Video Generationtextimagevideoaudio

MiniMax H3 Highspeed

MiniMax H3 Highspeed balances generation quality and speed, with text-to-video, image-to-video, first-and-last-frame, and multimodal reference workflows at 768P with native audio.

Entrada

Generation mode

Describe the video with text only—no images required.

Prompt

Reference image (optional)

Compatible con JPG/JPEG, PNG, WebP, HEIC, HEIF · se admite arrastrar y soltar

Duration

415

Resolution

Aspect ratio

Ready to generate

Referencia de la API

POSThttps://api.token360.ai/v1/videos

# Step 1: Create video generation task
curl https://api.token360.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "minimax-h3-highspeed",
  "prompt": "A cat walking across a room",
  "duration": 5,
  "resolution": "768p",
  "aspect_ratio": "16:9"
}'

# Step 2: Poll for completion (replace VIDEO_ID with the id from step 1)
curl https://api.token360.ai/v1/videos/VIDEO_ID \
  -H "Authorization: Bearer your-api-key"

API Documentation

Overview#

MiniMax H3 Highspeed balances quality and speed for 768P video generation. It supports text-to-video, image-to-video, first-and-last-frame, and multimodal references with native audio.

API#

POST https://api.token360.ai/v1/videos using model minimax-h3-highspeed. Use frame_images for first/last-frame input and input_references for reference images, videos, or audio.