APIPod logoAPIPod
Kling AI · Video modelsKling 4.0 → Motion Control · One API

Every Kling video model, one API.

From 30-second Kling 4.0 takes to multi-shot Kling 3.0 scenes and Motion Control, with fast Flash drafts coming soon: the whole Kling family, compared side by side and callable with a single key.

Now showingKling 4.0A dragon over a burning city, one 28-second generation01 / 06
01 / 08The lineup

Six ways to direct a scene.

Each Kling model makes a different trade between length, control, speed and price. Hover a model to watch an official sample; click through for its parameters and pricing.

02 / 08Pick by job

What are you making?

Start from the job, not the model name. Each answer comes with the model we would pick and an official sample from it.

Kling 4.0 · Official sample
One generation · 28 s
Our pick

Kling 4.0

Up to 30 seconds in one generation at 1080p, steered by up to 10 keyframes and 15 references, with stereo sound.

  • 3–30 s at 720p or 1080p
  • First and last frame, up to 8 middle keyframes
  • Two-channel stereo with lip sync
03 / 08What Kling does

Proof, on screen.

Official samples from Kling AI, grouped by what they prove. Each card plays when it is in view. Turn the sound on: the audio was generated too.

Kling 3.0
01

Multi-shot storyboards

One request, several shots, each with its own prompt and duration. Wide, macro, tracking: Kling cuts the scene for you.

Kling 3.0
02

Dialogue, natively

Speech, room tone and effects come out with the picture. Characters can talk to each other, even in different languages.

Kling 3.0
03

Lettering that holds

Logos and lettering stay legible while the camera and the subject move. The original was generated in 4K.

Kling 3.0 Omni
04

Your cast, consistent

Characters defined once as elements keep their faces and wardrobe in every shot. The dog included.

Kling 3.0 Omni
05

Product hero shots

A product element drives the whole spot: macro texture, liquid and light, and the lipstick stays exactly that lipstick.

Kling 3.0 Omni
06

Action across cuts

Five scripted shots of a rooftop fight. The two fighters never change between cuts.

Kling 3.0 Omni
07

Animated characters

A stylized character carries from a classroom to a storm at sea, delivering lip-synced lines.

04 / 08Motion Control

Borrow a performance.

Motion Control turns one reference video into a performance for any character image. Body movement, hand gestures and expressions transfer; your character's look stays.

Faces that hold
Motion Control 3.0 keeps facial identity consistent across angles, emotions and long, complex moves.
Up to 30 seconds
Generate 3–30 s at 720p or 1080p. When the character keeps the image's orientation, takes run up to 10 s.
Keep the original sound
Carry the reference video's audio into the result, handy for dance and music performances.
Ready to try it? Kling Motion Control
Motion reference
Kling output

Official Kling sample: a performer's hand signs, re-performed finger by finger by a robed character from a single image.

05 / 083.0 → 4.0

From 3.0 to 4.0, in numbers.

What Kling AI changed between generations. Kling 3.0 is still the right call for plenty of jobs, and it runs on APIPod today.

Max duration
3.015 s
4.030 s
References per request
3.07
4.015
Reference video
3.01 clip, up to 15 s
4.05 clips, 30 s total
Frame control
3.0First and last frame
4.0Up to 10 keyframes
Dynamic range
3.08-bit SDR
4.010-bit HDR (coming soon)

Source: Kling AI, “Kling 4.0 vs 3.0” (October 2026). Bar lengths are relative within each row.

  1. Dec 17, 2025Motion Control 2.6Motion transfer from a reference video onto any character image.
  2. Feb 5, 2026Kling 3.0 and 3.0 OmniMulti-shot storytelling, native audio in five languages, up to 15 s and 4K.
  3. Sep 28, 2026Kling 4.0 FlashEarly access for the lighter, faster 4.0 model.
  4. Oct 15, 2026Kling 4.030-second takes, 10 keyframes, 15 references and stereo sound, open to everyone.
06 / 08Compare

The whole family, side by side.

Limits per request for every Kling model. Model names link to their series pages with full parameters and pricing.

CapabilityKling 4.0Kling 4.0 FlashComing soonKling 3.0 OmniKling 3.0Kling 3.0 TurboMotion Control
Model IDskling-4.0-t2v / -i2v / -r2vkling-4.0-flashkling-3.0-omni-t2v / -i2v / -r2v / -editkling-3.0-t2v / -i2vkling-3.0-turbo-t2v / -i2vkling-3.0-motion-control / kling-2.6-motion-control
Duration3–30 s3–20 s3–15 s3–15 s3–15 s3–30 s
Resolution720p / 1080p720p720p / 1080p / 4K720p / 1080p / 4K720p / 1080p720p / 1080p
InputsText, images, keyframes, references, videoText, first frame, referencesText, images, references, videoText, first and last frameText, first frameCharacter image + motion video
Multi-shot——Up to 6, or automaticUp to 5Up to 6—
ReferencesUp to 15 (10 images, 5 videos, 7 elements)Omni Reference (limits not published)1–7 images, or 1 video + 4 imagesUp to 3 @elements—One motion reference video
AudioStereo, lip-synced—OptionalOptionalAlways onKeep original sound
Video editingComing soon on APIPod—3–15.5 s source———
Best forThe final takeFast draftsConsistent casts and productsMulti-shot scenesSpeed, with soundDance, action, gestures

Kling 4.0 values are the limits APIPod enforces today (its video editing is coming soon); Kling 4.0 Flash values are Kling AI's published specifications; Kling 3.0 and Motion Control values are the limits APIPod enforces today. — = not offered or not published.

07 / 08One API

One endpoint for every Kling model.

Every Kling model on APIPod sits behind the same async video endpoint. Switching models means switching one string; authentication, polling and billing stay the same.

  1. POST /v1/videos/generations with any Kling model ID. A task_id comes back immediately.
  2. GET /v1/videos/status/{task_id} until the status is completed, or pass a callback_url.
  3. Download the video from result. The same key works for every model on APIPod.
generate.sh
curl https://api.apipod.ai/v1/videos/generations \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-4.0-t2v",
    "prompt": "Two old friends meet at dusk on a London street",
    "duration": 30,
    "resolution": "1080p",
    "aspect_ratio": "21:9"
  }'

# {"code":200,"data":{"task_id":"<task_id>","status":"pending"}}
# then: GET /v1/videos/status/<task_id>

Pick a model above to see its request. Kling 4.0, Kling 3.0 and Motion Control fields match APIPod's live schema; Kling 4.0 Flash isn't live yet, so its request is a preview. See the docs for each model's full parameter list.

08 / 08FAQ

Questions, answered.

What is Kling AI?

Kling AI is Kuaishou's video and image generation platform. Its video models (Kling 4.0, Kling 4.0 Flash, the Kling 3.0 family with Standard, Turbo and Omni, and Motion Control) turn text, images, reference videos and audio into video with native sound.

Which Kling model should I use?

Kling 4.0 for the finished take (up to 30 s at 1080p), Kling 3.0 for multi-shot scenes with dialogue, Kling 3.0 Omni when characters or products must stay consistent, Kling 3.0 Turbo for speed with sound on every clip, and Motion Control to transfer a real performance onto a character image. Kling 4.0 Flash, for fast 720p drafts, is coming to APIPod soon.

What is the difference between Kling 3.0 and Kling 4.0?

Kling 4.0 doubles the maximum length to 30 seconds, raises references per request from 7 to 15 (including up to 5 videos), adds up to 10 keyframes and two-channel stereo audio, and builds editing into the main model. Kling 3.0 remains a strong, proven choice for multi-shot scenes up to 15 seconds.

What does “Omni” mean in Kling 3.0 Omni?

Omni is the reference-driven variant. It reads 1–7 reference images (or one motion video plus up to 4 images), supports scripted or automatic multi-shot up to 6 shots, edits existing 3–15.5 s clips and renders up to 4K.

When should I pick Kling 3.0 Turbo?

When you want speed and sound by default. Turbo always generates native audio, supports up to 6 shots and first-frame image-to-video, at 720p or 1080p.

How does Kling Motion Control work?

Send a character image and a reference video. The model transfers the performer's body movement, gestures and expressions to your character, for 3–30 seconds at 720p or 1080p. Motion Control 3.0 improves facial consistency over 2.6.

Do Kling models generate audio?

Yes. Kling 4.0 outputs two-channel stereo with lip sync. Kling 3.0 and 3.0 Omni generate native audio on request (Turbo always does), with dialogue in Chinese, English, Japanese, Korean and Spanish. Motion Control can keep the reference video's original sound.

How do I call Kling models on APIPod?

Send POST /v1/videos/generations with the model ID (for example kling-4.0-t2v, kling-4.0-r2v, kling-3.0-omni-r2v or kling-3.0-motion-control), then poll GET /v1/videos/status/{task_id} or pass a callback_url. One API key works for every Kling model.

Every Kling model. One key.

Finish on Kling 4.0, keep your cast on 3.0 Omni, and draft on Flash when it lands, all without changing your integration.