> ## Documentation Index > Fetch the complete documentation index at: https://docs-vip.apigo.ai/llms.txt > Use this file to discover all available pages before exploring further. # /api/v3/contents/generations/tasks > Submit a prompt and reference media to generate a video asynchronously. A successful call only returns the task ID; poll the query endpoint for the result. Authenticate with `Authorization: Bearer `. Tasks run asynchronously: a successful call only returns the task ID. Call [Get video generation task](https://docs-vip.apigo.ai/en/api-reference/endpoints/seedance/get-task.md) for the result. ## Models | Model ID | Description | | - | - | | `dreamina-seedance-2-0-260128` | Seedance 2.0 | Available durations, resolutions, aspect ratios and pricing depend on what is enabled for your account. ## content items | Type | Format | | - | - | | Text | `{"type":"text","text":"prompt"}` | | Image | `{"type":"image_url","role":"reference_image","image_url":{"url":"asset://"}}` | | Audio | `{"type":"audio_url","role":"reference_audio","audio_url":{"url":"asset://"}}` | | Video | `{"type":"video_url","role":"reference_video","video_url":{"url":"asset://"}}` | * `url` can be an asset in the asset library with `Status=Active` (`asset://`), or a publicly reachable HTTP(S) URL. See [Asset library](https://docs-vip.apigo.ai/en/api-reference/endpoints/seedance/asset-overview.md) for importing assets. * In the prompt, refer to reference media as "image 1", "audio 1", "video 1" by their order within each type in `content`. * Audio cannot be the only reference media; combine it with an image or video. * `audio_url` is an input reference, while `generate_audio` controls whether the output video has sound. They are independent. Set `generate_audio` to `true` when using a reference audio or the original sound of a reference video. ## Asset reference errors When a referenced asset cannot be used, HTTP 400 is returned with `error.code` set to `InvalidParameter`: | message | Action | | - | - | | `Asset '' does not exist.` | Check that the asset ID is correct and has not been deleted | | `Asset '' is still processing. Use it after its status becomes Active.` | Wait until [GetAsset](https://docs-vip.apigo.ai/en/api-reference/endpoints/seedance/get-asset.md) returns `Active`, then resubmit | | `Asset '' failed processing and cannot be used.` | Processing failed. Fix the source file and import it again | | `The referenced assets cannot be used together in one request.` | The referenced assets cannot be combined in one request. Create a new asset group, re-import all assets needed for this request into it, and reference them once all are `Active` | ## Error codes | HTTP status | error.type | error.code | Description | | - | - | - | - | | 400 | `BadRequest` | `InvalidParameter` | Invalid JSON, missing fields, wrong types, or unusable asset references | | 400 | `BadRequest` | `InvalidParameter.UnsupportedImageFormat`, `InputImageSensitiveContentDetected`, etc. | Media format, parameter or content moderation check failed. `param` may be empty; also read `message` | | 401 | `Unauthorized` | `AuthenticationError` | Missing or invalid API key | | 403 | `Forbidden` | `AccountOverdueError` | Insufficient balance | | 403 | `Forbidden` | `AccessDenied` | Blocked by IP allowlist or model permission | | 404 | `NotFound` | `InvalidEndpointOrModel.NotFound` | Model does not exist or is unavailable | | 429 | `TooManyRequests` | `AccountRateLimitExceeded` | Too many requests | | 429 | `TooManyRequests` | `QuotaExceeded` | API key quota reached | | 500 | `InternalServerError` | `InternalServiceError` | Internal or upstream error | > [!NOTE] > > If a create request times out or the connection drops, the task may already have been created. Retrying blindly can create duplicate tasks. ## OpenAPI ````yaml en/api-reference/openapi.json POST /api/v3/contents/generations/tasks openapi: 3.1.0 info: title: OpenAPI Plant Store description: >- A sample API that uses a plant store as an example to demonstrate features in the OpenAPI specification license: name: MIT version: 1.0.0 servers: - url: https://api-vip.apigo.ai security: - bearerAuth: [] paths: /api/v3/contents/generations/tasks: post: summary: Create a Seedance video generation task description: >- Submit a prompt and reference media to generate a video asynchronously. A successful call only returns the task ID; poll the query endpoint for the result. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SeedanceCreateTaskRequest' example: model: dreamina-seedance-2-0-260128 content: - type: text text: >- Make the apple in image 1 move slightly while keeping the subject and composition. - type: image_url role: reference_image image_url: url: asset://asset-20261020080000-abcde duration: 5 resolution: 720p ratio: '16:9' generate_audio: false watermark: false responses: '200': description: Task created content: application/json: schema: $ref: '#/components/schemas/SeedanceCreateTaskResponse' example: id: task_20261020080000abcdef '400': description: Invalid parameters or asset reference content: application/json: schema: $ref: '#/components/schemas/SeedanceErrorResponse' example: error: code: InvalidParameter message: >- Asset 'asset-20261020080000-abcde' is still processing. Use it after its status becomes Active. param: '' type: BadRequest '401': description: Missing or invalid API key content: application/json: schema: $ref: '#/components/schemas/SeedanceErrorResponse' example: error: code: AuthenticationError message: The API key is missing or invalid. param: '' type: Unauthorized '403': description: Insufficient balance, or blocked by IP allowlist or model permission content: application/json: schema: $ref: '#/components/schemas/SeedanceErrorResponse' example: error: code: AccountOverdueError message: Your account balance is insufficient. param: '' type: Forbidden '404': description: Model does not exist or is unavailable content: application/json: schema: $ref: '#/components/schemas/SeedanceErrorResponse' example: error: code: InvalidEndpointOrModel.NotFound message: >- The model or endpoint does not exist or you do not have access to it. param: '' type: NotFound '429': description: Too many requests or API key quota reached content: application/json: schema: $ref: '#/components/schemas/SeedanceErrorResponse' example: error: code: AccountRateLimitExceeded message: Too many requests, please retry later. param: '' type: TooManyRequests components: schemas: SeedanceCreateTaskRequest: type: object required: - model - content properties: model: type: string description: Model ID. example: dreamina-seedance-2-0-260128 content: type: array description: >- Array of prompt text and reference media. In the prompt, refer to media as "image 1", "audio 1", "video 1" by their order within each type. items: $ref: '#/components/schemas/SeedanceContentItem' duration: type: integer description: Video length in seconds. example: 5 resolution: type: string description: Output resolution, for example `720p`. example: 720p ratio: type: string description: Aspect ratio, for example `16:9` or `1:1`. example: '16:9' generate_audio: type: boolean description: >- Whether to generate sound. Set to `true` when using a reference audio or the original sound of a reference video. watermark: type: boolean description: Whether to add a watermark. priority: type: integer description: Task priority. Echoed back in the query result when provided. safety_identifier: type: string description: >- End-user identifier. Use an irreversible hash. Echoed back in the query result when provided. SeedanceCreateTaskResponse: type: object required: - id properties: id: type: string description: Task ID. SeedanceErrorResponse: type: object required: - error properties: error: type: object description: Error object. properties: code: type: string description: Error code, for example `InvalidParameter`. message: type: string description: Error message. param: type: string description: Name of the offending parameter. May be empty. type: type: string description: Error type, for example `BadRequest`. SeedanceContentItem: type: object required: - type properties: type: type: string enum: - text - image_url - audio_url - video_url description: Content type. text: type: string description: Prompt text. Required when `type=text`. role: type: string enum: - reference_image - reference_audio - reference_video description: >- Reference media role matching `type`: `reference_image` / `reference_audio` / `reference_video`. image_url: type: object description: Reference image. Required when `type=image_url`. required: - url properties: url: type: string description: >- `asset://` (the asset must be `Active`), or a publicly reachable HTTP(S) URL. audio_url: type: object description: >- Reference audio. Required when `type=audio_url`. Audio cannot be the only reference media; combine it with an image or video. required: - url properties: url: type: string description: >- `asset://` (the asset must be `Active`), or a publicly reachable HTTP(S) URL. video_url: type: object description: Reference video. Required when `type=video_url`. required: - url properties: url: type: string description: >- `asset://` (the asset must be `Active`), or a publicly reachable HTTP(S) URL. securitySchemes: bearerAuth: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.