Start building

Kling Video V3 Pro

kwaivgi/kling-video/v3/pro/image-to-video

Kling Video V3 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.

Use in agentGet API key
Base price
$0.84USD / run
Execution
async
Model type
video
Input fields
7

Try the model

Playground

Open 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 image to be used for the video

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the image to be used for the end of the video
The duration of the generated video in seconds Allowed values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.
The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. Allowed values: customize, intelligent.
List of prompts for multi-shot video generation. If provided, divides the video into multiple shots.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.84 / run
Billing formula
params.duration * 0.168

Context & modalities

Input
Schema-defined
Output
video

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
KwaiVGI
Model ID
kwaivgi/kling-video/v3/pro/image-to-video
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Kling Video V3 Pro Image-to-Video

Kling Video V3 Pro animates a supplied opening image from a written direction. The image fixes the first frame while the prompt describes action, camera behavior, and changes over time. An optional end image can guide the final frame.

The route produces clips from 3 to 15 seconds and returns a video URL. A request can select custom or intelligent shot structure, and native audio is enabled by default. The opening image determines the frame shape because this route has no separate aspect-ratio field.

Highlights

  • Cinematic visual quality. The exact Pro image-to-video route is documented for cinematic visuals. This is the route's stated visual positioning.
  • Fluid motion. Fluid motion is explicitly identified for this Pro image animation route. Movement is a model capability rather than a request parameter.
  • Native audio generation. The exact route is documented to generate native audio with video. Audio belongs to the generated result rather than a separate post-process.
  • Strong subject and text consistency. The exact Pro page identifies strong subject and text consistency. This capability applies while the opening image is animated.

Pricing

DurationPrice
3 seconds$0.504
4 seconds$0.672
5 seconds$0.840
6 seconds$1.008
7 seconds$1.176
8 seconds$1.344
9 seconds$1.512
10 seconds$1.680
11 seconds$1.848
12 seconds$2.016
13 seconds$2.184
14 seconds$2.352
15 seconds$2.520

When to Use

✅ Good fit❌ Consider alternatives
Add movement to an existing product or character still.Begin without any opening image; use text-to-video.
Direct a camera move around the composition in the first frame.Select frame shape independently of the supplied image.
Guide a transition toward a supplied final frame.Require a clip longer than 15 seconds in one request.
Produce a short scene with generated sound enabled.Require voice behavior outside the documented language handling.
Use the Pro tier for this image-led workflow.Prefer the lower local price of the Standard sibling.

Prompt Guide

Describe how the visible scene should move. Keep the request to the required image and prompt fields first, then add duration, audio, end-frame, or shot settings only when needed.

Subject action: [movement over time]
Camera: [framing and camera path]
Environment: [light, wind, particles, background movement]
Timing: [pace and progression]
Audio: [ambience, effects, or speech when enabled]
Final state: [arrival at the optional end image]

{
  "image": "<start-image-url>",
  "prompt": "The craftsman slowly examines the bowl while warm light shifts and dust drifts through the air.",
  "duration": 5,
  "generate_audio": true
}

Technical Specs

SpecValue
Required inputsimage, prompt
Prompt lengthUp to 2,500 characters
Duration3–15 seconds; default 5
Frame guidanceRequired image; optional end_image
Shot typescustomize, intelligent
Multi-prompt fieldExposed locally, but prompt remains required by the request contract
Native audioOptional; default enabled
OutputVideo URL with optional file metadata

Related

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
kwaivgi/kling-video/v3/pro/image-to-video
# 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 $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "kwaivgi/kling-video/v3/pro/image-to-video",
  "image": "https://storage.googleapis.com/falserverless/example_inputs/kling-v3/pro-i2v/start_image.png",
  "prompt": "The craftsman slowly examines the bowl, turning it gently in his weathered hands. His eyes reflect years of wisdom. Subtle smile forms on his face. Dust particles drift in warm light. Breathing motion, blinking eyes.",
  "duration": 12,
  "shot_type": "customize",
  "generate_audio": true
}
SANDBASE_JSON
)
run_id=$(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"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Kling Video V3 ProThis model
KwaiVGI		———Feb 4, 2026
Kling Video O3
KwaiVGI		———Jul 6, 2026
Kling Video V3
KwaiVGI		———Jul 6, 2026
Kling 3.0 Omni Pro Video Reference
KwaiVGI		———Jul 3, 2026
Kling 3.0 Omni Pro Video Edit
KwaiVGI		———Jul 3, 2026
Kling 3.0 Omni Pro Reference to Video
KwaiVGI		———Jul 3, 2026