Skip to content
  1. Developers
  2. Models
  3. Video generation
By xAI, served by VidmoatAvailable

Grok Imagine Video

xAI's video model. Start from a prompt, a first frame or up to seven reference images; it can also extend a clip it made. The default when you do not name a provider.

id provider "grok"

Sample

A lighthouse on a rocky coast at golden hour, generated by Grok Imagine Video

Prompt Cinematic aerial shot slowly circling a lighthouse on a rocky coast at golden hour, waves crashing against the rocks

A real, unedited output of this model, made for this page.

The same prompt on other models

What it does well

  • Optional generated audio.
  • Make it longer: adds 2 to 10 seconds to a clip of 2 to 15 seconds.
  • Saved Cast members by castIds; references with a first frame run on Grok Imagine 1.5 at 64 credits a second.
  • Nine aspect ratios, from 21:9 to 9:21.
  • Shot presets: 12 camera moves, 6 framings, 5 lens looks, 3 paces, optional.

Limits

  • 1 to 15 seconds, 480p or 720p (no 1080p).
  • One video job at a time per account.

Where to call it

REST APIPOST /v1/ai/videosMCPgenerate_video
Editor agentgenerateMedia kind "video"
Chat botsTelegram, WhatsApp and Discord
Vidmoat appGenerate page and editor

Try it

curl
curl -X POST https://api.vidmoat.com/v1/ai/videos \
  -H "Authorization: Bearer $VIDMOAT_KEY" \
  -H "Content-Type: application/json" \
  -d '{"provider":"grok","prompt":"a paper boat drifting down a rainy street, close up","durationSec":5,"aspectRatio":"9:16"}'

A test key answers with a sample and spends nothing. Every parameter and error is in the API reference.

Read more