MiniMax H3 Reference-to-Video

Endpoint

POST /videos/generations

Full URL: https://modelfold.ai/v1/videos/generations

Authentication: every request must include the Authorization: Bearer <API_KEY> header.

Send model parameters directly in the JSON body. Do not wrap them in input. This request waits for generation to finish and returns data[].url; supported media models also offer async jobs, polling and callbacks. Replace example media URLs with your own publicly accessible files. See API gateway for billing and errors.

Request Parameters

Body (application/json)

Parameter	Type	Required	Description
model	string	Yes	The name of the model used for the generation task. Used for MiniMax H3 reference-to-video. Default："minimax-h3/reference-to-video"。 Allowed values：minimax-h3/reference-to-video。 Example：minimax-h3/reference-to-video。
prompt	string	Yes	Prompt required by the ModelFold gateway; at most 2000 characters. Video generation prompt, length is between 1 and 7000 characters. minLength: 1. maxLength: 2000. Example：Generate a continuous cinematic video referencing the characters, actions, and scenes in the input material。
reference_image_urls	array<string>	No	Array of reference image URLs. Supports up to 9 images. Publicly accessible HTTP(S) URL; supported image formats include JPG, JPEG, PNG, WEBP, HEIC, and HEIF; a single image size cannot exceed 30 MB; the side length of the image must be between 256 and 5760 pixels, and the aspect ratio must be between 0.4 and 2.5. Provide at least one of reference_image_urls or reference_video_urls. maxItems: 9.
reference_video_urls	array<string>	No	Array of reference video URLs. Supports up to 3 videos. Supports MP4, MOV; video encoding supports H.264, H.265; a single file size cannot exceed 50 MB; the duration of a single segment is 2 to 15 seconds, and the total duration of all reference videos cannot exceed 15 seconds; the video side length must be between 256 and 5760 pixels, the aspect ratio must be between 0.4 and 2.5, and the frame rate must be between 23.976 and 60. Provide at least one of reference_image_urls or reference_video_urls. maxItems: 3.
reference_audio_urls	array<string>	No	Array of reference audio URLs. Supports up to 3 audios. Supports WAV, MP3; a single file size cannot exceed 15 MB; the duration of a single segment is 2 to 15 seconds, and the total duration of all reference audios cannot exceed 15 seconds. reference_audio cannot be used alone, it must be accompanied by reference_image or reference_video. maxItems: 3.
aspect_ratio	string	No	Video aspect ratio. The default is adaptive, or a specific ratio can be specified. Default："adaptive"。 Allowed values：adaptive / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16。 Example：adaptive。
duration	integer	Yes	The duration of the generated video, supporting integer values from 4 to 15 seconds. Default：6。 Allowed values：4 / 5 / 6 / 7 / 8 / 9 / 10 / 11 / 12 / 13 / 14 / 15。 minimum: 4. maximum: 15. Example：6。
resolution	string	No	Video resolution. Default："2K"。 Allowed values：768P / 2K。 Example：2K。

Request Example

curl -X POST "https://modelfold.ai/v1/videos/generations" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-h3/reference-to-video",
  "prompt": "Generate a continuous cinematic video referencing the characters, actions, and scenes in the input material",
  "duration": 6,
  "aspect_ratio": "adaptive",
  "resolution": "2K"
}'

{
  "model": "minimax-h3/reference-to-video",
  "prompt": "Generate a continuous cinematic video referencing the characters, actions, and scenes in the input material",
  "duration": 6,
  "aspect_ratio": "adaptive",
  "resolution": "2K"
}

Response

200 — Generation completed. usage contains actual billing details; result URLs are illustrative.

{
  "ok": true,
  "created": 1792134000,
  "data": [
    {
      "url": "https://modelfold.ai/uploads/outputs/result.mp4"
    }
  ],
  "usage": {}
}