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

# Hailuo H3 Reference to Video

> Hailuo H3 (MiniMax-H3) reference-to-video: drive generation with reference images, videos and audio. Output is always 2K.

At least one `ref_imgs` or `ref_videos` item is required — audio alone is not accepted. First/last frames are not supported here; use the `hailuo_h3` model for those.

**Pricing:** billed per second — 2K is 7.15 tokens/s ($0.143/s). 768P (4.95 tokens/s) is coming soon.

Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video.



## OpenAPI

````yaml api-reference/video-generations/openapi-hailuo-h3-refs.json POST /api/v1/videos/generations
openapi: 3.1.0
info:
  title: GoEnhance API - Hailuo 2.3
  description: Video generation with Hailuo 2.3.
  version: 1.0.0
servers:
  - url: https://api.goenhance.ai
security: []
paths:
  /api/v1/videos/generations:
    post:
      tags:
        - VideoGenerations
      summary: Hailuo H3 Reference to Video
      description: >-
        Hailuo H3 (MiniMax-H3) reference-to-video: drive generation with
        reference images, videos and audio. Output is always 2K.


        At least one `ref_imgs` or `ref_videos` item is required — audio alone
        is not accepted. First/last frames are not supported here; use the
        `hailuo_h3` model for those.


        **Pricing:** billed per second — 2K is 7.15 tokens/s ($0.143/s). 768P
        (4.95 tokens/s) is coming soon.


        Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use
        `custom_callback_url`) to get the generated video.
      parameters:
        - name: Authorization
          in: header
          description: ''
          required: false
          example: '{{Authorization}}'
          schema:
            type: string
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                model:
                  type: string
                  enum:
                    - hailuo_h3_refs
                  description: Model name. Must be `hailuo_h3_refs`.
                prompt:
                  type: string
                  maxLength: 7000
                  description: >-
                    Text prompt describing the video. Required. Max 7000
                    characters.
                ref_imgs:
                  type: array
                  items:
                    type: string
                    format: uri
                  maxItems: 9
                  description: >-
                    Reference images (up to 9). JPG/PNG/WEBP/HEIC/HEIF, ≤30MB
                    each, 256–5760px, aspect ratio 0.4–2.5.
                ref_videos:
                  type: array
                  items:
                    type: string
                    format: uri
                  maxItems: 3
                  description: >-
                    Reference videos (up to 3). mp4/mov, 2–15s each and ≤15s
                    total, ≤50MB each, frame rate 23.976–60.
                ref_audios:
                  type: array
                  items:
                    type: string
                    format: uri
                  maxItems: 3
                  description: >-
                    Reference audio (up to 3). wav/mp3, 2–15s each and ≤15s
                    total, ≤15MB each. Requires at least one ref_imgs or
                    ref_videos item.
                resolution:
                  type: string
                  enum:
                    - 2K
                  default: 2K
                  description: >-
                    Output resolution. Only 2K is available today; 768P is
                    coming soon.
                duration:
                  type: integer
                  minimum: 4
                  maximum: 15
                  default: 5
                  description: Video duration in seconds. Any integer from 4 to 15.
                ratio:
                  type: string
                  enum:
                    - adaptive
                    - '21:9'
                    - '16:9'
                    - '4:3'
                    - '1:1'
                    - '3:4'
                    - '9:16'
                  default: adaptive
                  description: >-
                    Aspect ratio. Defaults to adaptive (chosen automatically
                    from the reference assets).
                custom_callback_url:
                  type: string
                  format: uri
                  description: >-
                    Optional. A publicly accessible HTTPS URL. When the task
                    status changes (processing / success / failed), GoEnhance
                    sends a POST request to this URL. The request body is
                    identical to the response of GET /api/v1/jobs/detail. If
                    your server does not respond with HTTP 200, the notification
                    is retried up to 3 times, with a 3-second timeout per
                    attempt.
                  example: https://your-server.com/goenhance/callback
              required:
                - model
                - prompt
            example:
              model: hailuo_h3_refs
              prompt: Character speaks in the style of the reference video
              ref_imgs:
                - https://your-cdn.com/character.jpg
              ref_videos:
                - https://your-cdn.com/reference.mp4
              ref_audios:
                - https://your-cdn.com/voice.mp3
              duration: 5
              ratio: adaptive
      responses:
        '200':
          description: ''
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: integer
                  msg:
                    type: string
                  data:
                    type: object
                    properties:
                      img_uuid:
                        type: string
                    required:
                      - img_uuid
                required:
                  - code
                  - msg
                  - data
              examples:
                '1':
                  summary: Success
                  value:
                    code: 0
                    msg: Success
                    data:
                      img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5
                '2':
                  summary: Insufficient tokens
                  value:
                    code: 100
                    msg: tokens is not enough
          headers: {}
        '401':
          description: ''
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: integer
                  msg:
                    type: string
                required:
                  - code
                  - msg
          headers: {}
      deprecated: false
      security: []

````