Kling 3.0 Pro Image to Video
Kuaishou's flagship video generation model delivering stunning visual fidelity. Kling 3.0 Pro supports text-to-video, image-to-video with start/end frames, element references for character consistency, and native audio generation.
60% less than the priciest provider (5 compared). Same model, same output.
Starting frame. The video animates from this image.
Duration
Length of the generated video in seconds (3-15). Billed per second.
Audio
Native audio: lip-synced dialogue, ambience and sound effects. Adds about 50% to the per-second price.
60% less than the priciest provider (5 compared). Same model, same output.
Your result renders here.
Use Kling 3.0 Pro Image to Video via the API
Generate with Kling 3.0 Pro Image to Video from your own code. Async by design: submit a generation, get a run id back instantly, poll until it completes. Billed in credits at the best available provider price — from $0.112 per second.
1 — Start a generation
curl -X POST https://app.scenetra.com/api/v1/generate/kling-v3-pro-i2v \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"Slow push-in, the subject turns to camera and smiles, soft wind in the hair","image_url":"https://example.com/start-frame.jpg","duration":"5"}'Response (202)
{
"runId": "run_abc123",
"status": "PENDING",
"model": "kling-v3-pro-i2v",
"estimatedCredits": 450,
"statusUrl": "/api/v1/runs/run_abc123"
}2 — Poll until COMPLETED (every 2-5 seconds)
curl https://app.scenetra.com/api/v1/runs/run_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"Response
{
"runId": "run_abc123",
"status": "COMPLETED",
"progress": { "completed": 1, "total": 1 },
"outputs": [
{ "type": "video", "url": "https://images.scenetra.com/..." }
],
"error": null,
"estimatedCredits": 450
}Request fields
| Field | Type | Description | Default |
|---|---|---|---|
| prompt* | string | Describe the motion and camera work; the look comes from the input image. | — |
| image_url* | string (https URL) | Starting frame. The video animates from this image. | — |
| duration | string | Length of the generated video in seconds (3-15). Billed per second.3 · 4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15 | 5 |
| generate_audio | string | Native audio: lip-synced dialogue, ambience and sound effects. Adds about 50% to the per-second price.false · true | false |
| callbackUrl | string (https URL) | Optional. When the run finishes (completed or failed), we POST the final run status to this URL — same shape as the poll response, plus model, params, and chargedCredits. Best-effort; polling remains the source of truth. | |
Unknown fields are rejected with a helpful 400. Media fields take https URLs. There is no provider parameter — every run is routed to the cheapest capable provider automatically.
Good to know
Billing
Runs bill your account credits at provider cost with 0% markup. The submit response includes the credit estimate; failed generations are refunded automatically. Add ?dryRun=1 to get the estimate without running anything.
Errors
Errors are always { "error": { "code", "message" } } with stable codes: unauthorized, model_not_available, invalid_parameter, insufficient_credits, rate_limited. A failed run is not an HTTP error — poll responses report status: "FAILED" with the reason.
What makes Kling 3.0 Pro Image to Video different
Direct the shot with first and last frames
Kling 3.0 Pro accepts an optional starting frame, an optional ending frame, or both. Lock just the opening image and let the model invent the motion, or pin both ends and it generates the transition that connects them — match cuts, transformations, and camera moves that land exactly where you planned. It is the difference between prompting and directing.
Elements keep your characters consistent
Upload reference images of a character, product, or object as Elements and Kling 3.0 Pro carries them through the generation — same face, same outfit, same product across every frame. This is the feature that makes multi-shot storytelling practical: generate shot after shot with the same cast instead of hoping the prompt re-describes them accurately each time.
Any duration from 3 to 15 seconds
Most video models offer two or three fixed lengths. Kling 3.0 Pro lets you pick any whole-second duration from 3 to 15, generated in a single pass — a 4-second product beat, a 7-second dialogue exchange, or a full 15-second scene with no stitching and no continuity drift. Since billing is per second, you pay only for exactly the length you need.
Native audio, with optional voice control
Audio is generated together with the picture — ambient sound and speech synchronized to what is on screen, no separate audio pass. Silent footage bills at $0.112 per second; switch audio on for $0.168 per second, or use the voice-control tier at $0.196 per second when you want to direct how generated speech sounds.
Parameters
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt* | text | Text describing the video you want to generate. | — |
| Duration | select | Length of the generated video in seconds.3 · 4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15 | 5 |
| Aspect Ratio | select | Aspect ratio of the output video.16:9 · 9:16 · 1:1 | 16:9 |
| First Frame | image upload | Optional starting frame image for image-to-video generation. | — |
| Last Frame | image upload | Optional ending frame for controlled video generation. | — |
| Elements | image upload | Reference images for character/object consistency across the video. | — |
Pricing
From $0.112 per second
Pay per generation — only pay for what you use.
Video only
$0.112/s
per second
With audio
$0.168/s
per second
Voice control
$0.196/s
per second
What a video costs
| Duration | Audio off | Audio on |
|---|---|---|
| 5 seconds | $0.56 | $0.84 |
| 10 seconds | $1.12 | $1.68 |
| 15 seconds | $1.68 | $2.52 |
Use cases
Film & storytelling
- Multi-shot scenes with one cast
- Dialogue moments with audio
- First-to-last frame match cuts
- 15-second single-pass shots
Marketing & ads
- Product hero shots via Elements
- Brand character campaigns
- Cinematic spec ads
- A/B variants of one scene
Social content
- Vertical 9:16 shorts
- Recurring character series
- Sound-on hooks
- Seamless loop transitions
Previz & concepting
- Animatics from storyboards
- Camera-move exploration
- Casting consistent characters early
- Client-ready mood clips
Frequently asked questions
What is Kling 3.0 Pro?+
Kling 3.0 Pro is the flagship tier of Kuaishou's Kling 3.0 video generation model. It creates videos from text prompts or images, supports first and last frame control, keeps characters consistent across shots with Elements reference images, and generates native audio. On Scenetra it runs as a node in the visual workflow editor — no separate Kling account or API key needed.
How much does Kling 3.0 Pro cost?+
On Scenetra, Kling 3.0 Pro is billed per second of generated video: $0.112/s without audio, $0.168/s with audio, and $0.196/s when voice control is used with audio. A 5-second clip with audio costs $0.84; a full 15-second clip with audio costs $2.52. You pay per generation from your credit balance — there is no monthly plan required.
Is Kling AI free or paid?+
Kling 3.0 Pro is a paid model, but you can try it without paying: new Scenetra accounts start with free welcome credits and a 7-day trial, which covers your first generations. After that it is pay-per-generation — no subscription gate on the model and nothing to cancel.
Do I need a Kling AI subscription or monthly plan?+
Not on Scenetra. Kling's own apps sell monthly credit plans, but Scenetra bills per second of video you actually generate. If you make one video this month, you pay for one video. Scenetra is web-based, so it also works anywhere without installing an app.
Is Kling 3.0 better than Veo 3.1?+
They trade blows. Community comparisons tend to favor Kling 3.0 for natural body motion and camera movement, while Veo 3.1 is often preferred for lip-sync precision, film-like textures, and higher resolutions. Kling 3.0 Pro is also cheaper per second with audio on. On Scenetra both are on the same board, so the practical answer is to run your prompt through each and compare.
How do Kling 3.0 Elements work?+
Elements are reference images you attach alongside your prompt — a character portrait, a product shot, an object. Kling 3.0 Pro uses them to keep that subject consistent in the generated video, and across separate generations if you reuse the same Elements. Combined with first/last frame control, this makes coherent multi-shot sequences possible.
Is Kling 3.0 Chinese?+
Kling is developed by Kuaishou, a Chinese technology company. On Scenetra you do not need a Kling account or any regional app — the model runs through Scenetra's web-based board like every other model, billed from the same credit balance.
What is the difference between Kling 3.0 Pro and Kling 3.0 Standard?+
Both tiers share the same feature set on Scenetra — text-to-video, image-to-video with first/last frames, Elements references, native audio, and durations from 3 to 15 seconds. Pro targets higher visual fidelity and costs $0.112/s (audio off) versus Standard's $0.084/s. A sensible workflow is to iterate on Standard and re-run the final prompt on Pro.
Related models
Start creating with Kling 3.0 Pro Image to Video
Use Kling 3.0 Pro Image to Video alongside 50+ other AI models in Scenetra's visual workflow editor. No setup required.
Get Started Free