MiniMax H3 (Text to Video)
/v1/runGenerate native-stereo 2K video from text with MiniMax H3.
Request body
Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.
Model identifier. Set to minimax/h3/text-to-video.
Default: minimax/h3/text-to-video
Text prompt that describes the image or asset to generate.
Default: A cinematic wide shot of an astronaut walking across a red desert at sunset, wind lifting fine dust, with natural footsteps and distant ambient sound.
Request parameter supported by this model.
Allowed values: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
Default: 5
Aspect ratio of the generated image.
Allowed values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Default: 16:9
Output resolution. 768P is generated natively; 2K is upscaled via an in-context regeneration pass.
Allowed values: 768P, 2K
Default: 2K
Response Schema
The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.
Structured error returned when the task fails.
Unique identifier for the submitted request or completed response.
Model identifier used for this request.
Generated output items returned when the task completes.
Current generation status. Non-terminal responses should be polled until completed, failed, or timeout.
Allowed values: pending, running, completed, failed, timeout
Model capabilities
Capabilities declared by the model registry.
Default: text-to-video
Execution mode declared by the model registry.
Default: async

