MiniMax H3 Reference to Video

POST

https://api.apipod.ai/v1/videos/generations

text to video

Last modified:2026-08-01 03:12:45

MiniMax H3, opensource, unifies text, image, video, and audio for 2K video generation, multimodal referencing, native stereo sound, motion transfer, and precise editing.

MiniMax H3 Reference to Video supports reference images, reference videos and reference audios, with a maximum of 9 images, 3 videos and 3 audios. Audio cannot be used independently; at least one reference image or one reference video is required. First frame/last frame fields are not allowed!

Request

Authorization

Bearer Token

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Body Params application/jsonRequired

Examples

Responses

🟢200成功

application/json

Bodyapplication/json

Request Example

Shell

JavaScript

Java

Swift

curl --location 'https://api.apipod.ai/v1/videos/generations' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "minimax-h3-r2v",
    "prompt": "minim dolor",
    "image_urls": [],
    "video_urls": [],
    "audio_urls": [
        "https://limping-comparison.us/",
        "https://dark-convection.biz/"
    ],
    "aspect_ratio": "ad",
    "duration": 10,
    "resolution": "2K"
}'

Response Example

{
    "code": 200,
    "message": "string",
    "data": {
        "task_id": "string"
    }
}

Modified at 2026-08-01 03:12:45

MiniMax H3 Image to Video

Query Video Task