> ## Documentation Index > Fetch the complete documentation index at: https://docs.vidgo.ai/llms.txt > Use this file to discover all available pages before exploring further. # Kling 4.0 Reference to Video > The Kling 4.0 Reference to Video API guides 3–30 second videos with up to 10 reference images, 5 reference videos and 7 elements, cited as @Image1 or @Element1. > [!TIP] > > 1. After submission, a `task_id` will be returned. If you provided a `callback_url`, when the task status becomes `finished` or `failed`, a POST request will be sent to the `callback_url`. > 2. Regardless of whether `callback_url` is provided, you can retrieve the result through the unified [Query Task Status](https://docs.vidgo.ai/api-manual/task-management/status.md) endpoint. Kling 4.0 Reference to Video generates a 3–30 second video guided by reference images, reference videos and reusable subjects (elements), so characters, products and settings stay consistent. Cite each reference in the prompt by its position, such as `@Image1`, `@Video1` or `@Element1`. Kling 4.0 is Kuaishou's Kling AI video model. Vidgo exposes it as four model IDs: [Text to Video](https://docs.vidgo.ai/api-manual/video-series/kwaivgi-kling-v4-0-text-to-video.md), [Image to Video](https://docs.vidgo.ai/api-manual/video-series/kwaivgi-kling-v4-0-image-to-video.md), [Reference to Video](https://docs.vidgo.ai/api-manual/video-series/kwaivgi-kling-v4-0-reference-to-video.md) and [Video Edit](https://docs.vidgo.ai/api-manual/video-series/kwaivgi-kling-v4-0-video-edit.md). ## Models * **kwaivgi/kling-v4.0/reference-to-video** — Reference-to-video with Kling 4.0 from images, videos and elements, 3–30 seconds, 720p or 1080p. ## Features * Up to 10 reference images, 5 reference videos and 7 elements, 15 assets in total. * Elements built from 2–4 images or one video of the same subject. * Optional start frame via `image_urls`. * Single or multi-shot prompts; 3–30 seconds at 720p or 1080p. * Five aspect ratios: `auto`, `16:9`, `9:16`, `1:1`, `21:9`. ## Input modes Send at least one reference input; you can combine them: * **Reference images** (`reference_image_urls`): cite as `@Image1`, `@Image2`, …. * **Reference videos** (`reference_video_urls`): cite as `@Video1`, `@Video2`, …. Billed as input video. * **Elements** (`kling_elements`): cite as `@Element1`, `@Element2`, …. Video-based elements are billed as input video. Add `image_urls` with one image to fix the opening frame. Then choose a single `prompt` or a `multi_prompt` shot list: * **Single prompt**: send `prompt` and, optionally, `duration`. * **Multi-shot**: send `multi_prompt` with one entry per shot. The clip length is the sum of the shot durations; leave `duration` out or set it to that sum. ## Required parameters * At least one of `reference_image_urls`, `reference_video_urls` or `kling_elements`. * `prompt` (string) **or** `multi_prompt` (object\[]): send exactly one. * `prompt`: 1–26,000 characters after trimming. * `multi_prompt`: a non-empty list of shots `{prompt, duration?}`. Each shot `prompt` is 1–512 characters; each shot `duration` is an integer `1`–`30` (default `5`). The shot durations must total 3–30 seconds. ## Optional parameters * `reference_image_urls` (string\[]): Up to 10 public HTTP(S) image URLs. * `reference_video_urls` (string\[]): Up to 5 public HTTP(S) video URLs, each 3–30 seconds. * `kling_elements` (object\[]): Up to 7 elements, at most 3 video-based. Each element has exactly one of: * `element_input_urls` (string\[]): 2–4 image URLs of the subject. * `element_input_video_urls` (string\[]): exactly 1 video URL of the subject (3–30 seconds). * `image_urls` (string\[]): One start-frame image URL. * `duration` (integer): Output length, `3`–`30` seconds. Default `5`; with `multi_prompt` the default is the shot total, and an explicit value must equal it. * `resolution` (string): `720p` or `1080p`. Default `720p`. * `aspect_ratio` (string): `auto`, `16:9`, `9:16`, `1:1` or `21:9`. Default `auto`. ## Output The finished task returns one MP4 video, with an audio track, in the `files` array of [Query Task Status](https://docs.vidgo.ai/api-manual/task-management/status.md) and the callback payload. ## Examples * **Reference images**: a character and a cafe image, cited as `@Image1` and `@Image2`, 8 seconds at 720p. * **Elements plus a reference video, with callback**: one robot element from two images and a dance clip cited as `@Video1`, 10 seconds at 1080p, `9:16`. ## Notes * Limits: start frame plus reference images ≤ 10; all assets (start frame, reference images, reference videos, elements) ≤ 15; video-based elements ≤ 3. * Input videos are downloaded and measured server-side (up to 100 MB each). Each must run 3–30 seconds, and all input videos together must not exceed 30 seconds. * `voice_id` and other extra fields inside an element return 400. * Fields not listed above return 400. `model` and `callback_url` belong at the request root, not inside `input`. * Credits are reserved at submission and depend on `resolution` and duration. When an input video is present, a separate input-video rate applies to billed seconds = output duration + the larger of the output duration and the total input video length (summed, then rounded up to whole seconds). A failed task is refunded in full. See the [pricing page](https://vidgo.ai/apis/api-pricing) for current rates. Requests with reference images or image elements only use the standard rate on the output duration. * Output is 720p or 1080p only; there is no 4K or HDR tier, no audio on/off switch and no `seed` on this model. ## OpenAPI ````yaml api-manual/video-series/kwaivgi-kling-v4-0-reference-to-video.json POST /api/generate/submit openapi: 3.0.0 info: title: Vidgo API - Kling 4.0 Reference to Video description: >- The Kling 4.0 Reference to Video API guides 3–30 second videos with up to 10 reference images, 5 reference videos and 7 elements, cited as @Image1 or @Element1. version: 1.0.0 servers: - url: https://api.vidgo.ai description: Production server security: - BearerAuth: [] paths: /api/generate/submit: post: tags: - Video Series summary: Kling 4.0 Reference to Video description: >- Send at least one of `reference_image_urls`, `reference_video_urls` or `kling_elements`, and exactly one of `prompt` or `multi_prompt`. Start frame plus reference images: at most 10. All assets together: at most 15. Input videos are downloaded and measured server-side (up to 100 MB each). Each must run 3–30 seconds, and all input videos together must not exceed 30 seconds. operationId: submit_kwaivgi_kling_v4_0_reference_to_video requestBody: required: true content: application/json: schema: type: object required: - model - input properties: model: type: string description: Model ID. Use `kwaivgi/kling-v4.0/reference-to-video`. example: kwaivgi/kling-v4.0/reference-to-video callback_url: type: string format: uri nullable: true description: >- Optional public HTTP(S) endpoint that receives a POST when the task becomes `finished` or `failed`. HTTPS is recommended. Omit it, or send `null` or an empty string, to disable callbacks. example: https://your-domain.com/callback input: type: object properties: reference_image_urls: type: array items: type: string format: uri maxItems: 10 description: >- Up to 10 public HTTP(S) reference image URLs (10 including the start frame). Refer to them in the prompt as `@Image1`, `@Image2`, … in array order. reference_video_urls: type: array items: type: string format: uri maxItems: 5 description: >- Up to 5 public HTTP(S) reference video URLs, each 3–30 seconds, 30 seconds in total. Refer to them as `@Video1`, `@Video2`, …. Billed as input video. kling_elements: type: array items: type: object properties: element_input_urls: type: array items: type: string format: uri minItems: 2 maxItems: 4 description: >- 2–4 public HTTP(S) image URLs showing the same subject. element_input_video_urls: type: array items: type: string format: uri minItems: 1 maxItems: 1 description: >- Exactly one public HTTP(S) video URL of the subject (3–30 seconds). Billed as input video. additionalProperties: false description: 'One element: images or one video of the same subject.' maxItems: 7 description: >- Up to 7 subjects (elements), at most 3 of them video-based. Each element has exactly one of `element_input_urls` or `element_input_video_urls`. Refer to them in the prompt as `@Element1`, `@Element2`, … in array order. image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 1 description: >- Optional start frame: at most one public HTTP(S) image URL. prompt: type: string minLength: 1 maxLength: 26000 description: >- Text prompt, 1–26,000 characters after trimming. Send exactly one of `prompt` or `multi_prompt`. multi_prompt: type: array items: type: object required: - prompt properties: prompt: type: string minLength: 1 maxLength: 512 description: Shot prompt, 1–512 characters. duration: type: integer minimum: 1 maximum: 30 default: 5 description: Shot length in seconds (integer). additionalProperties: false description: One shot. minItems: 1 description: >- Multi-shot prompt: a non-empty list of shots, each with its own `prompt` and optional `duration`. Shot durations must total 3–30 seconds. Send exactly one of `prompt` or `multi_prompt`. duration: type: integer minimum: 3 maximum: 30 default: 5 description: >- Output length in seconds (integer). With `multi_prompt` it defaults to the shot total and, if sent, must equal it. resolution: type: string enum: - 720p - 1080p default: 720p description: Output resolution. It sets the billing rate. aspect_ratio: type: string enum: - auto - '16:9' - '9:16' - '1:1' - '21:9' default: auto description: Output aspect ratio. `auto` lets the model choose. additionalProperties: false description: Generation parameters. examples: reference_images: summary: Reference images value: model: kwaivgi/kling-v4.0/reference-to-video input: reference_image_urls: - https://example.com/character.png - https://example.com/cafe.png prompt: >- @Image1 sits at a window table in the cafe from @Image2, sips coffee and waves at the camera, warm afternoon light duration: 8 resolution: 720p aspect_ratio: '16:9' elements_and_video: summary: Elements plus a reference video, with callback value: model: kwaivgi/kling-v4.0/reference-to-video callback_url: https://your-domain.com/callback input: kling_elements: - element_input_urls: - https://example.com/robot-front.png - https://example.com/robot-side.png reference_video_urls: - https://example.com/dance-move.mp4 prompt: >- @Element1 performs the dance from @Video1 on a rooftop at sunset, wide shot duration: 10 resolution: 1080p aspect_ratio: '9:16' responses: '200': description: Task submitted content: application/json: schema: type: object required: - code - data properties: code: type: integer enum: - 200 description: HTTP status code. data: type: object required: - task_id - status - created_time properties: task_id: type: string description: >- Task ID. Use it with [Query Task Status](/api-manual/task-management/status). status: type: string enum: - not_started description: Initial task status. created_time: type: string format: date-time description: Time the task was created (ISO 8601). example: code: 200 data: task_id: task-unified-1762160000-abc123 status: not_started created_time: '2026-11-03T10:30:00' '400': description: >- Invalid input, unsupported field, inaccessible media, or insufficient credits content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '401': description: Invalid credentials content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '403': description: Access denied content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '404': description: Unknown or disabled model content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '408': description: Request timed out content: text/plain: schema: type: string example: Request timeout '422': description: Invalid JSON or non-object request body content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '429': description: Rate or API key credit limit exceeded content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '500': description: Internal error content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '502': description: Unable to create the upstream generation task content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '503': description: The requested model is temporarily unavailable content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. components: securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key description: >- All API endpoints require Bearer Token authentication Get your API Key: Go to **Dashboard → API Key** ([API Key Management Page](https://vidgo.ai/apis/dashboard/api-key)) to get your API Key Add it to the request header: ``` Authorization: Bearer VIDGO_API_KEY ``` ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.