MiniMax H3 Max

NEW

VideoUltra

fal's post-trained MiniMax H3, ranked #1 for overall quality, prompt understanding, and aesthetics against leading video models. 5-15 second clips from a prompt or a start frame, tuned for prompt adherence and rendered on a throughput-optimized stack.

Capabilities

Text to VideoImage to Video

Specifications

Aspect Ratios

21:916:94:31:13:49:16

Supported Durations

5s6s7s8s9s10s11s12s13s14s15s

Estimated Generation Time

~1-2 min

API Usage

cURL

curl https://www.flixly.ai/api/v1/generate \
  -H "Authorization: Bearer flx_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "h3-max",
    "prompt": "A beautiful sunset over the ocean",
    "type": "TEXT_TO_VIDEO"
  }'

Get your API key from the Developer Portal.

Try MiniMax H3 Max

Generate content with this model now. New users get 10 free credits.

Model Details

Quality Score97/100

TierUltra

TypeVideo

Speed~1-2 min

Related Models

View all

Sora 2 Pro

VideoUltra

Sora 2 with enhanced quality and longer durations

Sora 2

VideoUltra

State-of-the-art video generation model with exceptional quality and understanding

Veo 3.1

VideoUltra

Premium video generation model with native audio

Seedance 2.5

VideoUltra

ByteDance's newest video model. Generates up to 30 seconds in a single shot with synchronized audio — dialogue, music, and effects in the same pass — from a prompt, a start frame, or up to 50 image, video, and audio references.