Omni 1080p (Pro): Kling 3.0 Omni Pro Image to Video
Kling O3 Pro Image to Video
Kling O3 Pro image-to-video, the quality-first O3 tier. image anchors the first frame and an optional end_image sets the last; the prompt directs action and camera over 3–15 seconds.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 2,500 characters. |
image | image URL, required | — | First frame. JPEG, PNG, or WebP URL. |
end_image | image URL | — | Optional last frame. |
duration | 3–15 | 5 | Output length in seconds. |
generate_audio | boolean | false | Generate native audio with the clip. |
multi_prompt | object[] | — | Optional list of shots, each with its own prompt and duration. |
shot_type | customize / intelligent | customize | customize follows your multi_prompt shot list; intelligent lets the model plan the cuts. |
Billing
You pay for output seconds: $0.112 without audio and $0.14 with generate_audio.
| Output | Without audio | With audio |
|---|---|---|
| 3s | $0.336 | $0.42 |
| 5s (default) | $0.56 | $0.70 |
| 10s | $1.12 | $1.40 |
| 15s | $1.68 | $2.10 |
Failed runs are not charged.
Prompting
- Describe what moves, not what is already visible.
- With two frames, describe the transition between them.
Limits
- Clips are 3–15 seconds.
Also on SandBase
Other Kling O3 Pro endpoints and tiers: kwaivgi/kling-video/o3/pro/text-to-video, kwaivgi/kling-video/o3/pro/reference-to-video, kwaivgi/kling-video/o3/pro/edit, kwaivgi/kling-video/o3/pro/video-to-video, kwaivgi/kling-video/o3/standard/image-to-video, kwaivgi/kling-video/o3/4k/image-to-video.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "kwaivgi/kling-video/o3/pro/image-to-video",
"image": "https://static.sandbase.ai/examples/mirrored/0ff4703452ec-8ABMp4n9rh3kfD2Rq8fHd_start_frame.png",
"prompt": "The character walks forward slowly, with the camera following from behind.",
"duration": 10,
"end_image": "https://static.sandbase.ai/examples/alibaba/qwen-image-edit-plus-lora-gallery/add-background/output_url_1.png",
"shot_type": "customize",
"generate_audio": false
}
SANDBASE_JSON
)
run_id=$(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
promptstringrequired
Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.
durationinteger
Video duration in seconds (3-15s).
Default: 5
Possible values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
end_imagestring
URL of the end frame image (optional).
shot_typestring
The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.
Default: "customize"
Possible values: "customize", "intelligent"
multi_promptarray
List of prompts for multi-shot video generation.
generate_audioboolean
Whether to generate native audio for the video.
Default: false
{
"model": "kwaivgi/kling-video/o3/pro/image-to-video",
"image": "https://static.sandbase.ai/examples/mirrored/0ff4703452ec-8ABMp4n9rh3kfD2Rq8fHd_start_frame.png",
"prompt": "The character walks forward slowly, with the camera following from behind.",
"duration": 10,
"end_image": "https://static.sandbase.ai/examples/alibaba/qwen-image-edit-plus-lora-gallery/add-background/output_url_1.png",
"shot_type": "customize",
"generate_audio": false
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"poster": "https://static.sandbase.ai/examples/posters/d5c31361d3dbd34606cd.jpg",
"source": "Kling AI official schema mirror",
"source_url": "https://kling.ai/document-api/guides/get-started/overview",
"url": "https://static.sandbase.ai/examples/c6322fde-5914-45ea-9f6e-c5fe4046e468/output/eafecc38-d655-4aed-8c07-9cb64794c1ab.mp4"
}
]