All the models in one place
Run Hailuo H3 Max (MiniMax) and every other model on Glif from one chat. One account, one balance, no API keys to wire up.
Hailuo H3 Max (MiniMax)
Glif default
Detailed clips with synchronized sound, guided by text, frames or mixed media references.
Pricing details
- Cost per second: 6.75 credits (480p), 10.8 credits (768p). Reference inputs are billed in tokens (first 4,096 free, then 2.7 credits per 1K): about 1K per image, ~7.5K per second of reference video at 768p.
Rated by blind team votes and an AI judge
As of
Score 67 · #3 of 22 in Image-to-video
90% range 52–80
Score out of 100: how often people would pick this model's output over an average model's on the same tests. 50 is average.
How we score
On image-to-video: Wins 22 / Losses 9 / Ties 1 from 32 team votes, plus 7 AI judge scores.
Every model runs the same Glif tests. Team members see two outputs side by side without the model names and pick the one that better fits the test, or call it a tie. An AI judge also scores every output from 0 to 10.
A Bradley-Terry fit turns all those head-to-head results into one rating per model. Ties count as half a win, and each AI judge score counts as half a vote.
The score is the predicted chance people prefer this model's output to the average model's on the same board, so 50 is average. A board is one kind of task, like text-to-image. Scores only compare models on the same board.
The 90% range comes from resampling the votes and refitting many times. Overlapping ranges are close to a tie. A model ranks once it has 20 votes' worth of ratings on a board. Until then it shows no score, only how close it is.
Other boards
Text-to-video: Needs more ratings (15 of 20)
Multi-image reference: Needs more ratings (3 of 20)
First-to-last frame: Needs more ratings (3 of 20)
Test outputs
Compare all modelsHailuo H3 Max (MiniMax) in practice
What it does and when to use it.
Model summary
Hailuo H3 Max is fal’s adapted version of MiniMax H3. It generates video with synchronized audio from text or a starting image. An optional closing frame guides the ending, so a short scene can include motion and sound without a separate audio step.
Capabilities
Text to video
Image to video
First to last frame
Video with audio
Suggested use cases
- Create short videos from a written scene description
- Animate still images with motion and synchronized sound
- Guide a shot between an opening and closing frame
Hailuo H3 Max (MiniMax) variants
Edit, extend and reference tools built on the same model.
More from the Hailuo family
Explore other options from the same family.