Text-to-video · audio evaluated · all categories · resolution=768P
95% CI 1,143.65–1,173.65 · n=5,962
minimaxReleased Jul 30, 2026
MiniMax H3 Text to Video
Generates natively at 480P or 768P; 2K and 4K upscale the 768P result. Can replace the soundtrack with supplied audio.
Source description
MiniMax H3 is a frontier video model. This endpoint generates video from a text prompt alone, rendering at 2K in durations from 5 to 15 seconds across seven aspect ratios.
Measured performance
All leaderboards ↗Benchmark results
Text-to-video · silent evaluation · all categories · resolution=768P
95% CI 1,103.09–1,139.09 · n=3,799
Access & cost
0 quotesPrices across providers
No listed provider price
Model specifications
- Developer
- minimax
- Modality
- Video
- Context
- Not reported
- Maximum output
- Not reported
- Weights
- Open weights
- Released
- Jul 30, 2026
- Provider listed
- Jul 31, 2026
- First discovered
- Oct 16, 2026
Provider-reported tasks
- Text → videofal ↗Checked
Exact identities
- fal
minimax/h3/text-to-video - aa-video
da987d84-718f-4ac2-a278-518595967b42
Sources
Updated Oct 17, 2026
More from minimax
View all ↗minimaxListed 10 days ago
H3 Max Relight
Relight any video with H3 Max from a lighting sphere image, while preserving the source subjects, motion, camera and audio.
No reported score
No reported score
minimaxListed 15 days ago
H3 Max Turbo Extend Video
Extend an existing video with H3 Max Turbo: add 1 to 15 seconds of prompt-guided footage, with optional audio references and output resolutions from 480p to 2K.
No reported score
No reported score
minimaxListed 15 days ago
H3 Max Recast
Replaces people across shots from reference photos in 5–30 second videos, retaining the source soundtrack.
No reported score
No reported score
minimaxListed 18 days ago
H3 Max
Insert a new scene into an existing video with H3 Max. Guide the scene with a prompt, reference images, or reference videos, then return to the original footage.
No reported score
No reported score
Price not listed