Introduction
Kling O3 Image to video animates your own opening frame. Upload an image, optionally add a closing frame to pin the ending, and describe what happens in between - the prompt field takes up to 2,500 characters. Choose a length of 3 to 15 whole seconds, a resolution up to 4K, and whether to generate native audio with the picture.
Choose a Kling O3 mode by starting material
| What you have at the start | Mode |
|---|---|
| a written scene and nothing else | Kling O3 Text to video |
| an approved opening frame | Kling O3 Image to video |
| up to 7 reference photos | Kling O3 Reference to video |
| a video you already have | Kling O3 Video edit |
Key features
The opening frame is followed closely
Whoever and whatever is in your frame - the people, the wardrobe, the room - is what the clip keeps. In our umbrella example, the two women's faces matched the opening frame all the way through a five-second clip; the prompt only had to describe the new action.
An optional closing frame pins the ending
Add last_image_url and the clip is built to land on that frame instead of wherever the model would otherwise stop. Keep the two frames close in light, angle and framing - a large jump between them is what makes the middle of a long clip wander.
Sound generated with the motion
generate_audio adds dialogue, effects and ambience in the same pass as the animation, timed to the action you describe rather than added in a separate step afterward.
Request parameters
| Parameter | Required | Description |
|---|---|---|
duration_seconds | No | How long the clip runs. You pay per second. ≥ 3 · ≤ 15 · Default: 5 |
generate_audio | No | Adds sound made to match the picture: voices, ambience and effects. Default: false |
image_url | Yes | The picture to start from. |
last_image_url | No | Optional final frame, so the clip ends exactly where you want. |
multi_prompt | No | Shot list for shot_type customize: one entry per shot, in order, each with its own prompt and length in seconds. The lengths must add up to duration_seconds. |
prompt | Yes | Describe what happens after the opening frame: the action, the camera and, with sound on, the sounds. |
resolution | No | Output size. Bigger sizes look sharper and cost more. 720p · 1080p · 4k · Default: 720p |
shot_type | No | single keeps one continuous shot; multi lets the model cut the prompt into several shots on its own; customize follows the shot list you give in multi_prompt. single · multi · customize · Default: single |
Pricing
Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.
| Option | Credits per second | ≈ USD |
|---|---|---|
| generate_audio false · resolution 720p | 10.08 | $0.10 |
| generate_audio false · resolution 1080p | 13.44 | $0.13 |
| generate_audio true · resolution 720p | 13.44 | $0.13 |
| generate_audio true · resolution 1080p | 16.8 | $0.17 |
| generate_audio false · resolution 4K | 50.4 | $0.50 |
| generate_audio true · resolution 4K | 50.4 | $0.50 |
Each task is rounded up to whole credits, so one run at the lowest tier costs 51 credits for a 5-second clip ($0.51).
For an exact number before you run, send the same body to POST /jobs/quote.
Use cases
Animate a frame you have already approved
When the exact people, wardrobe and composition matter, generate or select the still first, then send it here instead of leaving those details to a text prompt - which redraws them fresh on every run.
Bridge two frames you already have
With both image_url and last_image_url set, the clip fills in a believable motion path between an approved start and an approved end - useful for a scene that has to land on a specific final composition.
Add dialogue to a still you already like
Turn on generate_audio and describe a line of dialogue along with the action; the frame supplies the look, the prompt supplies the movement and the words.
Prompt guide & pro tips
Describe the after, not the already-there
Do not redescribe who is in the frame or what they are wearing - the image already answers that. Spend the prompt on what changes: the action, the camera move, the sound.
Keep a closing frame close to the opening one
If you use last_image_url, choose or generate a frame with similar light and framing to the opening image. A near match keeps the motion in between believable; a big jump asks the model to invent more than it can hold steady.
Lock the take when continuity matters
Shot_type single is a preference, not a guarantee. For a scene that must not cut - a single unbroken reaction, for instance - add "one continuous shot, no cuts" to the end of the prompt.
API quick start
Call the Kling O3 API in three steps
- Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
- Send the request. POST /jobs/createTask with model kling/o3/image-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
- Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-d '{
"model": "kling/o3/image-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single"
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.
Kling O3 API questions
How much does the Kling O3 API cost?
Kling O3 starts at 51 credits ($0.51) for a 5-second clip with Image to Video, its cheapest task. Prices by option: false · 720p 10.08 credits per second, false · 1080p 13.44 credits per second, true · 720p 13.44 credits per second, true · 1080p 16.8 credits per second. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.
What is the model name for Kling O3 in the API?
Put kling/o3/text-to-video for Create Video; kling/o3/image-to-video for Image to Video; kling/o3/reference-to-video for Reference to Video; kling/o3/video-edit for Edit Video in the model field of POST /jobs/createTask.
What is Kling O3?
It is Kling's own name for what the market calls Kling 3.0 Omni: one model that covers text-to-video, image-to-video, reference-to-video and video-edit, with optional native sound and automatic multi-shot cuts.
Can I edit a video I already have?
Yes, with video-edit. Upload the clip and describe only what should change - season, wardrobe, backdrop, style - and everything you do not mention carries over. The result runs exactly as long as your source clip.
How many reference images can I use?
Up to seven on reference-to-video, and up to four optional ones on video-edit for a new character, outfit or object. Give each photo one job in the prompt and call it out as <<<image_1>>>, <<<image_2>>> and so on.
Does Kling O3 generate sound?
Yes, as an option on text-to-video, image-to-video and reference-to-video: turn on generate_audio and dialogue, effects and ambience come back in the same file as the picture. Video-edit has no audio switch.
What are the limits of the Kling O3 API?
Clip length: 3–15 s; Resolutions: 720p · 1080p · 4K; Prompt length (characters): 2,500; Largest upload: 10 MB. Requests outside these limits are rejected before anything is charged.
Can I try Kling O3 without writing code?
Yes. The Playground runs Kling O3 on your PopNow credits, needs no API key, and shows the matching code for every run.
All Kling models
Kling 3.0 is the pick for a single polished shot with first and last frames or Motion Control. O3 wins when you need reference photos, video editing or several modes in one place.
- Kling 3.0 API4K clips, multi-shot cuts and motion controlFrom 51 credits for a 5-second clip
- Kling O3 APIKling’s unified model: create, animate, reference and edit up to 4KFrom 51 credits for a 5-second clip
- Kling 3.0 Turbo APIFaster Kling 3.0 with sound on every clipFrom 84 credits for a 5-second clip
- Kling Avatar 2.0 APIA portrait that speaks or sings your audio, up to 5 minutesFrom 7.68 credits per second
- Kling 2.6 API1080p clips with optional sound and motion controlFrom 52 credits for a 5-second clip
- Kling 2.5 Turbo API1080p clips with a soundtrack on every takeFrom 42 credits for a 5-second clip
- Kling 2.1 Master APISilent 1080p clips with fine prompt controlFrom 162 credits for a 5-second clip
- Kling 2.1 APIAnimate a frame at 720p or 1080p, with an optional end frameFrom 27 credits for a 5-second clip
More about Kling O3
- Compare
- Kling 3.0 vs Kling O3

