Skip to main content
ReachAPIReachAPI
MiniMax H3

MiniMax H3

MiniMax Hailuo-03 for high-quality asynchronous video generation with frame and multimodal references.

Hailuo-03Multimodal VideoAsync Tasks

Execution

Async video

Submit a task, then poll or use a callback

Duration

4-15s

Integer output duration

Resolution

2K / 768P

Mode-dependent fixed or adaptive aspect ratios

Output price

$0.08-$0.13 / sec

Based on output resolution

Model Codeminimax-h3

Playground

minimax-h3
First Frame0/1

Click or drag

Last Frame0/1

Click or drag

4s8s15s

Resolution (sent to backend)

Aspect Ratio (sent to backend)

No output yet

Pricing

MeterResolutionPriceBilling basis
Output video2K$0.13 / secondActual output duration
Output video768P$0.08 / secondActual output duration
Reference video input2K$0.13 / secondReference video duration
Reference video input768P$0.08 / secondReference video duration
Additional input imagesAny$0.04 / imageFirst 5 free; charged from the 6th

768P · $0.08 · per second

2K · $0.13 · per second

README

MiniMax H3 generates 4-15 second videos at 2K or 768P from text, first/last frames, or image, video, and audio references through ReachAPI's asynchronous task API.
  • MiniMax H3 supports text-to-video, first-frame image-to-video, first-and-last-frame generation, and multimodal reference workflows.
  • Multimodal reference mode accepts up to 9 reference images, 3 reference videos, and 3 reference audio files. Frame inputs and reference media cannot be mixed in one request.
  • Text-only requests require a fixed aspect ratio. Frame modes always use the input image ratio, while reference mode supports an effective fixed ratio or adaptive source ratio.

API

Use the API docs for request format, parameters, and integration details.

MiniMax Hailuo-03 for high-quality asynchronous video generation with frame and multimodal references.

Model Code

minimax-h3

View API Docs

API

Playground coming soon

Related Models

Related video models

Seedance 2.5

ByteDance's Seedance 2.5 model for long-form multimodal video generation, editing, extension, and audio-driven creation.

Seedance 2

ByteDance's Seedance 2 video model for multimodal reference input, editing, extension, and asynchronous generation.

Seedance 2 Fast

ByteDance's faster Seedance 2 variant for multimodal asynchronous video generation at lower per-second rates.

Seedance 1.5 Pro

ByteDance's Seedance 1.5 Pro video model for higher-capability text and frame-guided video generation.

Seedance 1.0 Pro

ByteDance's Seedance 1.0 Pro video generation model for text-guided and frame-guided cinematic video tasks.

Seedance 1.0 Pro Fast

ByteDance's faster Seedance 1.0 Pro variant for lower-cost asynchronous video generation.