> ## Documentation Index
> Fetch the complete documentation index at: https://docs.imini.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Wan 3.0 Video

> Wan 3.0 standard: text-to-video, first/last frames and multimodal references.



## OpenAPI

````yaml en/openapi/videos/wan3-0-video.yaml POST /v1/videos/generate
openapi: 3.1.0
info:
  title: Wan 3.0 Video
  version: '1.0'
  description: >-
    Wan 3.0 standard: text-to-video, first/last frames and multimodal
    references.
servers:
  - url: https://openapi.imini.ai/imini/router
security:
  - ApiKeyAuth: []
paths:
  /v1/videos/generate:
    post:
      summary: Wan 3.0 Video
      description: >
        Use model ID `wan3.0-video`, not `dashscope/wan3.0-video`. Poll the
        video task query endpoint after submission.


        Supports text-only, first frame, first and last frames, and mixed
        image/video/audio references. Frame inputs cannot mix with asset
        references; a last frame requires a first frame. Audio references
        require an image or video. Independent video editing and `edit_source`
        are not available in this release. Do not send `video_mode`.


        Defaults to 720P and 5 seconds. Credits per requested output second:
        480P 80, 720P 160, 1080P 280. Reference video duration adds no charge;
        audio generation does not change the price.


        Each input video must be 1-15 seconds; combined input video duration
        must not exceed 15 seconds. Input video duration plus requested output
        duration must not exceed 30 seconds; the provider validates these
        limits. Media must be publicly accessible. keep_original_sound,
        generate_bgm and extension parameters are not supported.
      operationId: generateWan30Video
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - prompt
              properties:
                model:
                  type: string
                  enum:
                    - wan3.0-video
                prompt:
                  type: string
                  minLength: 1
                  maxLength: 20000
                  description: Required prompt.
                resolution:
                  type: string
                  enum:
                    - 480P
                    - 720P
                    - 1080P
                  default: 720P
                duration:
                  type: integer
                  minimum: 2
                  maximum: 30
                  default: 5
                  description: Requested output duration in seconds; -1 is not accepted.
                aspect_ratio:
                  type: string
                  enum:
                    - '16:9'
                    - '9:16'
                    - '1:1'
                    - '4:3'
                    - '3:4'
                  description: >-
                    Optional; the model adapts the output aspect ratio when
                    omitted.
                generate_audio:
                  type: boolean
                  default: false
                  description: Generate audio; does not affect credits.
                reference_images:
                  type: array
                  maxItems: 10
                  description: >-
                    Up to 10 asset images; frame control permits one first frame
                    and one optional last frame.
                  items:
                    type: object
                    required:
                      - url
                    properties:
                      url:
                        type: string
                        description: Public HTTP(S) image URL or data:image/ Base64.
                      reference_type:
                        type:
                          - string
                          - 'null'
                        default: asset
                        description: >-
                          asset (default), first_frame or last_frame. Omitted,
                          null, empty and unknown strings are treated as asset.
                reference_videos:
                  type: array
                  maxItems: 5
                  items:
                    type: object
                    required:
                      - url
                    properties:
                      url:
                        type: string
                        description: Public HTTP(S) video URL; Base64 is not supported.
                      reference_type:
                        type:
                          - string
                          - 'null'
                        default: asset
                        description: >-
                          Use asset for reference video. Omitted, null, empty
                          and unknown strings become asset. edit_source is not
                          supported.
                reference_audios:
                  type: array
                  maxItems: 5
                  description: Must accompany asset image or video references.
                  items:
                    type: object
                    required:
                      - url
                    properties:
                      url:
                        type: string
                        description: Public HTTP(S) audio URL; Base64 is not supported.
                      reference_type:
                        type:
                          - string
                          - 'null'
                        default: asset
                        description: >-
                          asset; omitted, null, empty and unknown strings become
                          asset.
            examples:
              text:
                summary: Text to video
                value:
                  model: wan3.0-video
                  prompt: A slow camera move across a garden in morning light.
                  resolution: 720P
                  duration: 5
              frames:
                summary: First and last frames
                value:
                  model: wan3.0-video
                  prompt: Smoothly transition between the two scenes.
                  duration: 5
                  reference_images:
                    - url: https://example.com/first.png
                      reference_type: first_frame
                    - url: https://example.com/last.png
                      reference_type: last_frame
              mixed:
                summary: Mixed references (replace with accessible media URLs)
                value:
                  model: wan3.0-video
                  prompt: >-
                    Generate a garden scene using the supplied visual and sound
                    references.
                  resolution: 480P
                  duration: 5
                  generate_audio: true
                  reference_images:
                    - url: https://example.com/image.png
                      reference_type: asset
                  reference_videos:
                    - url: https://example.com/video.mp4
                      reference_type: asset
                  reference_audios:
                    - url: https://example.com/audio.mp3
                      reference_type: asset
      responses:
        '200':
          description: Task accepted; poll for the result.
          content:
            application/json:
              schema:
                type: object
                properties:
                  task_id:
                    type: string
                  model:
                    type: string
                    example: wan3.0-video
                  created_at:
                    type: string
                    description: ISO 8601 UTC
                  request_id:
                    type: string
        '400':
          description: Invalid request parameters
          content:
            application/json:
              schema:
                type: object
                properties:
                  error:
                    type: object
                    properties:
                      code:
                        type: string
                      message:
                        type: string
                      status:
                        type: integer
                      request_id:
                        type: string
components:
  securitySchemes:
    ApiKeyAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: >-
        Use Authorization: Bearer <YOUR_API_KEY>. [API
        Keys](https://imini.ai/api-keys)

````