Kling 3.0 Turbo provides Standard 720p and Pro 1080p tasks for creating 3–15-second videos from text or one source image. Write a scene and action for Text to Video, or supply a prepared image and describe its movement for Image to Video. Use a single prompt for one continuous brief, or use multi_prompt to assign an ordered prompt and duration to each planned shot. Choose the output tier and timing around your project, then review the current per-second rate and complete request estimate.
Kling 3.0 Turbo is developed by Kuaishou. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Begin with Text to Video for a written scene or Image to Video for one prepared image. Choose Standard for 720p output or Pro for 1080p, then set a 3–15-second duration. For a timed sequence, prepare up to six multi_prompt entries and keep their combined duration within the task limits.
Kling 3.0 Turbo video model with Standard 720p and Pro 1080p tiers for text-to-video and image-to-video, 3 to 15 seconds.
Kling 3.0 Turbo video model with Standard 720p and Pro 1080p tiers for text-to-video and image-to-video, 3 to 15 seconds.
Kling 3.0 Turbo video model with Standard 720p and Pro 1080p tiers for text-to-video and image-to-video, 3 to 15 seconds.
Kling 3.0 Turbo video model with Standard 720p and Pro 1080p tiers for text-to-video and image-to-video, 3 to 15 seconds.
The text tasks describe the subject, setting and camera through words. The image tasks use exactly one image_urls entry to establish the visual source, with the prompt describing the requested motion. Standard and Pro keep those two input choices while providing their respective 720p and 1080p output tiers.
| Model / task | Input and workflow |
|---|---|
| Kling 3.0 Turbo Standard Text to Video | Kling 3.0 Turbo video model with Standard 720p and Pro 1080p tiers for text-to-video and image-to-video, 3 to 15 seconds. |
| Kling 3.0 Turbo Standard Image to Video | Kling 3.0 Turbo video model with Standard 720p and Pro 1080p tiers for text-to-video and image-to-video, 3 to 15 seconds. |
| Kling 3.0 Turbo Pro Text to Video | Kling 3.0 Turbo video model with Standard 720p and Pro 1080p tiers for text-to-video and image-to-video, 3 to 15 seconds. |
| Kling 3.0 Turbo Pro Image to Video | Kling 3.0 Turbo video model with Standard 720p and Pro 1080p tiers for text-to-video and image-to-video, 3 to 15 seconds. |
Use a written scene to create new visual material or a source image to retain a prepared composition. Specify the movement and camera, choose the output tier and duration, and use timed multi_prompt entries when your brief needs separate shot instructions. The examples below are the original single-prompt generation records.
Describe the subject, material detail, light and camera behavior. The raindrop record asks for a macro slow-motion scene with moss, ripples and drifting spores. Inspect the result when developing a natural-history or atmosphere study.
Provide one source image and name the elements that should move. The morning-coffee input establishes the cup and surrounding light before the short prompt requests rising steam and subtle camera drift.
Describe how steam, mist or other visible material changes over the shot. The coffee record provides a 5-second Standard result for checking steam direction, the source composition and the requested camera movement.
Use the Pro image task when the project needs its 1080p output tier. The 3-second train record requests forward travel across a stone bridge with smoke drifting backward. Compare its actual result with its source and prompt to inspect the vehicle and smoke.
Choose an integer duration from 3 to 15 seconds for a single prompt. For an ordered sequence, provide one to six multi_prompt entries with individual prompts and durations; keep the total at most 15 seconds and make an explicitly supplied duration equal that total. The coastal text record shown here remains a single-prompt example.
The Standard example supplies a coffee image and requests steam swirling in the morning light with subtle camera drift over 5 seconds. The Pro example supplies a locomotive image and requests forward travel across the bridge with smoke drifting backward over 3 seconds. Read each original prompt and compare its source with the corresponding actual result to assess movement and composition for that scene.
Steam rises gently from the hot coffee, swirling in the morning light, subtle camera drift
The steam locomotive moves forward across the stone bridge, white smoke billowing and drifting back
Prepare a written brief for a new scene, a single image for an existing composition, or an ordered set of shot prompts for a timed sequence. Describe the movement and camera, choose Standard 720p or Pro 1080p and plan a total duration within 3–15 seconds. Review the generated clip for a storyboard, motion study, visual presentation or API-driven project.
Describe the environment, light and a small visible action, then choose a duration and output tier. Review the resulting shot for a nature concept, mood board or storyboard.
Provide one image with a clear composition and describe the material’s movement and camera. Inspect the completed clip for a presentation or atmospheric visual study.
Prepare a vehicle image and state its direction of travel, wheel or smoke behavior and surroundings to preserve. Review motion and structure for a transport or narrative concept.
Choose an integer duration from 3 to 15 seconds and describe an action that fits the available time. Review the result and the complete duration-based estimate before selecting a clip for your sequence.
Prepare one to six multi_prompt entries with a clear prompt and integer duration for each. Keep their total within the video limits, set any explicit overall duration to that total and inspect the generated sequence against the plan.
Retain the model identifier, prompt or timed shot list, optional source-image URL and chosen duration. Submit the request through the API, track its task ID and retrieve the generated file for your application.
Kling 3.0 Turbo is billed per second using the selected Standard 720p or Pro 1080p tier and the requested video duration. The dynamic table shows the current starting rate and billing unit for each task. Select the actual clip length or timed shot sequence on the task page to review the complete request estimate before generation.
| Model | Provider | Workflow | Input material | Output specification | Starting rate |
|---|---|---|---|---|---|
| Kling 3.0 Turbo Standard Text to Video | Kling | Text to Video | Text prompt | 720p | $0.085 / second |
| Kling 3.0 Turbo Standard Image to Video | Kling | Image to Video | One source image | 720p | $0.085 / second |
| Kling 3.0 Turbo Pro Text to Video | Kling | Text to Video | Text prompt | 1080p | $0.11 / second |
| Kling 3.0 Turbo Pro Image to Video | Kling | Image to Video | One source image | 1080p | $0.11 / second |
Test your creative brief online, then bring the verified request into your application.
Enter the scene prompt and, for image generation, supply one image. Choose the Standard or Pro task and an integer duration from 3 to 15 seconds. When using timed multi_prompt entries, review their order and total duration. Check the estimate, generate the clip and inspect the requested movement and composition.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Choose Text to Video for a written scene or Image to Video for one prepared image. Select Standard 720p or Pro 1080p, then use a single prompt with a 3–15-second duration or a multi_prompt shot list whose combined duration follows the same overall limits.
Open the matching task, enter your brief and supply the required images. Review the generated result against subject appearance, composition and the requested changes before carrying the workflow into a project.
Review the Standard or Pro per-second rate and the full requested duration. For multi_prompt generation, use the combined shot duration when checking the estimate, then include the planned number of tests in your project budget.
Read the actual prompt and inspect its source images and result together. Use those examples to understand how to assign input roles and describe the details to preserve or change in your own request.
Retain the task ID returned by the API to query status and retrieve completed file URLs. Use your online generation history to review earlier results and the creative direction you tested.
Use the documentation linked from each task for its exact model identifier, accepted inputs, authentication and response format. Integrate the same task you tested online so its media and settings match the request.
Kling 3.0 Turbo is a Kuaishou video model with Standard 720p and Pro 1080p text-to-video and image-to-video tasks on Vidgo. It supports 3–15-second output, one image for image generation and a single prompt or timed multi_prompt shot instructions. Select the task and timing around the source material and the output your project needs.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
