Kling 3.0

Endpoint

POST /videos/generations

Full URL: https://modelfold.ai/v1/videos/generations

Authentication: every request must include the Authorization: Bearer <API_KEY> header.

Send model parameters directly in the JSON body. Do not wrap them in input. This request waits for generation to finish and returns data[].url; supported media models also offer async jobs, polling and callbacks. Replace example media URLs with your own publicly accessible files. See API gateway for billing and errors.

Input parameters for the generation task

Request Parameters

Body (application/json)

Parameter	Type	Required	Description
model	string	Yes	The model name. Must be kling-3.0/video. Default："kling-3.0/video"。 Allowed values：kling-3.0/video。 Example：kling-3.0/video。
prompt	string	Yes	Prompt required by the ModelFold gateway; at most 2000 characters. Required when multi_shots is false. Up to 2,500 characters. maxLength: 2000. Example：In a bright rehearsal room, sunlight streams through the window@element_dog。
image_urls	array<string>	No	First and last frame image URLs. Optional; not required when using kling_elements. When multi_shots is false: if length is 2, index 0 is the first frame and index 1 is the last frame; if length is 1, the array item serves as the first frame. When multi_shots is true: only the first frame is supported.
sound	boolean	Yes	Required. Whether to generate audio (speech, sound effects, ambience) with the video. Affects price. Example：true。
duration	string	Yes	Required. Video duration in seconds, 3–15 (string, e.g. "5"). In multi-shot mode, output length and billing follow the sum of multi_prompt[].duration (3–15 s); set duration to the same total. Allowed values：3 / 4 / 5 / 6 / 7 / 8 / 9 / 10 / 11 / 12 / 13 / 14 / 15。 Example：5。
aspect_ratio	string	No	Optional when image_urls is provided (the output follows the first frame's aspect ratio). For text-to-video, set it explicitly: 16:9, 9:16 or 1:1. Allowed values：16:9 / 9:16 / 1:1。 Example：16:9。
mode	string	Yes	Required. Generation mode. std has standard resolution, pro has higher resolution, 4K has 4K resolution. Resolution mapping: - std mode: 16:9 (1280×720), 9:16 (720×1280), 1:1 (720×720) - pro mode: 16:9 (1920×1080), 9:16 (1080×1920), 1:1 (1080×1080) - 4K mode: 16:9 (3840×2160), 9:16 (2160×3840), 1:1 (2160×2160) Allowed values：std / pro / 4K。 Example：pro。
multi_shots	boolean	Yes	Required. Whether to use multi-shot mode. true enables multi-shot mode, false enables single-shot mode. Example：false。
multi_prompt	array<object>	No	Shot prompts. Takes effect when multi_shots is true. Used to describe the text and duration of each shot. Supports up to 5 shots. Each shot duration is 1-12 seconds. If you need to use elements, add them after the prompt.
multi_prompt[].prompt	string	Yes	Prompt text for this shot, a maximum of 500 characters per shot. Each @element will occupy 37 characters. maxLength: 500. Example：a happy dog in running@element_cat。
multi_prompt[].duration	integer	Yes	Duration of this shot in seconds. Range: 1-12. minimum: 1. maximum: 12. Example：3。
kling_elements	array<object>	No	Referenced elements. Detailed information about elements referenced in the prompt. A single task can reference a maximum of three elements. maxItems: 3.
kling_elements[].name	string	Yes	Element name, used in prompt with @ prefix (e.g., @element_dog) Example：element_dog。
kling_elements[].description	string	Yes	Element description Example：dog。
kling_elements[].element_input_urls	array<string>	Yes	Either 2–4 images (JPG/PNG, up to 10 MB each) or 1 video (MP4/MOV).
kling_elements[].element_input_audio_urls	array<string>	No	Optional. List of audio material URLs for characters. The audio duration must be between 5 and 30 seconds.
kling_elements[].start_time	integer	No	Start time for video character material capture (in milliseconds). Only effective when uploading videos through element_input_urls. If not uploaded, it defaults to 0.
kling_elements[].end_time	integer	No	End time for video character material capture (in milliseconds). Only effective when uploading videos through element_input_urls. Must be greater than start_time, and the difference between end_time and start_time must be within 3000 to 8000 milliseconds.

Request Example

curl -X POST "https://modelfold.ai/v1/videos/generations" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling-3.0/video",
  "sound": true,
  "duration": "5",
  "mode": "pro",
  "multi_shots": false,
  "prompt": "In a bright rehearsal room, sunlight streams through the window@element_dog"
}'

{
  "model": "kling-3.0/video",
  "sound": true,
  "duration": "5",
  "mode": "pro",
  "multi_shots": false,
  "prompt": "In a bright rehearsal room, sunlight streams through the window@element_dog"
}

Response

200 — Generation completed. usage contains actual billing details; result URLs are illustrative.

{
  "ok": true,
  "created": 1792134000,
  "data": [
    {
      "url": "https://modelfold.ai/uploads/outputs/result.mp4"
    }
  ],
  "usage": {}
}