Model API

MiniMax H3 LoRA

Video with synchronized audio from MiniMax H3 with your trained LoRA for a consistent subject. Start from an image as the first frame, from reference images, or from text.

Model id

Use this in every request

minimax/h3/text-to-video/lora

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/h3/text-to-video/lora",
  "input": {
    "prompt": "A red ceramic cup on a wooden table, soft morning light",
    "loras": [
      {
        "path": "example"
      }
    ]
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "minimax/h3/text-to-video/lora", "quote_id": "QUOTE_ID", "input": {"prompt":"A red ceramic cup on a wooden table, soft morning light","loras":[{"path":"example"}]}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for minimax/h3/text-to-video/lora
Name	Type	Description
`prompt`required	string	Text prompt for video generation
`duration`	integer	The duration of the video in seconds. Default: `5`
`resolution`	string (enum)	The resolution of the generated video. 480P and 768P are native generation modes; 2K and 4K upscale a 768P base result. Default: `2K` One of: `480P`, `768P`, `2K`, `4K`
`seed`	integer	Random seed. A random seed is selected when omitted.
`sync_mode`	boolean	Return the generated video as base64 instead of a CDN URL. Default: `false`
`prompt_expansion_mode`	string	How much effort to spend rewriting the prompt before generation. 'disabled' skips prompt expansion. 'fast' returns in about a second. 'balanced' picks per request. 'quality' spends up to ~30s on a richer prompt. Default: `balanced`
`target_audio_url`	string (URL)	Optional URL of an audio clip at least 2 seconds long (maximum 15 MB) to pin to the generated soundtrack. Longer clips are trimmed to the generated video's length, keeping the beginning. The original audio replaces the output soundtrack, padded with silence if shorter than the video, without changing playback speed. Exceptionally high sample rates may be resampled to 96 kHz. Accepts an HTTP(S) URL or a base64 data URI.
`aspect_ratio`	string (enum)	The aspect ratio of the generated video. Default: `16:9` One of: `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`
`loras`required	array of objects	List of LoRA adapters to apply to the transformer.

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt

"outputs": [
  { "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]

Pricing

480P$0.0991/ second
768P$0.1189/ second
2K$0.2575/ second
4K$0.317/ second

The exact charge for your input comes from a quote. How charges settle