> ## Documentation Index > Fetch the complete documentation index at: https://docs.aiohub.org/llms.txt > Use this file to discover all available pages before exploring further. # Create video ยท OpenAI video > Submit a Seedance video task using OpenAI video, with examples, input limits and full parameters. Use this format with an existing OpenAI SDK `client.videos` integration. It supports text or one first-frame image at 720p. Use [Ark / Seedance](/en/api/video-ark) for reference audio, multiple reference images and video editing. ## Setup Set the OpenAI SDK base URL to `https://api.aiohub.org/v1` and supply your full AIOHub `sk-` API key. This is the video API, not Chat Completions or Responses. ## Example request Replace `` with your full API key. Its group must include the Seedance model used here. ```bash theme={"system"} curl https://api.aiohub.org/v1/videos \ -H "Authorization: Bearer " \ -H "Content-Type: application/json" \ -d '{ "model": "doubao-seedance-2-5-260628", "prompt": "A blue ceramic cup on a wooden table in daylight.", "seconds": "4", "size": "1280x720" }' ``` The creation response includes these fields. Save `id`; do not submit another creation request to check progress. ```json theme={"system"} {"id": "task_example", "object": "video", "status": "queued", "progress": 0} ``` After saving the task identifier, [poll the task](/en/api/video-openai-get). ## Parameter limits Use `application/json` for JSON requests and `multipart/form-data` with the `input_reference` field for file uploads. Crop or resize an image to match `size` before submitting. Install the `openai` SDK and set `AIOHUB_API_KEY` in your environment. These examples download only after generation succeeds. ```python Python theme={"system"} import os from openai import OpenAI client = OpenAI(api_key=os.environ["AIOHUB_API_KEY"], base_url="https://api.aiohub.org/v1") video = client.videos.create( model="doubao-seedance-2-5-260628", prompt="A blue ceramic cup on a wooden table in daylight, slow camera push-in.", seconds="4", size="1280x720", ) video = client.videos.poll(video.id) if video.status != "completed": raise RuntimeError(f"Video generation failed: {video.error}") with open("video.mp4", "wb") as f: f.write(client.videos.download_content(video.id).read()) ``` ```typescript TypeScript theme={"system"} import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.AIOHUB_API_KEY, baseURL: "https://api.aiohub.org/v1" }); let video = await client.videos.create({ model: "doubao-seedance-2-5-260628", prompt: "A blue ceramic cup on a wooden table in daylight, slow camera push-in.", seconds: "4", size: "1280x720", }); while (video.status !== "completed" && video.status !== "failed") { await new Promise((r) => setTimeout(r, 15000)); video = await client.videos.retrieve(video.id); } if (video.status !== "completed") { throw new Error(JSON.stringify(video.error)); } const bytes = await (await client.videos.downloadContent(video.id)).arrayBuffer(); ``` If creation times out without a task identifier, check the [usage log](https://api.aiohub.org/console/log) before resubmitting to avoid duplicate generation and charges. Correct parameters after a 400 and check the API key after a 401. See [Authentication](/en/api/authentication) for access and quota requirements. ## OpenAPI ````yaml openapi/relay.en.json POST /v1/videos openapi: 3.0.1 info: title: AIOHub API description: AIOHub public API version: 1.0.0 servers: - url: https://api.aiohub.org security: - BearerAuth: [] tags: - name: List models - name: OpenAI Chat - name: OpenAI Responses - name: Image generation - name: OpenAI Images - name: Video generation - name: Claude Messages - name: Gemini API - name: OpenAI Embeddings - name: Text completions - name: OpenAI Audio - name: Realtime API paths: /v1/videos: post: tags: - Video generation summary: Create video description: > OpenAI-compatible video generation endpoint. Works with the OpenAI SDK `videos` client. Seedance models generate 720p video through this endpoint: `seconds` is `"4"`, `"8"` or `"12"` (default `"4"`), `size` is `"1280x720"` or `"720x1280"` (default), and the optional `input_reference` is a first-frame image whose pixel size must equal `size`. For reference images, audio, video edit, 1080p or 4k, longer clips or other aspect ratios, use the task endpoints described in [Ark / Seedance](/en/api/video-ark). Reference: https://platform.openai.com/docs/api-reference/videos/create operationId: createVideo parameters: [] requestBody: content: application/json: schema: type: object required: - model - prompt properties: model: type: string example: doubao-seedance-2-5-260628 description: Model name prompt: type: string example: >- A blue ceramic cup on a wooden table in daylight, slow camera push-in. description: Prompt seconds: type: string example: '4' description: Duration in seconds size: type: string example: 1280x720 description: Video size input_reference: type: string example: https://example.com/first.png description: First-frame image as an HTTPS URL or data URL examples: text: summary: Text to video value: model: doubao-seedance-2-5-260628 prompt: A blue ceramic cup on a wooden table in daylight. seconds: '4' size: 1280x720 multipart/form-data: schema: type: object properties: model: type: string example: doubao-seedance-2-5-260628 description: Model name prompt: description: Prompt example: cute cat dance type: string seconds: type: string example: '4' description: Duration in seconds input_reference: format: binary type: string description: Reference image file example: '' size: type: string example: 1280x720 description: >- Video size. Seedance models accept `1280x720` and `720x1280`. examples: {} responses: '200': description: Video task created successfully content: application/json: schema: type: object properties: id: type: string description: Video ID object: type: string description: Object type model: type: string description: Model used status: type: string description: Task status progress: type: integer description: Progress percentage created_at: type: integer description: Creation timestamp seconds: type: string description: Video duration completed_at: type: integer description: Completion timestamp expires_at: type: integer description: Expiration timestamp size: type: string description: Video size error: $ref: '#/components/schemas/OpenAIVideoError' metadata: type: object description: Additional metadata additionalProperties: true properties: {} required: - id - object - model - status - progress - created_at - seconds example: id: task_ADQ5XK6AKWg36WePoJ3sZRyDvWl1ogGZ object: video model: doubao-seedance-2-5-260628 status: queued progress: 0 created_at: 1791275108 seconds: '4' size: 1280x720 headers: {} '400': description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: {} deprecated: false security: - BearerAuth: [] components: schemas: OpenAIVideoError: type: object description: OpenAI video error information properties: message: type: string description: Error message code: type: string description: Error code ErrorResponse: type: object properties: error: type: object properties: message: type: string description: Error message type: type: string description: Error type param: type: string description: Related parameters nullable: true code: type: string description: Error code nullable: true securitySchemes: BearerAuth: type: http scheme: bearer description: API key (sk-xxx) ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.