Video ● Operational Service status →

Kling 4.0

⧉

kling-4.0

Kling 4.0 is the next-generation video model from Kuaishou's Kling. Send no references for text-to-video, or up to 10 reference images, 5 reference videos and 3 reference audio clips, and say in the prompt what each one is for ("the character in image 1, the setting in image 2, the moves in the reference video"); the model brings them into one shot (images are references, not first frames). Any length from 3 to 30 seconds, 720P or 1080P, landscape 16:9 or portrait 9:16, with sound. Asynchronous: submit, then poll the job id for a re-hosted mp4 link; download it promptly. Billed per second: 720P $0.09/s, 1080P $0.125/s; with reference videos the billed seconds are the output seconds plus the reference-video seconds, and reference audio is not billed; failed jobs are refunded in full.

Text-to-videoMulti-image referenceVideo reference1080P

Get API Key → API Docs

Service Highlights

Kuaishou's next-generation Kling model, strong at character action and continuous camera moves
Up to 10 reference images, 5 reference videos and 3 reference audio clips, all in one request
3-30 s in one-second steps, 720P / 1080P, 16:9 / 9:16
Billed per second from $0.09/s at 720P, reference videos counted by their seconds; failed jobs refunded in full

Measured

2026-10

Median render time per clip3.3 min

Pricing

720P per second$0.09

1080P per second$0.125~~+39%~~

Shortest 3s$0.270

Longest 30s$2.700

Billed per second = rate x duration (3–30s, any integer). Per-second rates by resolution are listed above. The hold at submit equals the final settle exactly; failures are refunded in full.

View detailed pricing

Why this model

Kling 4.0 is live on NezhaGate: text-to-video, or reference images, videos and audio together, 3-30 seconds, 720P / 1080P, with sound.

Highlights

Up to 10 reference images, 5 reference videos and 3 reference audio clips in one request (images are references, never a first frame)
Any length from 3 to 30 seconds, 720P / 1080P, landscape 16:9 or portrait 9:16
A reference video sets motion and camera, reference audio sets a character's voice; every clip has sound and the lines go in the prompt
Billed per second: 720P $0.09/s, 1080P $0.125/s, reference videos counted by their seconds; failed renders refunded in full

Use cases

Product and brand films

Motion and camera taken from a reference video

A character's voice from reference audio, speaking your lines

Consistent characters and settings from reference images

Live Test · Playground

Try out Kling 4.0 right here (available after login).

Input

Prompt

"Beneath the Walls of Troy" - an epic action short. @Image1 is a Greek hero in golden armour and a crimson cloak with a long spear and a lion shield; @Image2 is a Trojan champion in black armour and a blue cloak with a curved sword and a horse shield; the setting follows the walls of Troy and the sunset battlefield of @Image3. Keep each warrior's armour, helmet, cloak colour and shield emblem exactly as in their own reference - never swap them.
Opening: wind drives the sand as the two face off twenty paces apart, sharp eyes behind their helmets.
Middle: they charge at once; the spear strikes the horse shield in a burst of sparks; rapid slashes and blocks up close as the camera orbits them 360 degrees.
Climax: the setting sun sits right between them as they clash mid-air in extreme slow motion, sparks, sand and the crimson cloak hanging in the air.
Ending: both lower their weapons and salute each other.
Cinematic action-commercial look, 24fps film grain, fluid and weighty fighting; war drums, clashing metal and an epic score with the big hits on the beat. No blood or wounds, no extra characters, no on-screen text or watermarks, no deformed weapons or limbs.

0 / 2500 chars

Duration

Resolution

Aspect ratio

Reference images0 / 10

Click to upload or drag files here jpg / png / webp / gif, up to 16 MB each or paste links

Every image is a reference (character, outfit, prop, setting), never a first frame. Say in the prompt what each one is for by its number, e.g. "the character in image 1 stands in the forest of image 2".

Reference videos0 / 5

Click to upload or drag files here mp4 / mov, up to 50 MB and 30 s each; all reference videos together at most 30s or paste links

Combines with reference images: photos set the people and the setting, the video sets motion and camera; say so in the prompt, e.g. "following the moves in the reference video". Reference videos count towards the billed seconds: cost = (output seconds + reference-video seconds) x the per-second rate; each clip at least 2 s and 700 px high (e.g. 1280x720 / 720x1280).

Reference audio0 / 3

Click to upload or drag files here mp3 / wav / m4a, up to 15 MB and 30 s each or paste links

Reference audio sets a character's voice: each clip 5-30 s of clear human speech (not music or sound effects), with a reference image or video as well; write the lines to be spoken in the prompt. Reference audio is not billed.

Uploaded references are kept for 7 days.

Rendering usually takes 5-20 min; when the backend is busy it can exceed 60 min (no result after 120 min counts as a timeout, fully refunded). Poll the job id rather than resubmitting - each resubmission is billed separately. Billed per second, fully refunded on failure. Prompt limit 2500 characters (Chinese and English count the same).

Output

video

Results will appear here after running.

🕑 Generated images and videos are kept for 15 days before 2026-10-29 09:49:40 UTC; from that time, they are kept for 7 days and existing files older than 7 days are removed.

About Kling 4.0

Kling 4.0 is the next-generation video model from Kuaishou's Kling, made for character action, product shorts and continuous camera moves. On NezhaGate, send no references for text-to-video, or up to 10 reference images (characters, outfits, props, settings), 5 reference videos (motion and camera) and 3 reference audio clips (a character's voice) together, and say in the prompt what each one is for. Any length from 3 to 30 seconds, 720P or 1080P, landscape 16:9 or portrait 9:16, with sound. Billed per second: 720P $0.09/s (18 credits), 1080P $0.125/s (25 credits); with reference videos the billed seconds are the output seconds plus the reference-video seconds, and reference images and audio are free; failed renders are refunded in full.

FAQ

How do reference images, videos and audio work?

Up to 10 reference images set characters, outfits, props and settings (never a first frame); up to 5 reference videos set motion and camera, each 2-30 s and at least 700 px high (e.g. 1280x720 or 720x1280), 30 s in all; up to 3 reference audio clips set a character's voice and must be 5-30 s of clear human speech, not music or sound effects. Say in the prompt what each one is for, e.g. "the character in image 1 swings the spear in the forest of image 2, following the moves in the reference video, and says in the voice of the reference audio: come on".

How is a reference video billed?

Billed seconds = output seconds + the seconds of every reference video, times the rate of the resolution. For example, 10 s of 720P output with a 5 s reference video bills 15 seconds: 270 credits ($1.35). The same reference-video link counts once; reference images and audio are free. The amount is held at submit, settled at the same figure on success and refunded in full on failure.

Which lengths, resolutions and aspect ratios are available?

Any whole number of seconds from 3 to 30 (default 5), 720P (default) or 1080P, and 16:9 or 9:16. First / last frames and turning the sound off are not supported; such a request is refused, never silently ignored.

How long does a render take?

Usually 3-5 minutes in our tests, longer when the queue is busy. Poll the job id instead of resubmitting, and download the clip once you have the link.