MiniMax H3 Turbo runs the MiniMax H3 recipe with its fast adapter fused in: the same synchronized video and stereo audio, in a fraction of the time with balanced quality. MachGen supports Text to Video, Image to Video, First & Last Frame and Reference to Video at 480p or 768p, all at 24 fps.
| 480p | $0.01/s |
| 768p | $0.01/s |
| 480p · with input video | $0.01/s |
| 768p · with input video | $0.01/s |
MiniMax H3 Turbo runs the MiniMax H3 recipe with its fast adapter fused in: the same synchronized video and stereo audio, in a fraction of the time with balanced quality. MachGen supports Text to Video, Image to Video, First & Last Frame and Reference to Video at 480p or 768p, all at 24 fps.
MiniMax H3 Turbo examples for fast iterations across text, image, first-and-last-frame, and multimodal reference video with native stereo audio.
This table reflects the model routes and controls currently exposed by MachGen.
| Mode | Required input | Available settings |
|---|---|---|
| Text to Video | Text prompt | Resolution: 480p, 768p, 1080p Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 Duration: 5-15s Frame rate: 24fps Optional generated audio Seed control Prompt enhancement Prompt limit: 65,535 characters |
| Image to Video | Text prompt and source image; optional end frame | Resolution: 480p, 768p, 1080p Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 Duration: 5-15s Frame rate: 24fps Optional generated audio Seed control Prompt enhancement Prompt limit: 65,535 characters |
| Reference to Video | Per-type limits: up to 9 images, up to 3 videos, up to 3 audio files; 15 references combined, plus a text prompt | Resolution: 480p, 768p, 1080p Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 Duration: 5-15s Frame rate: 24fps Optional generated audio Seed control Prompt enhancement Prompt limit: 65,535 characters |
| First & Last Frame | Text prompt, start frame, and end frame | Resolution: 480p, 768p, 1080p Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 Duration: 5-15s Frame rate: 24fps Optional generated audio Seed control Prompt enhancement Prompt limit: 65,535 characters |
For model background, technical details, and architecture, see the H3 acceleration LoRAs Community Hub.
Try this model in the MachGen Playground.
Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.
See Pricing for currently published MachGen rates. When available, the Playground estimate reflects the selected task and output settings.
Deployment: MachGen Hosted. MiniMax H3 Turbo runs on MachGen-managed inference infrastructure rather than being forwarded to a provider API.
The Playground and API sections on this page list the inputs and output settings exposed for this model.