MiniMax H3 Reference to Video API
Reference to Video with MiniMax H3 by MiniMax. Hailuo H3 — expressive motion and physics, up to 2K.
Try MiniMax H3 Reference to Video
Up to 5 images for characters, products, style or scene. Refer to them in the prompt as @Image1, @Image2…
Up to 3 MP4/MOV clips for motion, camera moves or effects (2–15 s each, 15 s in total, ≤ 50 MB each). Refer to them as @Video1, @Video2… Reference-video seconds are billed like output seconds.
Up to 3 MP3/WAV clips for voice, music or sound (2–15 s each, 15 s in total, ≤ 15 MB each). Refer to them as @Audio1, @Audio2… Needs at least one reference image or video.
Output frame shape.
Output resolution. Higher resolutions cost more per second.
Length of the generated clip in seconds (5–15s). You pay per second.
Create a free account with Google or email — pay only for what you generate.
Your video will appear here
Write a prompt, pick your settings and hit Run. You only pay for successful generations.
Also available: MiniMax H3 Text to Video · MiniMax H3 Image to Video
MiniMax H3 Reference to Video API
/api/v1/run/minimax/h3/reference-to-videoSubmits an asynchronous job and returns 202 with a generation id. Poll GET /api/v1/generations/{id} or pass webhook_url. See job lifecycle.
Input parameters
| Name | Type | Description | Affects price |
|---|---|---|---|
promptrequired | string | Describe the shot: subject, action, camera movement, lighting and style. | No |
reference_image_urls | string[] (URLs) | Up to 5 images for characters, products, style or scene. Refer to them in the prompt as @Image1, @Image2… Max items: 5 | No |
reference_video_urls | string[] (video URLs) | Up to 3 MP4/MOV clips for motion, camera moves or effects (2–15 s each, 15 s in total, ≤ 50 MB each). Refer to them as @Video1, @Video2… Reference-video seconds are billed like output seconds. Max items: 3 | Yes |
reference_audio_urls | string[] (audio URLs) | Up to 3 MP3/WAV clips for voice, music or sound (2–15 s each, 15 s in total, ≤ 15 MB each). Refer to them as @Audio1, @Audio2… Needs at least one reference image or video. Max items: 3 | No |
aspect_ratio | string (enum) | Output frame shape. Values: 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9 Default: 16:9 | Yes |
resolution | string (enum) | Output resolution. Higher resolutions cost more per second. Values: 768P · 2K Default: 768P | Yes |
duration | integer | Length of the generated clip in seconds (5–15s). You pay per second. Range: 5–15s Default: 6 | Yes |
seed | integer | Use the same seed and settings to reproduce a result. Leave empty for random. | No |
webhook_url | string (URL) | Optional. We POST the finished generation here, signed with your webhook secret. Webhooks | No |
Request
curl -X POST https://cheapergen.com/api/v1/run/minimax/h3/reference-to-video \
-H "Authorization: Bearer $CHEAPERGEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "The mascot from @Image1 dances in front of the storefront from @Image2, following the moves in @Video1",
"reference_image_urls": [
"https://cdn.cheapergen.ai/samples/reference-1.jpg",
"https://cdn.cheapergen.ai/samples/reference-2.jpg"
],
"reference_video_urls": [
"https://cdn.cheapergen.ai/samples/reference-1.mp4"
],
"aspect_ratio": "16:9",
"resolution": "768P",
"duration": 6
}'Response
{
"id": "gen_8c2QmX1nq0k4",
"object": "generation",
"model": "minimax/h3",
"endpoint": "minimax/h3/reference-to-video",
"mode": "reference-to-video",
"status": "queued",
"input": {
"prompt": "The mascot from @Image1 dances in front of the storefront from @Image2, following the moves in @Video1",
"reference_image_urls": [
"https://cdn.cheapergen.ai/samples/reference-1.jpg",
"https://cdn.cheapergen.ai/samples/reference-2.jpg"
],
"reference_video_urls": [
"https://cdn.cheapergen.ai/samples/reference-1.mp4"
],
"aspect_ratio": "16:9",
"resolution": "768P",
"duration": 6
},
"output": null,
"error": null,
"cost": {
"amount_usd": 0.2255,
"currency": "usd",
"estimated": true,
"official_usd": null,
"saved_usd": null
},
"source": "api",
"started_at": null,
"completed_at": null,
"urls": {
"get": "https://cheapergen.com/api/v1/generations/gen_8c2QmX1nq0k4",
"cancel": "https://cheapergen.com/api/v1/generations/gen_8c2QmX1nq0k4/cancel"
},
"created_at": "2026-10-15T09:21:04Z"
}MiniMax H3 pricing
Pay per second of video. No subscription. Failed generations are refunded automatically.
| Tier | Official price | Cheaper Gen. | You save |
|---|---|---|---|
768P per second | $0.041/s | −49% | |
2K per second | $0.066/s | −49% |
- Official price: MiniMax international official price ($0.08 / $0.13 per second; reference-video seconds billed at the output rate, reference audio free). Prices verified 2026-10-14.
- Reference-video seconds are billed at the output rate; reference audio is free.
Related models

MiniMaxH3 Max
Text · Image → Video
The enhanced H3 for sharper detail and stronger prompt following

Seedance2.0
Text · Image · Reference → Video
Cinematic multi-shot video with native audio, up to 4K

Wan3.0
Text · Image · Reference → Video
Up to 30-second videos with audio from Alibaba
