minimaxiH3 Get access
MiniMaxImage-to-videoVendor content policy applies

Hailuo-2.3 Fast

Speed-optimized variant of Hailuo-2.3 delivering rapid video generation while maintaining strong visual quality for quick iterations.

$0.29per secondStarting price at the base resolution and quality tier.
$2.28Typical 8-second clip at the base tier. Longer or higher-resolution outputs scale with duration and tier.
Pay per useBilled per request from your balance. No subscription, no minimum.
Sample output · prompt: “A powerful curved beam of light forcefully pierces through a transparent glass cube. The impact creates sharp refractions and scattering light rays. Fine cracks spread across the surface as shards subtly vibrate. Cinemat…”

What it does

Hailuo-2.3 Fast, in practice.

Hailuo 2.3 Fast is the high-speed version of MiniMax’s latest video generation model. It produces cinematic-quality videos 30–50% faster than the standard model while maintaining stable motion, clear detail, and balanced lighting — ideal for creators who need both speed and quality.

  • Accelerated Generation – Create 6–10 second clips up to twice as fast as Hailuo 2.3 Standard.
  • High Efficiency, Low Cost – Perfect for batch content creation, previews, and iteration loops.
  • Consistent Quality – Despite faster generation, visual stability and motion smoothness remain impressive.
  • Safety & Prompt Expansion – Built-in safety checker and automatic prompt enhancement for optimal output.
  • Flexible Durations – Supports both 6-second and 10-second formats at 1080p clarity.
  • Input: text prompt *(optional reference image for stability)*

Run Hailuo-2.3 Fast

from $0.29/sec
Drop an image hereor click to choose a fileFiles stay in your project. Nothing is trained on.
duration
Invite code opens Chat with this model loaded. No code yet? Join the waitlist — we count which models people ask for.

Parameters

What you can set.

ParameterWhat it doesOptions
durationThe duration of the generated media in seconds.6 10
enable_prompt_expansionThe model automatically optimizes incoming prompts to enhance output quality. This also activates the safety checker, which ensures content safety by detecting and filtering potential risks.default True
go_fastPrioritize faster video generation speed with a moderate trade-off in visual qualitydefault True
imageThe model generates video with the picture passed in as the first frame.Base64 encoded strings in data:image/jpeg; base64,{data} format for incoming images, or URLs accessible via the public network. The uploaded image needs to meet the fol
promptThe positive prompt for the generation.

Sample prompt

The prompt behind the sample.

A powerful curved beam of light forcefully pierces through a transparent glass cube. The impact creates sharp refractions and scattering light rays. Fine cracks spread across the surface as shards subtly vibrate. Cinematic lighting, high contrast, volumetric light, ultra-detailed glass texture, slow motion.
duration: 6enable_prompt_expansion: Truego_fast: True

FAQ

Short answers.

How much does Hailuo-2.3 Fast cost?

Pricing starts at $0.29 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $2.28. Usage is billed per request from your balance — no subscription.

Does Hailuo-2.3 Fast run uncensored here?

No. MiniMax applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Hailuo-2.3 Fast for everything else it does well.

What does Hailuo-2.3 Fast take as input?

It is a image-to-video model. Speed-optimized variant of Hailuo-2.3 delivering rapid video generation while maintaining strong visual quality for quick iterations.

How do I use it?

Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.

Related

Models people compare with this one.

Run Hailuo-2.3 Fast.

Invite code opens Chat with the model loaded. No code — join the waitlist and we will count the request.

Get access Browse models