Video · MiniMax
MiniMax H3 (Hailuo)
MiniMax's 2026 Hailuo models with stereo sound. H3 Max runs in private mode at a low price. Pick it for private, affordable clips.
Private, some versions anonymized Low costWhat sets it apart
MiniMax H3 is an omni-modal model: text, images, video and audio go in, and video with stereo sound comes out, up to 2K and 15 s with native multi-shot. Its weights are open, and its Max tier leads the Artificial Analysis image-to-video arena at the time of reading.
- Open weights, 33B parameters
- Stereo sound, up to 2K, 15 s
- Max tier adds camera keyframes
Recommended for: keep a video project private.
Strengths and limits
Where it shines
- H3 Max and Turbo run in private mode (no data kept)
- Turbo is among the cheapest clips with sound
- Multi-Angle makes product spins and bullet-time from one photo
Think twice when
- H3 Max stops at 1080p; 2K needs the anonymized H3
- Generated clips start at 5 s; Recast follows the length of your source video
- 5 to 15 s, native sound (Recast keeps the source audio)
- H3 Max: 480p to 1080p; H3: 768p or 2K
- Max versions private, plain H3 anonymized
Use cases
Orbit around a product photo
Using the Multi-Angle mode on my sneaker photo: keep the sneaker frozen and orbit the camera 90 degrees to the left, then rise slightly. 6 seconds.
The Max camera mode moves the viewpoint while the scene stays still.
Character from reference images
Use my 3 reference images of the explorer and my 5 second voice clip. She reads a map in a jungle and says 'We are close.'
It takes up to 9 images, 3 videos and 3 audio clips.
Cheap 768p preview
A paper boat drifting down a rainy gutter, close-up, 8 seconds, gentle rain sound.
768p costs well under 2K, good for testing.
Against its rivals
- Wan 3.0Wan 3.0 runs to 30 s but has closed weights.#3 of 22 on Artificial Analysis Image to Video Arena (1,164 Elo)
- Seedance 2.5Seedance 2.5 reaches 30 s with a larger reference budget.#2 of 18 on Artificial Analysis Text to Video Arena with audio (1,142 Elo)
- FLUX 3 videoFLUX 3 offers 20 s clips with keyframes and a draft mode.#5 of 18 on Artificial Analysis Text to Video Arena with audio (1,127 Elo)
Version history
Each version, dated, with what it changed over the one before.
- Hailuo 02Earlier, not in Sub Rosa
- Native 1080p, triple the parameters and four times the training data of its predecessor.
- 768p at 6 or 10 s, 1080p at 6 s, no audio.
- Hailuo 2.3Earlier, not in Sub Rosa
- Better body motion, stylization (anime, ink wash) and facial micro-expressions.
- Adds a cheaper Fast model at the same price tier.
- MiniMax H3
- General-purpose omni-modal model: text, image, video and audio in, one shared framework.
- Video with native stereo audio up to 2K and 15 s, with native multi-shot.
- Open weights on Hugging Face under the MiniMax H3 Community License.
- MiniMax H3 Max RecastLatest
- Video to video: replaces people in an existing clip with identities from reference photos, keeping the source motion, camera work, cuts and audio
- Renders at 768P or 1080P
Benchmarks
How to read these scores: what a benchmark tells you.
Artificial Analysis Image to Video Arena: #1 of 22 models measured in the catalog. The same blind duel, starting from one image: which clip brings it to life better. An Elo rating: higher is preferred more often. 100 points apart means the higher-rated model wins about 64% of duels.
- 1. MiniMax H3 MaxMiniMax H3 (Hailuo)1,195
- 2. MiniMax H3MiniMax H3 (Hailuo)1,181
- 3. Wan 3.0Wan 3.01,164
- 4. HappyHorse 1.1HappyHorse1,104
- 5. Grok Imagine 1.5Grok Imagine video1,098
- 6. HappyHorse 1.0HappyHorse1,083
- 7. Veo 3.1 Full QualityVeo 3 and 3.11,082
- 8. Wan 2.7Wan 2.x1,077
- 9. Grok ImagineGrok Imagine video1,072
- 10. Veo 3.1 FastVeo 3 and 3.11,066
See the numbers
| Model | Elo |
|---|---|
| 1. MiniMax H3 Max | 1,195 |
| 2. MiniMax H3 | 1,181 |
| 3. Wan 3.0 | 1,164 |
| 4. HappyHorse 1.1 | 1,104 |
| 5. Grok Imagine 1.5 | 1,098 |
| 6. HappyHorse 1.0 | 1,083 |
| 7. Veo 3.1 Full Quality | 1,082 |
| 8. Wan 2.7 | 1,077 |
| 9. Grok Imagine | 1,072 |
| 10. Veo 3.1 Fast | 1,066 |
Artificial Analysis Text to Video Arena with audio: #3 of 18 models measured in the catalog. The duel for clips with sound: picture, voices, effects and how well they match. An Elo rating: higher is preferred more often. Only models that make their own sound take part.
- 1. Wan 3.0Wan 3.01,156
- 2. Seedance 2.5Seedance 2.51,142
- 3. MiniMax H3MiniMax H3 (Hailuo)1,138
- 4. MiniMax H3 MaxMiniMax H3 (Hailuo)1,134
- 5. Flux 3FLUX 3 video1,127
- 6. Seedance 2.0Seedance 2.0 and 1.51,119
- 7. Gemini Omni Flash 1.1Gemini Omni Flash1,113
- 8. Grok Imagine 1.5Grok Imagine video1,044
- 9. HappyHorse 1.1HappyHorse1,043
- 10. Wan 2.7Wan 2.x1,029
See the numbers
| Model | Elo |
|---|---|
| 1. Wan 3.0 | 1,156 |
| 2. Seedance 2.5 | 1,142 |
| 3. MiniMax H3 | 1,138 |
| 4. MiniMax H3 Max | 1,134 |
| 5. Flux 3 | 1,127 |
| 6. Seedance 2.0 | 1,119 |
| 7. Gemini Omni Flash 1.1 | 1,113 |
| 8. Grok Imagine 1.5 | 1,044 |
| 9. HappyHorse 1.1 | 1,043 |
| 10. Wan 2.7 | 1,029 |
Artificial Analysis Text to Video Arena: #2 of 5 models measured in the catalog. People watch two silent clips made from the same description, without knowing the models, and pick the better one. An Elo rating: higher is preferred more often. 100 points apart means the higher-rated model wins about 64% of duels.
- 1. Wan 3.0Wan 3.01,129
- 2. MiniMax H3MiniMax H3 (Hailuo)1,118
- 3. MiniMax H3 MaxMiniMax H3 (Hailuo)1,115
- 4. Seedance 2.5Seedance 2.51,102
- 5. Flux 3FLUX 3 video1,094
See the numbers
| Model | Elo |
|---|---|
| 1. Wan 3.0 | 1,129 |
| 2. MiniMax H3 | 1,118 |
| 3. MiniMax H3 Max | 1,115 |
| 4. Seedance 2.5 | 1,102 |
| 5. Flux 3 | 1,094 |
All 12 models in this family
| Model | Use | Privacy | Price |
|---|---|---|---|
MiniMax H3minimax-h3-text-to-video | Text to video | Anonymized | $0.0728 per second of video$0.364 a 5 s clip |
MiniMax H3minimax-h3-image-to-video | Image to video | Anonymized | $0.0728 per second of video$0.364 a 5 s clip |
MiniMax H3 R2Vminimax-h3-reference-to-video | References to video | Anonymized | $0.0729 per second of video$0.365 a 5 s clip |
MiniMax H3 Enhancedminimax-h3-enhanced-text-to-video | Text to video | Anonymized | $0.0728 per second of video$0.364 a 5 s clip |
MiniMax H3 R2V Enhancedminimax-h3-enhanced-reference-to-video | References to video | Anonymized | $0.0729 per second of video$0.365 a 5 s clip |
MiniMax H3 Maxminimax-h3-max-text-to-video | Text to video | Private | $0.0279 per second of video$0.14 a 5 s clip |
MiniMax H3 Maxminimax-h3-max-image-to-video | Image to video | Private | $0.0279 per second of video$0.14 a 5 s clip |
MiniMax H3 Max R2Vminimax-h3-max-reference-to-video | References to video | Private | $0.0432 per second of video$0.216 a 5 s clip |
MiniMax H3 Max Multi-Angleminimax-h3-max-multi-angle | Image to video | Private | $0.018 per second of video$0.09 a 5 s clip |
MiniMax H3 Max Turbominimax-h3-max-turbo-text-to-video | Text to video | Private | $0.0144 per second of video$0.072 a 5 s clip |
MiniMax H3 Max Turbominimax-h3-max-turbo-image-to-video | Image to video | Private | $0.0144 per second of video$0.072 a 5 s clip |
MiniMax H3 Max Recastminimax-h3-max-recast | Text to video | Private | Shown in the app |
Specifications
| Specification | MiniMax H3 |
|---|---|
| Released | July 31, 2026 |
| Parameters | 33B |
| Weights | Open, MiniMax H3 Community License |
| Accepts | text, images, video, audio |
| Produces | video, audio |
| Clip length | 5 to 15 s, with sound |
| Resolutions | 768P, 2K |
| Price | $0.0728 per second of video |
| Privacy | Anonymized |
Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.
Sources
Everything on this page comes from these pages, read on October 16, 2026 or as dated on each score.
Show the 8 sources
- minimax.io/blog/minimax-h3
- huggingface.co/MiniMaxAI/MiniMax-H3
- fal.ai/learn/tools/what-is-h3-max-camera-controls
- minimax.io/news/minimax-hailuo-02
- minimax.io/news/minimax-hailuo-23
- artificialanalysis.ai/video/leaderboard/image-to-video
- openrouter.ai/minimax/hailuo-3-max
- eachlabs.ai/fal/minimax-h3-max/minimax-h3-max-recast