Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Balance
Subscription
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksEarn crypto
  1. Models
  2. Video
  3. MiniMax

MiniMax H3 Max Turbo

Try Model

MiniMax H3 Max Turbo generates 480p, 768p, or 1080p video from text, first/last frames, or image/video/audio references with synchronized audio. Text and frame modes support 5–15 seconds; references support 0.92–15 seconds and may run about 0.7 seconds longer. Use up to 9 images, 3 videos, and 3 audio clips, with 12 files total and 2–15 seconds per clip, at most 15 seconds per media type. Reference generation reserves $5 from your account balance and refunds the unused amount after billed output and reference usage are confirmed.

Added Sep 2, 2026

Details

Starting Price
From $0.125 per video
Model type
both

Final price depends on the selected settings and is shown before generation.

Settings

Generation controls available for this model.

Output Format

up to 1,080p
Square
Portrait
Landscape

Default Duration

5

Aspect Ratio

Select

Default

16:9

Options (7)

adaptive, 21:9, 16:9, 4:3 +3 more

Adaptive is available in reference mode.

Duration (seconds)

Number

Default

5

References: 0.92–15 seconds; output may run about 0.7 seconds longer. Text and first/last frames: 5–15 whole seconds.

Mode

Select

Default

auto

Options (2)

Auto-detect, Reference to Video

Ordered references (JSON)

Text

Default

N/A

Optional array of {type: image/video/audio, url}. Preserves mixed order. Do not combine with separate reference inputs.

Prompt Expansion

Select

Default

balanced

Options (3)

disabled, balanced, quality

Reference audio URLs

Text

Default

N/A

Optional URL, one URL per line, or a JSON array of URLs.

Reference image URLs

Text

Default

N/A

Optional URL, one URL per line, or a JSON array of URLs.

Reference video URLs

Text

Default

N/A

Optional URL, one URL per line, or a JSON array of URLs.

Resolution

Select

Default

768p

Options (3)

480p, 768p, 1080p

Showing 9 of 11 settings.

Benchmarks

No public benchmark scores for this model yet.

Examples

Loading examples…

Related video models

Compare MiniMax H3 Max Turbo with similar models from the same provider or model family.

MiniMax H3 Max

minimax/h3-max

Generate from text, first/last frames, or image/video/audio references.

MiniMax H3 Highspeed

minimax/h3-highspeed

MiniMax H3 Highspeed creates 4–15 second videos at 768p with native audio. Generate from text, animate a starting image with an optional end frame, or combine up to nine image, three video, and three audio references. Reference clips must be 2–15 seconds each, totaling at most 15 seconds per media type. Audio references require an image or video. Frame guidance and reference inputs cannot be combined.

MiniMax H3 Lite

minimax/h3-lite

MiniMax H3 Lite creates 4–15 second videos at 480p or 768p with native audio. Generate from text, animate a starting image with an optional end frame, or combine up to nine image, three video, and three audio references. Reference clips must be 2–15 seconds each, totaling at most 15 seconds per media type. Audio references require an image or video. Frame guidance and reference inputs cannot be combined.

MiniMax H3 Spicy Image-to-Video

wavespeed-ai/minimax-h3/image-to-video-spicy

Open-weights MiniMax H3 image-to-video generation with expressive unrestricted motion, native stereo audio, optional last-frame control, 3–15 second clips, and 480p or 768p output.

MiniMax H3

minimax-h3

Generate from text, images, or references with optional custom LoRAs. Editing and extension require no LoRA weights.

MiniMax Hailuo 2.3 Pro

minimax-hailuo-23-pro

MiniMax Hailuo 2.3 Pro delivers cinematic 1080p 5-second clips with advanced physics, prompt fidelity, and character consistency. Supports both pure text prompts and image-conditioned motion.