Skip to main content
MiniMax-H3 is a reasoning-grade multimodal video model with synchronized audio and 2K output. Clips are billed per second of output.

Endpoint

Async — returns {id, status: "pending"}; poll GET /v1/videos/generations/{id} until success or failed.

Parameters

string
required
Text prompt describing the desired video. Max 7000 characters.
"6" | "10"
default:"\"6\""
Length of the generated clip in seconds. Drives the price (billed per second of output).
"2K"
default:"\"2K\""
Output resolution.
"16:9" | "4:3" | "1:1" | "3:4" | "9:16" | "21:9"
default:"\"16:9\""
Aspect ratio. Text-to-video requires an explicit ratio — adaptive is not accepted for this task.

Example

Poll until terminal: