Kling Video V3 Pro
kwaivgi/kling-video/v3/pro/text-to-videoKling Video V3 Pro by KwaiVGI - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.
- Base price
- $0.84USD / run
- Execution
- async
- Model type
- video
- Input fields
- 6
Try the model
Playground
Input
Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.
The aspect ratio of the generated image. Allowed values: 16:9, 9:16, 1:1.
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, overrides the single prompt and divides the video into multiple shots with specified prompts and durations.
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/text-to-video
- Execution
- async
- API
- Unified Run API
- Endpoint
- /v1/run
API README
Kling Video V3 Pro Text-to-Video
Kling Video V3 Pro generates video directly from a written scene. The prompt describes the subject, action, camera, light, atmosphere, and sound without requiring an opening image. Landscape, portrait, and square frame shapes are available.
The route produces clips from 3 to 15 seconds and returns a video URL. Native audio is enabled by default, with documented language handling in the local contract. Custom and intelligent shot structure are exposed as request settings.
Highlights
- Cinematic visual quality. The exact Pro text-to-video route is documented for cinematic visuals. This is the route's stated visual positioning.
- Fluid motion. Fluid motion is explicitly identified for Pro text-to-video. Movement is generated from the written scene direction.
- Native audio generation. The exact route is documented to generate audio together with video. Sound can therefore be part of the original scene request.
- Multi-shot support. Multi-shot generation is explicitly named for this exact route. It is a documented model capability for sequences built from text.
Pricing
| Duration | Price |
|---|---|
| 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 |
|---|---|
| Turn a written scene into a short video without an image input. | Preserve a specific opening composition; use image-to-video. |
| Describe action and camera movement in one continuous prompt. | Require a clip longer than 15 seconds in one request. |
| Deliver landscape, vertical, or square video. | Require an aspect ratio outside the documented set. |
| Include generated ambience, effects, or speech. | Require voice behavior outside the documented language handling. |
| Use the Pro tier for this text-led workflow. | Prefer the lower local price of the Standard sibling. |
Prompt Guide
Write one continuous scene in temporal order. Start with the required prompt; add duration, aspect ratio, audio, or shot settings only when the request needs them.
Scene: [setting, time, atmosphere]
Subject: [appearance and action]
Camera: [framing and movement]
Lighting: [direction and change]
Motion: [subject and environment]
Audio: [ambience, effects, or speech when enabled]
{
"prompt": "Close-up of glowing fireflies dancing in a dark forest at twilight. Bioluminescent particles drift through the air with gentle movement.",
"duration": 5,
"aspect_ratio": "16:9",
"generate_audio": true
}
Technical Specs
| Spec | Value |
|---|---|
| Required input | prompt |
| Prompt length | Up to 2,500 characters |
| Duration | 3–15 seconds; default 5 |
| Aspect ratios | 16:9, 9:16, 1:1 |
| Shot types | customize, intelligent |
| Multi-prompt field | Exposed locally, but prompt remains required by the request contract |
| Native audio | Optional; default enabled |
| Output | Video URL with optional file metadata |
Related
- Kling Video V3 Pro Image-to-Video — Animate a supplied opening image.
- Kling Video V3 Standard Text-to-Video — Compare the sibling tier.
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# 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 $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "kwaivgi/kling-video/v3/pro/text-to-video",
"prompt": "Close-up of glowing fireflies dancing in a dark forest at twilight. Soft bioluminescent particles float through the air. Shallow depth of field, bokeh lights in background. Magical atmosphere, gentle movement.",
"duration": 5,
"shot_type": "customize",
"generate_audio": true
}
SANDBASE_JSON
)
run_id=$(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
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
Kling Video V3 ProThis model KwaiVGI | — | — | — | Feb 4, 2026 |
KwaiVGI | — | — | — | Jul 6, 2026 |
KwaiVGI | — | — | — | Jul 6, 2026 |
KwaiVGI | — | — | — | Jul 3, 2026 |
KwaiVGI | — | — | — | Jul 3, 2026 |
KwaiVGI | — | — | — | Jul 3, 2026 |