Kling 4.0: Price, 30-Second Multi-Shot Video and API

Kling 4.0 is a text-to-video and image-to-video model that generates clips from 3 to 30 seconds at 720p or 1080p. You can describe one continuous shot, or write separate prompts for each shot, and the video lasts as long as the shots added together. On Raywake it costs $0.2737 per second at 720p and $0.4097 per second at 1080p, with no subscription.

Kling 4.0 was published on 21 October 2026 and became available through the API on 24 October. It has been live on Raywake since 25 October 2026. Every figure below comes from the request contract and the live quotes on that date.

Kling 4.0 at a glance

Source: Kling 4.0 Text to Video and Image to Video API schemas.

How much does Kling 4.0 cost?

Kling 4.0 is billed per second of output video. The resolution sets the rate; aspect ratio and the number of shots do not.

These are Raywake quotes from 25 October 2026. The quote is frozen before you generate, so the price you approve is the most you pay. Raywake uses a prepaid USD balance. You do not need a Kling plan, monthly credits or a daily allowance.

What is new compared with Kling 3?

Length is the most visible change. The reviewed Kling 3 operations offer 3–15 seconds per request, while Kling 4.0 goes up to 30 seconds. Kling 4.0 also accepts a much longer prompt, which leaves room for a detailed scene description or a short script of camera moves.

Use Kling 3 Pro when the clip needs generated sound or reusable character elements. Use Kling 4.0 when you need a longer clip or a planned sequence of shots in one request. This table compares documented controls and prices, not visual quality.

How do multi-shot prompts work?

Instead of one prompt, send multi_prompt: a list of shots, each with its own prompt and duration. Kling 4.0 renders them as one video, and the total length is the sum of the shots.

This request produces a 10-second video, quoted at $4.10 at 1080p. Keep each shot to one clear action and repeat the key details of the subject in every shot, such as clothing, colour and props, so the character stays recognisable across cuts. Send either prompt or multi_prompt, never both.

When should you use Image to Video?

Choose Image to Video when the first frame must be exact: a product photo, a brand character or a real location. Upload it as start_image_url. Add end_image_url when the clip must land on a specific frame, such as a final packshot. Both images must be JPEG, PNG or WebP, at least 300 pixels on each side, with an aspect ratio between 0.4 and 2.5. The video takes its framing from the start image, so this operation has no aspect-ratio setting.

How to call Kling 4.0 through the API

Quote a request first. Quoting is free and returns the exact price; generation starts only when you submit the quoted request. The model ID is kling/v4/text-to-video, or kling/v4/image-to-video for a starting image.

curl --fail-with-body https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kling/v4/text-to-video","input":{"prompt":"A detective in a black trench coat stands on a rooftop in the rain, looking through a telescope at the street below.","duration":10,"resolution":"1080p","aspect_ratio":"16:9"}}'

The response contains a quote_id, the price in credits (100 credits = $1) and an expiry time. The quotes reference lists every field, and the video API cost guide explains timeouts and settlement.

Prompting tips for longer clips

Plan the camera, not only the subject. In a 20 or 30-second shot, say how the camera moves and where it ends: "the camera slowly circles behind him and stops on the street below".

Start at 720p, finish at 1080p. A 10-second test at 720p costs $2.74. Once the motion and framing work, render the final version at 1080p.

Use shots for changes of angle. One prompt suits a continuous movement. When the brief calls for a wide shot followed by a close-up, write two shots instead of describing a cut inside one prompt.

Add sound separately. Kling 4.0 returns silent video on Raywake. Pair it with a music or voice model in the same studio.

Common questions

Is Kling 4.0 available without a Kling subscription?

Yes. On Raywake each generation is paid from your prepaid USD balance. Kling's own plans and credits are not involved.

What is the longest Kling 4.0 video?

30 seconds in a single request, either as one prompt or as shots whose durations add up to 30.

Can Kling 4.0 make vertical videos?

Yes. Text to Video offers 9:16 for vertical video, along with 16:9, 1:1 and 21:9. Image to Video follows the shape of your start image.

Does Kling 4.0 support Turkish or other non-English prompts?

The API accepts any text in the prompt field. Test a short clip in your language at 720p before planning a long one.

Are reference-to-video and video editing available?

Not on Raywake at the moment. Kling 4.0 reference-to-video and video-to-video editing bill by input and output length together, and Raywake only opens an operation when its full price can be quoted before you generate.