MiniMax H3 Video Generation
Generate synchronized audio-video from text, a starting image, first and last frames, or multimodal references through the PixMind API.
Generate synchronized audio-video from text, a starting image, first and last frames, or multimodal references.
Provider
MiniMaxModel ID
minimax-h3Endpoint
POST /api-platform/v1/generationsModel notes
- Accepts 4-15 second durations in one-second steps and generates synchronized audio.
- Use referenceImages for multimodal reference generation; see the MiniMax H3 Eco page for the lower-cost text and image routes.
Request parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Stable PixMind model ID. Use `minimax-h3`. Allowed values: |
prompt | string | Yes | Natural-language generation or editing instructions. |
resolution | string | No | Output video resolution. This field affects per-second pricing. Allowed values: Default: |
duration | integer | No | Requested clip duration in seconds. Allowed values: Default: |
aspectRatio | string | No | Requested output aspect ratio. Allowed values: Default: |
imageUrl | string (URI) | No | Starting image for image-to-video generation. |
referenceImages | string[] (URI) | No | Reference image URLs used for editing, composition, subject, or style guidance. |
last_frame_url | string (URI) | No | Optional ending frame paired with imageUrl. |
generateAudio | boolean | No | Generate synchronized audio when supported by the selected mode. Allowed values: Default: |
Request example
curl https://aihub-admin.aimix.pro/api-platform/v1/generations \
-H "Authorization: Bearer $PIXMIND_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3",
"prompt": "A continuous cinematic product reveal with synchronized studio ambience",
"duration": 10,
"resolution": "768P",
"aspectRatio": "16:9",
"generateAudio": true
}'const response = await fetch("https://aihub-admin.aimix.pro/api-platform/v1/generations", {
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.PIXMIND_API_KEY}`,
"Content-Type": "application/json"
},
body: JSON.stringify({
"model": "minimax-h3",
"prompt": "A continuous cinematic product reveal with synchronized studio ambience",
"duration": 10,
"resolution": "768P",
"aspectRatio": "16:9",
"generateAudio": true
})
});
const task = await response.json();Accepted task response
Generation is asynchronous. Save taskId and poll GET /api-platform/v1/tasks/{taskId} until status is ready or failed.
{
"code": 1000,
"data": {
"id": "img_44160",
"taskId": 44160,
"type": "video",
"model": "minimax-h3",
"status": "processing"
}
}API pricing
| Configuration | Price |
|---|---|
| H3 standard, 768P from | $0.090 / second |
API pricing uses the apiPlatform role and is separate from PixMind Studio credits. The accepted task response is the final pricing snapshot.
Seedance 2.5 Video Generation
Generate native 30-second video with up to 50 multimodal references and region-level editing through the PixMind API.
MiniMax H3 Eco Video Generation
Lower-cost synchronized audio-video generation from text, a starting image, or first and last frames through the PixMind API.