MiniMax H3 (Hailuo 3) — AI Video Generator
MiniMax's new-generation video model, also known as Hailuo 3 or Hailuo H3. 4–15 second clips in native 2K — with stereo sound on every generation.
New accounts get 10 free credits — enough to try your first generations.
Generated with MiniMax H3 on EvoLink
Real MiniMax H3 samples with full prompts
Every clip below was generated with MiniMax H3 (Hailuo 3) — each ships with the exact prompt and settings behind it. Copy them, adapt them, make them yours.
Sci-Fi Mystery Trailer
Short sci-fi mystery film teaser Realistic cinematic look, high-contrast lighting, and a tight pace. Use Figure 1 as the overall atmosphere and style reference, and Figure 2 as the protagonist reference. Shot 1 — Ultra-wide establishing shot. A huge circular cosmic gateway nearly fills the frame. The person is only a tiny figure seen from behind before the gateway, positioned toward the lower right. The ground is wet and reflective, and the center of the gateway is pitch black. The camera slowly pushes forward. A large title fades in from the edge of the darkness, blurred at first and then sharp: "THE STARS WERE LISTENING". Use an extremely condensed, heavy, all-caps typeface in dark red mixed with rust red, with subtle grain and misted edges. Audio: a deep low-frequency pulse, faint metallic vibrations in the distance, and a soft hit as the text becomes sharp. → Hard cut. (Incomplete prompt; you may add details yourself)
15s · 16:9 · native 2K · 2 reference images · translated starter prompt
Official MiniMax sample, published with permission
Glowing Kitchen Creature
15-second, 16:9 landscape video. Blend live-action footage of a small kitchen at dusk with hand-drawn glowing animation. The last light of sunset lingers by the window. The lived-in kitchen contains an old wooden table, a half-washed mug, a slightly fogged glass bottle, and a hanging dishcloth. Give the footage subtle one-handed smartphone shake, hesitant close-range focusing, exposure fluctuations caused by backlight, and slightly coarse noise in the shadows. It should not look carefully arranged like an advertisement; instead, it should feel like someone hurriedly captured an unbelievable event at home. Do not show huge eyes, gaping mouths, fangs, threatening or lunging movements, sudden black frames, or jump scares. Use only kitchen room tone, cloth rubbing, the soft clink of a mug, water dripping from the faucet, the camera operator's footsteps and quiet breathing, plus gentle electronic sounds and tiny calls from the hand-drawn creature.
15s · 16:9 · native 2K · text-to-video · translated starter prompt
Official MiniMax sample, published with permission
Multi-Element Scene Edit
Replace the newspaper in the reference video with a green-covered book; change the chair the character is sitting on to a red sofa; remove the sunglasses worn by the character to retain a clear face; remove the car burning effect to keep the vehicle in a normal state; change the photo the character takes out of his arms to a small black book; and add a tree on the left side of the screen
10s · 16:9 · native 2K · video edit · translated prompt
Official MiniMax sample, published with permission
Vampire Romance Short Drama
Generate a 15-second, 9:16 vertical trailer segment for an international live-action vampire romance short drama. Use Figure 1 as the appearance reference for the male and female leads, and Figure 2 as the scene reference. Keep both leads' identities consistent, with a realistic live-action look and premium short-drama production quality. Story: an innocent human heroine accidentally enters a forbidden area of an old castle and awakens a sleeping aristocratic vampire. He discovers that she carries an aura connected to an ancient war, which sparks a powerful urge to control her and a dangerous fascination with her. She fears him but does not completely submit, resisting his pressure. Overall style: an international ReelShort / DramaBox vampire-romance trailer. Dark romance, dangerous attraction, fate, intense control, brooding oppression, and a striking reversal. Keep the visuals premium, restrained, and tightly paced, like the opening 15-second hook of a hit short drama. No gore, cheap horror, Halloween aesthetic, or modern street feel. Format: 9:16 vertical composition for TikTok / ReelShort / DramaBox. Use primarily medium close-ups, close-ups, and extreme close-ups, emphasizing faces, eye contact, pressure, and relationship tension within the vertical frame.
15s · 9:16 · native 2K · 2 reference images · translated starter prompt
Official MiniMax sample, published with permission
Futuristic Eyewear Campaign
Generate a vertical screen 9:16 high-end fashion glasses commercial, taking overall reference to the storyboard rhythm, editing speed, white studio texture and cool fashion atmosphere of the given video. The picture is a minimalist white booth, a seamless white background, a strong sense of high-end advertising, and a clean, simple, handsome, avant-garde, international first-line fashion blockbuster texture. Key visual character reference picture 1, two full-body female models, one black female model and one European and American model, maintain their high-end clothing, body posture, white studio light and shadow, fashion show temperament and overall cool attitude. Both of them wear futuristic high-end glasses. The design of the glasses refers to Figure 3, emphasizing the covered curved surface, sharp geometric cat-eye/goggle hybrid outline, mirror reflection, streamlined temples, and the texture of high-end fashion accessories. Please refer to Figure 2 for the appearance details of the two characters.
15s · 9:16 · native 2K · 3 reference images · translated starter prompt
Official MiniMax sample, published with permission
Clay Fox Canyon Leap
Claymation style. A sprinting fox reaches the edge of a cliff and launches without hesitation, making a dramatically tense, heroic slow-motion leap across a vast lava canyon. While the fox is airborne, the camera rushes at high speed beneath its belly in a sweeping dynamic move, fully revealing the terrifying depth of the chasm and the fox's clay body at maximum extension in midair.
10s · 16:9 · native 2K · 1 reference image · translated starter prompt
Official MiniMax sample, published with permission
What is MiniMax H3?
MiniMax H3 (also called Hailuo 3) is the newest video generation model from MiniMax, the team behind Hailuo AI. Instead of treating text-to-video, image-to-video and video editing as separate tools, H3 reads text, images, video and audio together as one brief, and returns a finished clip — picture and soundtrack in a single generation. Every output ships with native stereo audio, and the launch resolution is native 2K, re-generated rather than upscaled. It follows Hailuo 2.3, which stays available as the faster, lower-cost option.
One model, four names: MiniMax H3, Hailuo 3, Hailuo H3, Hailuo 03
MiniMax H3 is the official name — MiniMax's own site lists it alongside M3 (text) and Speech 2.8, where H marks the video line. You'll also see Hailuo 3 or Hailuo 3.0 (carried over from Hailuo AI, MiniMax's consumer app), Hailuo H3 (a mix of both), and Hailuo 03 (used in some MiniMax documents). All four refer to the same model — the one on this page.
What's new in MiniMax H3 vs Hailuo 2.3
- Sound on every clip. H3 generates native stereo audio with the video — dialogue, ambience and music come out of the same generation, no separate audio pass.
- Up to 12 reference files in one brief. Mix up to 9 images, 3 videos and 3 audio clips; H3 reads characters, motion, voice, style and pacing across all of them together.
- Editing-grade control. Change an existing video by describing the change: swap a character, replace the background, rewrite a line of dialogue, relight the scene.
Try MiniMax H3 in three steps
Create a free EvoLink account
10 free credits included.
Open the playground
Pick MiniMax H3 (Hailuo 3). Write a prompt, or drop in reference images, video or audio.
Generate
4–15 seconds, six aspect ratios from 21:9 to 9:16. Your clip downloads with sound baked in.
MiniMax H3 capabilities and limits
Good at
- Cinematic brand-film looks
- Readable on-screen text, subtitles and logo motion
- Product showcase
- Vertical short-drama
- Anime and game-PV styles
- Motion, voice and character reference
- Instruction-dense edits (multiple changes in one prompt)
Know before you generate
- Clips run 4–15 seconds — no longer takes yet.
- Launch resolution is native 2K only; 768P is coming within days of launch (per MiniMax).
- Every clip has audio — there is no silent mode.
- Audio references can stand alone — no image or video input required.
- Per-file upload caps: video 50 MB · image 30 MB · audio 15 MB; prompts up to 7,000 characters.
MiniMax H3 pricing — no subscription
MiniMax H3 on EvoLink is pay-as-you-go: top up once, spend credits only when you generate. No subscription, no monthly fee. New accounts get 10 free credits to start.
$0.65
5-second clip, native 2K
$1.30
10-second clip, native 2K
$1.95
15-second clip, native 2K
Prices are MiniMax's official launch rates for native 2K — a lower-cost 768P tier is coming within days of launch.
Building for production? MiniMax H3 API on EvoLink — day-one access, real pricing and docs.
MiniMax H3 API →Frequently asked questions
Everything you need to know about the product and billing.
Explore the Hailuo family
Last updated: