> ## Documentation Index > Fetch the complete documentation index at: https://docs.gengen.farm/llms.txt > Use this file to discover all available pages before exploring further. # Create a WonderClip video task > Create a WonderClip text, frame-guided, or multimodal video generation task. ## OpenAPI ````yaml openapi/wonderclip-video.yaml POST /contents/generations/tasks openapi: 3.1.0 info: title: WonderClip video API version: 1.0.0 description: Provider-specific GENGEN reference for WonderClip video generation. servers: - url: https://gengen.farm/api/gengen/v1 description: Production security: - bearerAuth: [] paths: /contents/generations/tasks: post: summary: Create a WonderClip video task description: > Create an asynchronous WonderClip video task through the shared GENGEN endpoint. This page intentionally exposes only WonderClip models, modes, assets, and controls. The standalone `happyhorse-1.1` model uses the separate Happy Horse integration. [Try WonderClip Pro in the API Explorer](https://gengen.farm/api-explorer/demos/video-generation?model=wonder-pro). operationId: createWonderClipVideoTask requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateWonderClipVideoTaskRequest' examples: textToVideo: summary: Text to video value: model: wonder-pro mode: text_to_video prompt: A paper spacecraft glides above a neon city at blue hour. controls: resolution: 1080p ratio: '16:9' duration: 6 outputCount: 2 firstAndLastFrame: summary: First-and-last-frame video value: model: wonder-standard mode: image_first_last_frame prompt: >- Move smoothly from the opening composition to the closing composition. assets: firstFrameImage: https://example.com/first.jpg lastFrameImage: https://example.com/last.jpg controls: resolution: 720p ratio: '9:16' duration: 5 outputCount: 1 multimodalReference: summary: Multimodal reference video value: model: wonder-pro mode: multimodal_reference prompt: >- Use the character design and camera movement from the references. assets: referenceImages: - https://example.com/character.png referenceVideos: - https://example.com/camera-reference.mp4 referenceAudio: https://example.com/music-reference.mp3 controls: resolution: 1080p ratio: '16:9' duration: 8 outputCount: 1 responses: '200': description: The task was accepted. content: application/json: schema: $ref: '#/components/schemas/VideoTask' example: id: wonderclip10:ag_123 model: wonder-pro status: queued outputs: videos: [] images: [] '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '402': $ref: '#/components/responses/PaymentRequired' '403': $ref: '#/components/responses/Forbidden' default: $ref: '#/components/responses/UnexpectedError' x-codeSamples: - lang: bash label: Text to video source: | curl --request POST \ --url https://gengen.farm/api/gengen/v1/contents/generations/tasks \ --header 'Authorization: Bearer gengen_live_xxxxxxxxxxxxxxxx' \ --header 'Content-Type: application/json' \ --data '{ "model": "wonder-pro", "mode": "text_to_video", "prompt": "A paper spacecraft glides above a neon city at blue hour.", "controls": { "resolution": "1080p", "ratio": "16:9", "duration": 6, "outputCount": 2 } }' components: schemas: CreateWonderClipVideoTaskRequest: type: object required: - model - prompt properties: model: type: string description: | Supported WonderClip public model IDs: - `wonder-pro` — WonderClip Pro - `wonder-standard` — WonderClip Standard - `wonder-happyhorse-1.1` — Happy Horse 1.1 through WonderClip - `wonder-happyhorse-1.0` — Happy Horse 1.0 through WonderClip enum: - wonder-pro - wonder-standard - wonder-happyhorse-1.1 - wonder-happyhorse-1.0 mode: type: string description: > WonderClip generation mode. GENGEN can infer the mode from assets, but an explicit value is recommended. Supported values: - `text_to_video` — generate from a text prompt - `image_first_frame` — animate a first-frame image - `image_first_last_frame` — interpolate between first and last frames - `multimodal_reference` — guide generation with reference media enum: - text_to_video - image_first_frame - image_first_last_frame - multimodal_reference prompt: type: string minLength: 1 description: Required generation instructions for every WonderClip mode. assets: $ref: '#/components/schemas/WonderClipAssets' controls: $ref: '#/components/schemas/WonderClipControls' additionalProperties: false VideoTask: type: object required: - id - model - status - outputs properties: id: type: string model: type: string status: type: string outputs: $ref: '#/components/schemas/GenerationOutputs' createdAt: type: string format: date-time updatedAt: type: string format: date-time statusUpdateTime: type: string format: date-time additionalProperties: true WonderClipAssets: type: object description: | Reference media is limited to 1–9 items in total. The `wonder-happyhorse-1.1` model accepts only image references in `multimodal_reference` mode. properties: firstFrameImage: type: string format: uri description: Required for first-frame and first-and-last-frame modes. lastFrameImage: type: string format: uri description: Required for first-and-last-frame mode. referenceImages: type: array maxItems: 9 items: type: string format: uri referenceVideos: type: array maxItems: 9 items: type: string format: uri referenceAudio: type: string format: uri additionalProperties: false WonderClipControls: type: object properties: resolution: type: string default: 720p description: | Supported values: - `720p` — HD output - `1080p` — Full HD output enum: - 720p - 1080p ratio: type: string default: '16:9' description: | Supported values: - `1:1` — square video - `4:3` / `3:4` — landscape or portrait standard format - `16:9` / `9:16` — landscape or portrait widescreen format enum: - '16:9' - '9:16' - '4:3' - '3:4' - '1:1' duration: type: integer minimum: 4 maximum: 15 default: 5 outputCount: type: integer minimum: 1 maximum: 4 default: 1 additionalProperties: false GenerationOutputs: type: object required: - videos - images properties: videos: type: array items: type: string format: uri images: type: array items: type: string format: uri additionalProperties: true Error: type: object properties: error_code: type: string error: type: string error_params: type: object additionalProperties: true additionalProperties: true responses: BadRequest: description: The WonderClip request is invalid. content: application/json: schema: $ref: '#/components/schemas/Error' Unauthorized: description: The bearer token is missing or invalid. content: application/json: schema: $ref: '#/components/schemas/Error' PaymentRequired: description: The workspace does not have enough available balance. content: application/json: schema: $ref: '#/components/schemas/Error' Forbidden: description: The API key is not authorized for this operation. content: application/json: schema: $ref: '#/components/schemas/Error' UnexpectedError: description: GENGEN or WonderClip could not complete the request. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: GENGEN API key description: A workspace API key beginning with `gengen_live_`. ````