> ## Documentation Index > Fetch the complete documentation index at: https://docs.poyo.ai/llms.txt > Use this file to discover all available pages before exploring further. # Kling 4.0 Flash > Generate fast 720p videos of 3–20 seconds from text, a start frame, or visual references, and edit an existing video. > [!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 response result through the unified [Query Task Status](https://docs.poyo.ai/api-manual/task-management/status.md) endpoint. Kling 4.0 Flash is the faster 720p tier of [Kling 4.0](https://docs.poyo.ai/api-manual/video-series/kling-4-0.md). It creates videos from text, animates a starting frame, combines visual references, or edits an existing video. The supplied media selects the mode automatically. ## Models * **kling-4.0-flash** — Text-to-video, image-to-video, reference-to-video, and video editing at `720p` ## Features * **Fast 720p output**: Generate 3–20 second videos at `720p`. * **Starting frame**: Animate one starting image. Flash does not accept an ending frame. * **Visual references**: Guide appearance and movement with reference images, reference videos, and subjects defined by images or a video. * **Video editing**: Supply a source video and describe the changes. Editing also accepts reference images, reference videos, and subjects. Omit `duration` to retain the source video's duration. * **Aspect ratios**: Use `16:9`, `9:16`, `1:1`, `21:9`, or `auto` in text and reference modes. ## Input modes | Mode | Selected when | | - | - | | Video editing | `video_url` is provided | | Reference-to-video | Reference images, reference videos, or `kling_elements` are non-empty | | Image-to-video | `image_urls` is non-empty without reference materials | | Text-to-video | No media is provided | In reference mode, `image_urls` may contain one optional starting frame. In image mode, `prompt` is optional; omit `aspect_ratio`, because the output follows the starting frame's aspect ratio. Editing does not accept `image_urls` or `aspect_ratio`; the output follows the source video's aspect ratio. ## Required parameters * `prompt` (string): Video instructions, 1–26,000 characters, containing at least one non-whitespace character. Required in every mode except image-to-video, where it is optional. ## Optional parameters * `duration` (integer): Output duration from 3 to 20 seconds. Generation defaults to `5`. In editing, omit this field to retain the source video's duration; chargeable output duration is rounded up to whole seconds. * `resolution` (string): `720p` only. Default: `720p`. * `aspect_ratio` (string): `auto`, `16:9`, `9:16`, `1:1`, or `21:9`, for text and reference modes. Default: `16:9`. In text-to-video, `auto` is treated as `16:9`; in reference mode, `auto` adapts to the supplied materials. Omit this field in image and editing modes. * `image_urls` (array of strings): One starting image. * `video_url` (string): Source video for editing. Must last 3–20 seconds. * `reference_image_urls` (array of strings): Up to 10 publicly accessible HTTP or HTTPS image URLs. * `reference_video_urls` (array of strings): Publicly accessible HTTP or HTTPS video URLs, each lasting 3–20 seconds. Up to 5 in reference mode and up to 4 in editing mode. * `kling_elements` (array of objects): Up to 7 subjects. Each subject supplies exactly one of: * `element_input_urls` (array of strings): 2–4 images, with the frontal view first and additional reference views after it. * `element_input_video_urls` (array of strings): Exactly one 3–8 second video. At most 3 subjects may use videos. Subjects use their positions in the array and require no names. Refer to them as `@Element1`, `@Element2`, and so on. Reference images use `@Image1`, `@Image2`, and so on. In reference mode, reference videos start at `@Video1`; in editing mode, the source video is `@Video1` and reference videos start at `@Video2`. Existing `@image_1` and `@video_1` references remain supported. ## Examples ### Text to Video ```json theme={"dark"} { "model": "kling-4.0-flash", "callback_url": "https://your-domain.com/callback", "input": { "prompt": "A paper boat drifts through a miniature city at sunset, slow camera push-in", "duration": 5, "aspect_ratio": "16:9" } } ``` ### Image to Video ```json theme={"dark"} { "model": "kling-4.0-flash", "input": { "prompt": "The red panda shakes the snow off its fur and turns toward the camera", "image_urls": ["https://example.com/start-frame.png"], "duration": 5 } } ``` ### Reference Images and Subjects ```json theme={"dark"} { "model": "kling-4.0-flash", "input": { "prompt": "@Element1 walks along the cliff path toward the lighthouse in @Image1 at golden hour", "reference_image_urls": ["https://example.com/lighthouse.png"], "kling_elements": [ { "element_input_urls": [ "https://example.com/keeper-front.png", "https://example.com/keeper-side.png" ] } ], "duration": 8, "aspect_ratio": "9:16" } } ``` ### Reference Videos ```json theme={"dark"} { "model": "kling-4.0-flash", "input": { "prompt": "Follow the camera movement of @Video1 in the snowy mountain scene from @Image1", "reference_image_urls": ["https://example.com/mountain.png"], "reference_video_urls": ["https://example.com/camera-motion.mp4"], "duration": 8, "aspect_ratio": "16:9" } } ``` ### Video Editing ```json theme={"dark"} { "model": "kling-4.0-flash", "input": { "prompt": "Change the season in @Video1 to spring using @Image1, keeping the motion and camera", "video_url": "https://example.com/source.mp4", "reference_image_urls": ["https://example.com/spring.png"] } } ``` ## Notes * In reference mode, the optional starting frame and reference images together cannot exceed 10 images. The number of starting frames, reference images, reference videos, and subjects combined cannot exceed 15. Images inside a subject count as one subject, not as separate materials. * The source video, reference videos, and video-based subjects must have a combined original duration of at most 20 seconds. Each source or reference video must last 3–20 seconds, and each subject video 3–8 seconds. * Flash does not support `1080p`, ending frames, or `multi_prompt`. Use [Kling 4.0](https://docs.poyo.ai/api-manual/video-series/kling-4-0.md) for these. * Reference indexes start at 1 and follow the order of the corresponding input array. Use publicly accessible media URLs and omit unused optional fields. ## OpenAPI ````yaml api-manual/video-series/kling-4-0-flash.json POST /api/generate/submit openapi: 3.0.0 info: title: Kling 4.0 Flash description: >- Generate fast 720p videos from text, a start frame, or visual references, and edit an existing video. version: 1.0.0 servers: - url: https://api.poyo.ai security: - BearerAuth: [] paths: /api/generate/submit: post: summary: Submit a Kling 4.0 Flash video task operationId: submit_kling_4_0_flash requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SubmitRequest' examples: text-to-video: summary: Generate video from a text prompt value: model: kling-4.0-flash input: prompt: A paper boat floats through a miniature city at sunset. image-to-video: summary: Animate a starting image value: model: kling-4.0-flash input: image_urls: - https://example.com/start.png prompt: The camera slowly pushes in as the lanterns flicker. duration: 10 reference-image: summary: Guide the video with a reference image value: model: kling-4.0-flash input: prompt: >- The character in @Image1 walks along a sunlit forest trail. reference_image_urls: - https://example.com/character.png aspect_ratio: '9:16' reference-video: summary: Guide movement with a reference video value: model: kling-4.0-flash input: prompt: >- Recreate the camera movement from @Video1 in a snowy mountain landscape. reference_video_urls: - https://example.com/camera-motion.mp4 duration: 8 image-subject: summary: Guide a subject with a frontal view and reference views value: model: kling-4.0-flash input: prompt: '@Element1 walks through the city square shown in @Image1.' reference_image_urls: - https://example.com/square.png kling_elements: - element_input_urls: - https://example.com/character-front.png - https://example.com/character-side.png video-edit: summary: Edit a video while retaining its original duration value: model: kling-4.0-flash input: prompt: >- Replace the background of @Video1 with a snowy mountain landscape while keeping the camera movement. video_url: https://example.com/source.mp4 responses: '200': description: Task submitted successfully content: application/json: schema: $ref: '#/components/schemas/SubmitResponse' '400': description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized - Invalid API key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: SubmitRequest: type: object additionalProperties: false required: - model - input properties: model: type: string enum: - kling-4.0-flash description: Public model identifier. callback_url: type: string format: uri description: Optional webhook URL for task completion or failure notifications. example: https://your-domain.com/callback input: type: object additionalProperties: false description: >- Selects editing when video_url is supplied, reference-to-video when reference images, reference videos, or subjects are supplied, image-to-video when only image_urls is supplied, and text-to-video otherwise. All media URLs must be publicly accessible HTTP or HTTPS URLs. properties: prompt: type: string minLength: 1 maxLength: 26000 description: >- Video instructions containing at least one non-whitespace character. Required in every mode except image-to-video, where it is optional. Reference images, videos, and subjects as @Image1, @Video1, and @Element1 in array order. In editing, the source video is @Video1 and reference videos start at @Video2. Existing @image_1 and @video_1 references remain supported. example: >- A paper boat drifts through a miniature city at sunset, slow camera push-in duration: type: integer minimum: 3 maximum: 20 description: >- Output duration in whole seconds. Generation defaults to 5 seconds. In editing, omit this field to retain the source video duration; chargeable output duration is rounded up to whole seconds. example: 5 resolution: type: string enum: - 720p default: 720p description: Output video resolution. Flash supports 720p only. example: 720p aspect_ratio: type: string enum: - auto - '16:9' - '9:16' - '1:1' - '21:9' default: '16:9' description: >- Output aspect ratio for text and reference modes. Defaults to 16:9. In text-to-video, auto is treated as 16:9; in reference mode, auto adapts to the supplied materials. Do not provide this field in image or editing modes; those modes follow the aspect ratio of the starting frame or source video. example: '16:9' reference_image_urls: type: array maxItems: 10 items: type: string format: uri description: >- Up to 10 publicly accessible HTTP or HTTPS reference images. Reference them as @Image1, @Image2, and so on. In reference mode, these images and the optional starting frame together cannot exceed 10 images. Supported in reference and editing modes. example: - https://example.com/reference-image.png reference_video_urls: type: array maxItems: 5 x-video-duration-seconds: minimum: 3 maximum: 20 items: type: string format: uri description: >- Publicly accessible HTTP or HTTPS reference videos, each lasting 3-20 seconds. Up to 5 in reference mode, referenced as @Video1, @Video2, and so on; up to 4 in editing mode, referenced as @Video2, @Video3, and so on. All input videos together must not exceed 20 seconds. example: - https://example.com/reference-video.mp4 image_urls: type: array maxItems: 1 items: type: string format: uri description: >- One publicly accessible HTTP or HTTPS starting frame. Flash does not accept an ending frame. Without references, selects image-to-video. In reference mode, the starting frame counts toward the 10-image and 15-material limits. Do not provide this field in editing mode. minItems: 1 example: - https://example.com/start-frame.png video_url: type: string format: uri x-video-duration-seconds: minimum: 3 maximum: 20 description: >- Publicly accessible HTTP or HTTPS source video for editing, lasting 3-20 seconds. Selects editing mode. Supports reference images, reference videos, and subjects; cannot be combined with image_urls or aspect_ratio. example: https://example.com/source.mp4 kling_elements: type: array maxItems: 7 items: type: object additionalProperties: false minProperties: 1 maxProperties: 1 description: >- Provide exactly one of element_input_urls and element_input_video_urls. Subjects use array positions, such as @Element1, and require no names. properties: element_input_urls: type: array maxItems: 4 items: type: string format: uri description: >- Publicly accessible HTTP or HTTPS images of this subject: frontal view first, followed by 1-3 additional reference views. minItems: 2 element_input_video_urls: type: array maxItems: 1 x-video-duration-seconds: minimum: 3 maximum: 8 items: type: string format: uri description: >- Exactly one publicly accessible HTTP or HTTPS subject video lasting 3-8 seconds. At most 3 subjects may use videos. minItems: 1 description: >- Up to 7 position-based subjects. Use @Element1, @Element2, and so on in the prompt. At most 3 subjects may use videos. Supported in reference and editing modes. In reference mode, starting frames, reference images, reference videos, and subjects combined cannot exceed 15 materials; images inside a subject count as one subject. example: - element_input_urls: - https://example.com/subject-front.png - https://example.com/subject-side.png SubmitResponse: type: object required: - code - data properties: code: type: integer example: 200 enum: - 200 - 400 - 401 - 402 - 403 - 404 - 408 - 429 - 500 - 502 - 503 description: >- Business status code. `200` means success; any other value means the request failed. Always check this field: some validation errors return HTTP 200 with `code: 400` in the body. - `200`: Success - `400`: Invalid request parameters - `401`: Missing or invalid API key - `402`: Insufficient credits - `403`: Permission denied - `404`: Resource not found - `408`: Request timeout - `429`: Rate limit exceeded - `500`: Internal server error - `502`: Upstream service error - `503`: Service unavailable See [Error Codes](/api-manual/error-codes) for details. data: type: object required: - task_id - status - created_time properties: task_id: type: string example: task-unified-1792741800-example status: type: string enum: - not_started - running - finished - failed example: not_started description: >- Task status. Always `not_started` right after submission. Use [Query Task Status](/api-manual/task-management/status) or `callback_url` to get later states. - `not_started`: Queued, waiting to be processed - `running`: Being generated - `finished`: Completed; results are in `files` or `output` - `failed`: Failed; details are in `error_message` created_time: type: string format: date-time example: '2026-10-23T10:30:00' ErrorResponse: type: object required: - code - error properties: code: type: integer example: 400 enum: - 200 - 400 - 401 - 402 - 403 - 404 - 408 - 429 - 500 - 502 - 503 description: >- Business status code. `200` means success; any other value means the request failed. Always check this field: some validation errors return HTTP 200 with `code: 400` in the body. - `200`: Success - `400`: Invalid request parameters - `401`: Missing or invalid API key - `402`: Insufficient credits - `403`: Permission denied - `404`: Resource not found - `408`: Request timeout - `429`: Rate limit exceeded - `500`: Internal server error - `502`: Upstream service error - `503`: Service unavailable See [Error Codes](/api-manual/error-codes) for details. error: type: object required: - message - type properties: message: type: string example: Invalid request parameters type: type: string example: invalid_request_error securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key description: >- All API endpoints require Bearer Token authentication. Create an API key: sign in to PoYo, open **Dashboard → API Key** at [poyo.ai/dashboard/api-key](https://poyo.ai/dashboard/api-key), and click to create a key. Add it to the request header: ``` Authorization: Bearer YOUR_API_KEY ``` ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.