DEV Community

Cover image for Kling 4.0 API: Pricing, Endpoints & Tested Prompts
Siray AI
Siray AI

Posted on Originally published at blog.siray.ai

Kling 4.0 API: Pricing, Endpoints & Tested Prompts

The Kling 4.0 API gives you Kuaishou's Kling 4.0 video model through eight Siray AI endpoints for text-to-video, image-to-video, reference-to-video and video editing. It costs about $0.157 per second at 720p and $0.235 per second at 1080p, and the faster Kling 4.0 Flash costs $0.094 per second at 720p. It suits clips of 3 to 30 seconds with sound, from product shots to multi-shot scenes.

Key takeaways

  • Eight endpoints: Kling 4.0 and Kling 4.0 Flash each have t2v, i2v, ref2v and video-edit endpoints on Siray AI.
  • Length and resolution: Kling 4.0 makes 3–30 second clips at 720p or 1080p. Flash makes 3–20 second clips at 720p only.
  • Pricing: a 5-second clip costs $0.785 at 720p and $1.175 at 1080p with Kling 4.0, or $0.47 with Flash.
  • Speed in our tests: Kling 4.0 jobs took 106–284 seconds. The same 5-second prompt on Flash took 86 seconds instead of 213.
  • Audio is always on: all six of our test clips came back with a two-channel audio track, and none of the endpoints has an audio switch.

What is Kling 4.0?

Kling 4.0 is the fourth-generation video model from Kling AI, the video product of Kuaishou Technology. Kling AI announced it on September 30, 2026, and Kuaishou's press release says it officially launched on October 15, 2026. Kling 4.0 is Kuaishou's model; Siray AI offers it through its unified API.

According to the official announcement, Kling 4.0:

  • "generates videos up to 30 seconds long in a single generation";
  • accepts "up to 15 reference assets in a single generation", split into up to 10 images, 5 videos and 7 subjects;
  • uses "up to 10 keyframe images to define key visual moments";
  • supports "high-quality audio and two-channel stereo" with more accurate lip sync;
  • can "make targeted edits to character expressions, body movements, camera positions, camera movements, overall style … while keeping the rest of the scene stable";
  • takes prompts of up to 8,000 tokens.

Kling 4.0 Flash is the lighter tier. Kling AI describes it as "built for frequent creation" and says it "combines fast generation with excellent value".

Known limits. Kling AI's announcement labels 10-bit HDR at 4K and video extension up to 2 minutes as "coming soon". Kuaishou's October 16 press release still describes 4K as upcoming. On Siray AI, the top resolution is 1080p, and the i2v endpoint takes a first frame and an optional last frame, not 10 keyframes.

Kling 4.0 endpoints on Siray AI

Model ID Task Required inputs Optional inputs
kuaishou/kling-4.0-t2v Text-to-video prompt, duration, size, aspect_ratio —
kuaishou/kling-4.0-i2v Image-to-video prompt, image, duration, size, aspect_ratio end_image
kuaishou/kling-4.0-ref2v Reference-to-video prompt, duration, size, aspect_ratio images (≤10), videos (≤5)
kuaishou/kling-4.0-video-edit Edit a video prompt, video, duration, size, aspect_ratio elements, keep_original_sound
kuaishou/kling-4.0-flash-t2v Text-to-video prompt, duration, size, aspect_ratio —
kuaishou/kling-4.0-flash-i2v Image-to-video prompt, image, duration, size, aspect_ratio —
kuaishou/kling-4.0-flash-ref2v Reference-to-video prompt, duration, size, aspect_ratio images (≤10), videos (≤5)
kuaishou/kling-4.0-flash-video-edit Edit a video prompt, video, duration, size, aspect_ratio elements, keep_original_sound

Values from the Siray AI API reference:

  • duration: any whole number from 3 to 30 on Kling 4.0, and 3 to 20 on Flash.
  • size: 720p or 1080p on Kling 4.0; 720p only on Flash.
  • aspect_ratio: auto, 16:9, 9:16, 1:1 or 21:9.
  • image and images accept a URL or a data URL. end_image, video and videos are documented as URLs.
  • elements is a list of characters or objects, each with a frontal_image, reference_images and an optional reference video.
  • Flash i2v has no end_image, so last-frame control needs the full model.

Kling 4.0 pricing on Siray AI

Text-to-video, image-to-video and reference-to-video without a video input are billed per second of output:

Duration Kling 4.0, 720p Kling 4.0, 1080p Flash, 720p
5 seconds $0.785 $1.175 $0.47
10 seconds $1.57 $2.35 $0.94
20 seconds $3.14 $4.70 $1.88
30 seconds $4.71 $7.05 —
Per second ≈ $0.157 ≈ $0.235 ≈ $0.094

Jobs that take a video input (video-edit, and ref2v with videos) bill both the output and the input. Siray AI's pricing note gives the formula: billable duration = output duration + max(input duration, output duration). The per-second rates for these jobs are:

Endpoint Output Input video
Kling 4.0, 720p $0.094/s $0.094/s
Kling 4.0, 1080p $0.141/s $0.141/s
Flash, 720p $0.063/s $0.063/s

Worked examples:

  • A 5-second 1080p product shot: $1.175. Ten takes cost $11.75.
  • The same 5 seconds as a Flash draft: $0.47, which is 40% less than Kling 4.0 at 720p.
  • Editing a 5-second clip with Flash: 5 seconds out plus 5 seconds in at $0.063 each, $0.63.
  • A full 30-second 1080p scene: $7.05.

Prices were read from the Siray AI pricing API on November 17, 2026, with no discount shown. Check the Kling 4.0 t2v model page for live prices. Failed requests are not billed, according to the same pricing note.

Watch the clip: a short concept video about how cost grows with clip length, made with Kling 4.0 Flash

Concept video generated with Kling 4.0 Flash on Siray AI.

Quickstart: call the Kling 4.0 API

Generation is asynchronous. Submit a task to get a task_id, then check it every 3–5 seconds. When the status is SUCCESS, download the video from data.outputs.

1. Submit a task

This is the request we used for our first test:

curl -X POST https://api.siray.ai/v1/video/generations \
  -H "Authorization: Bearer $SIRAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kuaishou/kling-4.0-t2v",
    "prompt": "A slow, low-angle dolly shot moving forward along a rain-soaked cobblestone alley...",
    "duration": 5,
    "size": "1080p",
    "aspect_ratio": "16:9"
  }'
Enter fullscreen mode Exit fullscreen mode

In our tests the task ID came back at the top level of the response (task_id), not under data as the API reference shows, so read both places.

2. Poll until the task finishes

curl https://api.siray.ai/v1/video/generations/<task_id> \
  -H "Authorization: Bearer $SIRAY_API_KEY"
Enter fullscreen mode Exit fullscreen mode

data.status moves through NOT_START, SUBMITTED, QUEUED and IN_PROGRESS to SUCCESS or FAILURE. On success, data.outputs holds the MP4 URL. Two details we noticed: fail_reason also contains the output URL on successful tasks, so judge success by status only, and the task record has no usage field for these endpoints.

To switch tasks, change model and add the inputs: "image" (and optionally "end_image") for i2v, "images": [...] for ref2v, or "video": "<URL>" for video-edit.

Watch the clip: a short concept video about the submit-and-poll flow, made with Kling 4.0 Flash

Concept video generated with Kling 4.0 Flash on Siray AI.

Kling 4.0 prompt examples (tested)

We ran every example below on November 17, 2026 through the Siray AI API. Times are measured from submit to finish on the task record. Costs are calculated from Siray AI's list prices, because the task record does not report usage for these endpoints. Every clip came back at 24 fps with a two-channel audio track.

1. Camera move at 1080p

A slow, low-angle dolly shot moving forward along a rain-soaked cobblestone alley in a Japanese mountain town at dusk. Paper lanterns glow above wooden shopfronts, steam drifts from a small noodle stall, and puddles reflect the warm light. In the final second the camera rises smoothly above the rooftops to reveal forested mountains under a deep blue sky. Cinematic 35mm film look, soft grain, natural motion. No people. No text, no signs with letters, no logos.
Enter fullscreen mode Exit fullscreen mode
  • Endpoint: kling-4.0-t2v, 5 s, 1080p, 16:9
  • Time: 213 seconds · Cost: $1.175 · Output: 1920×1080

Rain-soaked cobblestone alley in a Japanese mountain town at dusk with lanterns and wet tiled roofs, video frame made with Kling 4.0

Watch the clip

The low dolly, the steam, the puddle reflections and the final rise over the rooftops all appear, in that order. Putting the camera move in a sentence of its own ("In the final second the camera rises…") gave the model a clear point to change the motion.

2. The same prompt on Kling 4.0 Flash

  • Endpoint: kling-4.0-flash-t2v, 5 s, 720p, 16:9, same prompt as example 1
  • Time: 86 seconds · Cost: $0.47 · Output: 1280×720

The same alley rendered by Kling 4.0 Flash with long rows of round lanterns and a polished stone path, video frame made with Kling 4.0 Flash

Watch the clip

Flash finished in less than half the time and kept the dolly and the rise. The look changed more than the motion did. Flash replaced the scattered lanterns with long, even rows, smoothed the cobblestones and made the scene cleaner and more stylized. It works well for checking timing and camera moves before you pay for a 1080p take.

3. Three shots in one 10-second clip

A three-shot sequence in a small bicycle repair shop on a sunny morning, natural documentary look.
Shot 1 (wide): a mechanic in his 40s with a short grey beard and a green canvas apron rolls up the metal shutter of the shop and wheels a blue bicycle inside.
Shot 2 (close-up): his hands fit a new chain onto the rear sprocket and spin the pedal; the wheel turns smoothly.
Shot 3 (medium shot): he hands the bicycle to a woman in her 30s at the door, she nods, and he wipes his hands on a rag and smiles.
Keep the same man, apron, bicycle and shop in every shot. Adults only, no children, teenagers, babies or minors. No text, no logos.
Enter fullscreen mode Exit fullscreen mode
  • Endpoint: kling-4.0-t2v, 10 s, 720p, 16:9
  • Time: 236 seconds · Cost: $1.57 · Output: 1280×720

Bearded mechanic in a green apron handing a blue bicycle to a woman at a repair shop door, video frame made with Kling 4.0

Watch the clip

Kling 4.0 cut between three distinct shots and kept the same man, apron, blue bicycle and shop throughout. Labelling each shot with its framing (wide, close-up, medium) gave clean cuts. The close-up showed the rear sprocket and chain, though the hands turned the sprocket rather than spinning the pedal.

4. Image-to-video with a first and last frame

We gave the i2v endpoint two photos of the same woman on a rooftop. The image shows her in a moss-green wool coat. The end_image shows her in just the cream turtleneck and charcoal trousers, with the coat folded on the wall behind her. We made the end frame by editing the first photo with Seedream 5.5, so the face, light and background match exactly.

End frame used as end_image: the same woman on the rooftop in a cream turtleneck, her green coat folded on the white wall to her right, image edited with Seedream 5.5

The woman on the rooftop slowly unbuttons her moss-green wool coat, slips it off her shoulders, folds it once and lays it on the white parapet wall to her right, leaving her in the cream turtleneck sweater and charcoal trousers. She then turns back toward the camera and settles into the same pose as the end frame. Warm golden-hour light, gentle breeze in her hair, steady handheld camera. Adult woman only, fully clothed. No text, no logos.
Enter fullscreen mode Exit fullscreen mode
  • Endpoint: kling-4.0-i2v with end_image, 5 s, 720p, aspect_ratio: auto
  • Time: 284 seconds · Cost: $0.785 · Output: 836×1116, matching the shape of the input photos

Woman on a Lisbon-style rooftop at golden hour sliding a green wool coat off her shoulders over a cream turtleneck, video frame made with Kling 4.0

Watch the clip

The clip starts on the first photo and lands on the end frame, with the same face, sweater, rooftop and light. In between, Kling 4.0 played the whole action in order: she unbuttons the coat, slides it off both shoulders, turns away to lay it on the wall and turns back to the camera. The path is approximate, not exact. For about a second the coat stands up stiffly on the wall before it settles into the folded shape from the end frame.

An earlier version of this test used a navy blazer of the same cut as the end frame. That made the result read as a color swap rather than a coat coming off. An end frame that differs clearly in shape, not only in color, gives the model a transition it can show.

5. Reference-to-video: a person and a product

We passed two images to ref2v: a potter in her studio and a stoneware pour-over coffee set on a plain background.

Use image 1 as the location and the person, and image 2 as the product. The grey-haired potter from image 1 stops her wheel, wipes her hands on her apron and walks to a wooden table by the rainy window, where the stoneware pour-over coffee set from image 2 is waiting. She pours hot water from the kettle into the dripper in a slow spiral while steam rises in the soft window light. The camera pushes in slowly from a medium shot to a close-up of the coffee dripping into the cup. Keep the shape, glaze and colour of the coffee set exactly as in image 2, and keep the potter's face, hair and apron as in image 1. Adults only. No text, no logos.
Enter fullscreen mode Exit fullscreen mode
  • Endpoint: kling-4.0-ref2v, images with 2 items, 5 s, 720p, 16:9
  • Time: 106 seconds · Cost: $0.785 · Output: 1280×720

Close-up of a gooseneck kettle pouring water into a fluted stoneware dripper with a brass ring, video frame made with Kling 4.0

Watch the clip

The product held up best: the fluted dripper, the brass ring and the spouted pitcher match the reference photo. The studio, the rainy window and the potter's hair and apron also carried over. The opening was compressed: she is already walking with the kettle when the clip begins, so the wheel and the hand wipe are skipped. Numbering the images ("image 1", "image 2") and saying what each is for kept the two references apart.

6. Video edit with Flash: rain to snow

We sent the Flash clip from example 2 to the Flash video-edit endpoint.

Change the weather from rain to a quiet snowfall. Cover the cobblestones, rooftops and the noodle stall roof with a fresh layer of white snow, replace the puddles with soft snow, and add slow, large snowflakes falling through the lantern light. Keep the same street, buildings, lanterns, steam and camera movement as the original video. No people. No text, no logos.
Enter fullscreen mode Exit fullscreen mode
  • Endpoint: kling-4.0-flash-video-edit, 5 s input, 5 s, 720p, 16:9
  • Time: 74 seconds · Cost: $0.63 (5 s output + 5 s input) · Output: 1280×720

The same lantern-lit alley covered in fresh snow with snowy rooftops, video frame made with Kling 4.0 Flash video edit

Watch the clip

The street, lanterns, steam, stall and camera move stayed the same, and snow now covers the ground and roofs. One detail went the opposite way: the spots where the puddles were became bare patches of cobblestone in the snow. We could not see falling snowflakes in the frames we checked. This was the fastest job in our tests.

Prompting tips for Kling 4.0

  • Give each camera move its own sentence. "In the final second the camera rises…" produced a clean change of motion at the right moment.
  • Label shots with their framing. "Shot 1 (wide) … Shot 2 (close-up) …" gave three clear cuts in a 10-second clip. Repeat what must stay the same in every shot.
  • Number reference images and give each a role. "Use image 1 as the location and the person, and image 2 as the product" kept the two inputs apart.
  • Put the key action early. In both image-driven tests, the first step of a multi-step action was the one most likely to be skipped or shortened.
  • Draft on Flash, finish on Kling 4.0. The Flash take kept the camera move at 40% of the 720p price, so you can check timing before paying for 1080p.
  • Plan for sound. Every clip comes with audio. Describe the sound you want, or strip the track in editing if you don't need it.

When to use Kling 4.0 (and when not to)

Use Kling 4.0 for:

  • Final 1080p clips up to 30 seconds with sound.
  • Multi-shot scenes where the same person and props must carry across cuts.
  • Product videos from reference photos, where the product's shape and finish must hold.
  • First-and-last-frame transitions, such as outfit or product reveals.

Use Kling 4.0 Flash for:

  • Drafts, timing checks and A/B variants at 720p.
  • High-volume social clips up to 20 seconds.
  • Quick video edits, such as changing weather or time of day.

Look elsewhere when:

  • You need 4K or clips longer than 30 seconds: Kling AI lists 4K and 2-minute extension as coming soon, and Siray AI does not offer them yet.
  • You need control over every frame with up to 10 keyframes: the Siray AI i2v endpoint takes a first and a last frame.
  • You need a lower price per second at 480p: Seedance 2.5 Flash costs about $0.068 per second at 480p.

For more Kling examples, see Kling 3.0 Omni, Kling 3.0 Motion Control and the comparison Veo vs Kling vs Seedance 2.0.

FAQ

How much does the Kling 4.0 API cost per second?

About $0.157 per second at 720p and $0.235 per second at 1080p on Siray AI. A 5-second clip costs $0.785 at 720p and $1.175 at 1080p (prices checked November 17, 2026).

What is the difference between Kling 4.0 and Kling 4.0 Flash?

Flash is the faster, cheaper tier. On Siray AI it outputs 720p only, makes clips of up to 20 seconds instead of 30, and its i2v endpoint has no last frame. It costs about $0.094 per second, and in our test the same prompt finished in 86 seconds instead of 213.

How long can a Kling 4.0 video be?

From 3 to 30 seconds on Kling 4.0 and 3 to 20 seconds on Flash, chosen with duration.

Does Kling 4.0 generate audio?

Yes. Every clip in our tests came with a two-channel audio track. None of the Siray AI endpoints has a switch to turn audio off. On the video-edit endpoints, keep_original_sound keeps the input video's sound.

Can Kling 4.0 edit an existing video?

Yes. Send a video URL to kuaishou/kling-4.0-video-edit or kuaishou/kling-4.0-flash-video-edit with a prompt describing the change. You pay for both the output and the input duration. Our 5-second Flash edit cost $0.63.

How long does Kling 4.0 take to generate a video?

In our tests, Kling 4.0 took 106 to 284 seconds for 5- to 10-second clips. Flash took 74 to 86 seconds.

Try Kling 4.0 on Siray AI

Get an API key and run your first clip from the Kling 4.0 t2v model page. The same key works for all eight Kling 4.0 endpoints and every other model on Siray AI.

Sources


Originally published on the Siray AI blog. Prices were checked on 2026-11-17 and can change; see the live model page for current pricing.

Top comments (0)