> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt > Use this file to discover all available pages before exploring further. # seedance-2.0-mini > Create an asynchronous video generation task. Supports multiple input modes: - Text-to-video - Image-to-video (first frame / first+last frame) - Multimodal reference (image + video + audio combinations) - Video editing - Video extension - Web search enhanced generation Poll `GET /v1/video/generations/{id}` until `status` is `succeeded`. ## OpenAPI ````yaml api-reference/model-api/bytedance/openapi/seedance-2-0-mini/openapi.yaml POST /v1/video/generations openapi: 3.1.0 info: title: Seedance 2.0 Mini description: >- ByteDance's lightweight Seedance 2.0 Mini video generation model with text-to-video, image-to-video, multimodal reference, video editing, video extension, audio generation, and web search. version: 1.0.0 servers: - url: https://www.anyfast.ai security: - bearerAuth: [] paths: /v1/video/generations: post: summary: Create Video Generation Task description: > Create an asynchronous video generation task. Supports multiple input modes: - Text-to-video - Image-to-video (first frame / first+last frame) - Multimodal reference (image + video + audio combinations) - Video editing - Video extension - Web search enhanced generation Poll `GET /v1/video/generations/{id}` until `status` is `succeeded`. operationId: createSeedanceMini requestBody: required: true content: application/json: schema: type: object required: - model - content properties: model: type: string enum: - seedance-2.0-mini description: Model ID example: seedance-2.0-mini content: type: array description: > Input content array for video generation. Supports text, images, videos, and audio in various combinations: - Text only - Text (optional) + Image(s) - Text (optional) + Video(s) - Text (optional) + Image + Audio - Text (optional) + Image + Video - Text (optional) + Video + Audio - Text (optional) + Image + Video + Audio items: type: object properties: type: type: string enum: - text - image_url - video_url - audio_url description: > Content type: - `text` — Text prompt - `image_url` — Image input (first frame / last frame / reference) - `video_url` — Video input (reference video) - `audio_url` — Audio input (reference audio) text: type: string description: >- Text prompt describing the desired video. Recommended max 500 Chinese characters or 1000 English words. image_url: type: object description: Image object. properties: url: type: string description: > Image URL, Base64 data URI, or asset ID (`asset://`). Supported formats: jpeg, png, webp, bmp, tiff, gif. Max 30 MB per image. video_url: type: object description: Video object. properties: url: type: string description: > Video URL or asset ID (`asset://`). Supported formats: mp4, mov. Max 50 MB, duration 2–15s. audio_url: type: object description: >- Audio object. Must be combined with at least one image or video. properties: url: type: string description: > Audio URL, Base64 data URI, or asset ID (`asset://`). Supported formats: wav, mp3. Max 15 MB, duration 2–15s. role: type: string enum: - first_frame - last_frame - reference_image - reference_video - reference_audio description: > Role of the content item: - `first_frame` — First frame image (image-to-video) - `last_frame` — Last frame image (first+last frame mode) - `reference_image` — Reference image (multimodal reference, 0–9 images) - `reference_video` — Reference video (multimodal reference, max 3 videos) - `reference_audio` — Reference audio (multimodal reference, max 3 clips) example: - type: text text: A cat playing piano in a sunlit room - type: image_url image_url: url: https://example.com/reference.jpg role: reference_image generate_audio: type: boolean default: true description: > Generate synchronized audio with the video. - `true` — Video includes auto-generated voice, sound effects, and background music - `false` — Silent video resolution: type: string enum: - 480p - 720p default: 720p description: >- Output video resolution. Seedance 2.0 Mini does not support 1080p. ratio: type: string enum: - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' - '21:9' - adaptive default: adaptive description: > Output aspect ratio. `adaptive` automatically selects the best ratio based on input. duration: type: integer minimum: 4 maximum: 15 default: 5 description: | Video duration in seconds (integer, 4–15). tools: type: array description: >- Tools for the model to use. Currently supports web search (text-to-video only). items: type: object properties: type: type: string enum: - web_search description: >- Tool type. `web_search` enables internet search for real-time content. watermark: type: boolean default: false description: Add watermark to the generated video. responses: '200': description: Video generation task created content: application/json: schema: type: object properties: id: type: string description: Task ID for polling example: cgt-20260312231129-7db6s task_id: type: string description: Task ID (same as id) example: cgt-20260312231129-7db6s object: type: string example: video model: type: string example: seedance-2.0-mini status: type: string description: Initially empty example: '' progress: type: integer example: 0 created_at: type: integer description: Unix timestamp example: 1773328294 '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: Error: type: object properties: error: type: object properties: code: type: string message: type: string securitySchemes: bearerAuth: type: http scheme: bearer ````