HedraVideo to videoComing soon

minimax-h3

Name: minimax-h3
Brand: Hedra

minimax-h3 is a video to video tool from Hedra that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt` required	text	—	Generation prompt. From 1 to 7000 characters.
`resolution` required	one of 480p, 768p, 2K, 4K	—	Output resolution.
`duration_ms` required	one of 5000, 6000, 7000, 8000, 9000, 10000, 11000, 12000, 13000, 14000, 15000	—	Duration in ms.
`audios`	JSON	—	Reference audios. 1 to 3 audio files, each from 2s to 15s and at most 104.8 MB, at most 15s in total.
`images`	JSON	—	Reference images. 1 to 5 images, each from 256px to 5760px on each side, with an aspect ratio from 0.4 to 2.5, and at most 30 MB.
`videos`	JSON	—	Reference videos. 1 to 3 videos, each from 2s to 15s and at most 524.2 MB, at most 15s in total.
`end_image`	JSON	—	A file uploaded via POST /v3/files, referenced by the returned url.
`num_outputs`	one of 1	1	Number of outputs generated per job. Only 1 is supported.
`start_image`	JSON	—	A file uploaded via POST /v3/files, referenced by the returned url.
`aspect_ratio`	one of 1:1, 3:4, 4:3, 16:9, 21:9, 9:16, adaptive	—	Output aspect ratio. Omitted or `adaptive` uses the supported ratio nearest the first reference image, else the first reference video.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "hedra",
    "model": "minimax-h3",
    "input": {
      "prompt": "<prompt>",
      "resolution": "480p",
      "duration_ms": 5000
    }
  }'