xAI · model guide
Grok Imagine Video 1.5 Guide
xAI video model accepting text, image and audio inputs. This page connects the model data to working GenVideoKit prompt, image-to-video, comparison and cost tools.
Prompting strategy
Write a concise audiovisual shot description with a strong start state, clear action and camera motion. Keep identity and scene geometry stable, and describe audio only when it contributes to the intended result.
Capabilities
Text → videoImage → videoNative audio
Reference pricing snapshot
$0.14 / second
720p · checked 2026-09-19
Official/provider pricing source