xAI

This page is auto-generated from model configurations. Last updated: 2026-03-13.

This reference lists all available xAI video generation models and their parameters. Use these parameter names when calling the Generation API.


Grok Imagine Video

Generate and edit videos using xAI's Grok model — supports text-to-video, image-to-video (up to 15s), and video editing (up to 8.7s) with 480p/720p resolution and flexible aspect ratios

Model ID: model_xai-grok-imagine-video

Capabilities: txt2video, img2video, video2video

LLM Markdown: https://app.scenario.com/api/models/model_xai-grok-imagine-video/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
promptstringYes----Text description of the video to generate, or desired edits when a source video is provided
imagefileNo----Source image for image-to-video generation. The model will animate the provided image based on the text prompt. Mutually exclusive with video input.
videofileNo----Source video to edit. Auto-preprocessed to max 8.7s at 720p. Duration, aspect ratio, and resolution are inherited from the source. Mutually exclusive with image input.
numOutputsnumberNo114-Number of videos to generate concurrently
durationnumberNo5115-Video duration in seconds. Ignored in video editing mode (output duration matches source, max 8.7s).
aspectRatiostringNo16:9--16:9, 3:2, 4:3, 1:1, 3:4, 2:3, 9:16Aspect ratio for the generated video. Ignored in video editing mode.
resolutionstringNo480p--480p, 720pOutput resolution for the generated video. Ignored in video editing mode.