Log inSign Up
Open Hedra

Grok Video

All models
Video modelxAI

Grok Video T2V

Text → Video — generates video.

Specifications

Input mode
Text → Video
Aspect ratios
16:9, 9:16, 1:1
Resolutions
480p, 720p
Durations
5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
Max duration
15s
Native audio
No
Pricing
7 credits / second — longer clips and higher resolutions cost more
Typical generation time
~44s
Free tier
Yes

Examples

A video still showing a majestic deity with metallic golden skin, glowing white eyes, and flowing light-colored hair. The figure stands inside a translucent crystal structure against a deep blue cosmic background featuring galaxies and stars. This 1280x720 text-to-video generation was created using Grok Video.Golden Cosmic Deity — Grok VideoA close-up shot of a male desert wanderer wearing brass goggles on his forehead and a scarf blowing in the wind. The background features a vast desert landscape under a purple twilight sky with glowing crystal structures, generated by Grok Video at 1280x720 resolution.Desert Wanderer with Goggles — Grok VideoA wide shot of a Sufi whirling dervish spinning in a traditional white skirt and tall hat inside an ancient stone courtyard with arched pillars. Warm sunlight beams through the background. This 1280x720 video was generated using the Grok Video model.Whirling Dervish in Stone Courtyard — Grok VideoAn extreme close-up of a smooth, white wax sculpture of a human face with stylized droplets under the eyes. Generated by Grok Video at 1280x720 resolution, the frame features soft studio lighting against a dark, neutral background.Melting Wax Face Sculpture — Grok VideoA low-angle shot of a man in a white tank top, black headband, and large diamond chain gesturing at the camera. He stands in front of a black SUV on a wet city street at night. Generated by Grok Video at 848x480 resolution.Grok Video: Rapper in Front of Black SUV

Similar models

Kling 2.1 Master T2VText → VideoKling 2.5 Turbo T2VText → VideoKling 2.6 Pro T2VText → VideoMiniMax Hailuo 2.3 Pro T2VText → VideoMiniMax Hailuo 2.3 Standard T2VText → Video