All Models

xAI logo

Grok Imagine Video 1.5

Grok Imagine Video 1.5 generates, animates, and references short video from text or images.

Price is per video output second, rounded up.
Offering
Price
480p
$0.08
720p
$0.14
1080p
$0.25

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

Grok Imagine Video 1.5

Grok Imagine Video 1.5 is xAI’s short video model. You can generate from a prompt, animate a still, or condition on reference images. Clips run from 1 to 15 seconds, default 6. Generate resolutions are 480p, 720p, and 1080p. Reference tops out at 720p. Aspect ratios are 16:9, 1:1, 9:16, 3:2, and 2:3.

There is no native-audio flag. Animate does not take a last frame. Reference is stills only — no reference video and no reference audio.

The 1-second minimum is unusual. It is there so you can test a subject quickly before committing to a longer clip.

What it's good for

Short, stylized motion in the Grok look, including still-conditioned clips. Restrained documentary realism is not what this model is for. Sound is a separate step.

Model ID

xai/grok-imagine-video-1.5

Output Type

Video

Pricing

From $0.08/s

Provider

xAI

Hosting

Protoface

Grok Imagine Video 1.5

Grok Imagine Video 1.5 is xAI’s short video model. You can generate from a prompt, animate a still, or condition on reference images. Clips run from 1 to 15 seconds, default 6. Generate resolutions are 480p, 720p, and 1080p. Reference tops out at 720p. Aspect ratios are 16:9, 1:1, 9:16, 3:2, and 2:3.

There is no native-audio flag. Animate does not take a last frame. Reference is stills only — no reference video and no reference audio.

The 1-second minimum is unusual. It is there so you can test a subject quickly before committing to a longer clip.

What it's good for

Short, stylized motion in the Grok look, including still-conditioned clips. Restrained documentary realism is not what this model is for. Sound is a separate step.