VidMachine

VidMachine

MiniMax

Hailuo 3

MiniMax · AI video
Hailuo 3 (MiniMax H3) is MiniMax's video generation model on OpenRouter. It turns a text prompt and optional first/last frames into short clips, with native audio generation and a 2K resolution tier.
The API accepts 5–15 second durations and common aspect ratios including 9:16 and 16:9. First-frame and last-frame images can condition the start and end of the clip.
On VidMachine, scene generation uses image-to-video at 2K with your scene starting frame and motion prompt—routed via OpenRouter at 26 credits per second.

Key features and benefits

Text-to-video and image-to-video

Describe the clip with a prompt, or condition generation on a first frame (and optionally a last frame) so motion starts from your key art.

2K output

Hailuo 3 generates at a 2K resolution tier on OpenRouter, with aspect ratios such as 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16.

Native audio

Optional audio generation produces sound alongside the video in one pass.

Duration

Clips run 5–15 seconds per generation.

Technical specifications

ProviderMiniMax (Hailuo 3 / H3)
Primary inputsText prompt; optional first-frame and last-frame images; optional reference images
Resolution2K
Aspect ratio21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Duration5–15 seconds
AudioOptional native audio generation

Use cases and applications

Use Hailuo 3 for cinematic shorts, product motion from stills, and 9:16 social clips when you want MiniMax's Hailuo motion profile at 2K.
First-and-last-frame control is useful when you already have start and end keyframes and want the model to interpolate motion between them.

Why this model

Pick Hailuo 3 when you want MiniMax's latest Hailuo video stack with 2K output and native audio on OpenRouter.
Compare credit cost and look with other 2K / high-tier models in your project settings before committing a long export.

How VidMachine uses it

VidMachine generates scene clips via image-to-video at 2K, using each scene's starting frame and motion prompt. Duration is clamped to the model's 5–15 second range. Optional last-frame images are sent when available. Generation is routed through OpenRouter.
Billing is 26 credits per second of output video.

What you should know

What resolution does VidMachine use?
Scene generation runs at Hailuo 3's 2K tier via OpenRouter, billed at 26 credits per second.
Does Hailuo 3 support last-frame control?
Yes. The OpenRouter API accepts first_frame and last_frame images. VidMachine sends the scene start frame and, when present, the scene last frame.
Is Hailuo 3 available for AI Influencer lip-sync?
No. Hailuo 3 is for standard AI Video scenes. Influencer talking-head segments use models that accept scene speech audio.