xAI: Grok Imagine Video 1.5 Preview

Grok Imagine Video 1.5 Preview animates an input image into a short clip. It is suited to testing motion around an established visual composition, with a preview model that should be evaluated on representative shots before wider use.

Compare models

grok-imagine-video-1.5-preview

AvailablexAIVideoAsync

Price: From $0.04
Modalities: Video

About Grok Imagine Video 1.5 Preview

Grok Imagine Video 1.5 Preview is the pre-release build of xAI's 1.5 video model, animating a supplied image into a short clip. It offers the same one to fifteen second durations, 480p and 720p output and seven aspect ratios as the final 1.5 ID. Use it to test motion around a fixed composition.

Where it works well

Animates a still image you supply, keeping its composition as the opening frame.
Lets you try 1.5-line motion behaviour on your own images before standardizing on a model.
Clip length is adjustable from one to fifteen seconds.
Seven aspect ratios include 9:16 for vertical delivery.
480p output keeps test renders quick while you tune the prompt.

When to choose another model

As a preview, its behaviour may differ from the final grok-imagine-video-1.5 release, so avoid building on it for stable output.
Image-to-video only; it cannot start from text or edit existing footage.
Resolution stops at 720p, which can be too low for large-screen or print delivery.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Image to videoTokenLab endpoint

POST/v1/videos/generations

curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "aspect_ratio": "16:9",
  "duration": 5,
  "operation": "image-to-video",
  "resolution": "720p",
  "model": "grok-imagine-video-1.5-preview",
  "prompt": "Cinematic sunrise over a calm lake with gentle camera motion.",
  "image_url": "https://example.com/image.jpg"
}'

Pricing

Official price is the model maker's public baseline. TokenLab price is what you pay for this model on TokenLab.

Pricing

per second

TokenLab price: How pricing works
Official price: How pricing works

	Official priceper second	TokenLab priceper second	Discount
Price	How pricing works	How pricing works	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 3, 2026, 07:28 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Grok Imagine Video 1.5 Preview in Console with a prompt ready to edit or send.

Help me create with grok-imagine-video-1.5-preview using image-to-video at /v1/videos/generations. Show the result, status, and cost.

Use cases

Evaluating the 1.5 line
Run a set of your typical images through the preview to see how motion looks before choosing between 1.5 and the original model.
Motion tests on a fixed shot
Take one approved frame and try several camera or subject moves to find the one that suits it.
Draft animations for review
Produce quick low-resolution animatics for stakeholders, then regenerate approved shots on the final model.

Prompt examples

The camera drifts slowly to the right across the market stall while steam rises from the pots.

Her scarf blows in the wind as the camera holds still, five seconds, cinematic.

Animate this logo reveal: light sweeps across the metal letters from left to right.

FAQ

What is the 1.5 Preview model?

It is a preview release of xAI's Grok Imagine Video 1.5 that turns an input image into a short clip. It is meant for trying the model before the standard release, so test it on your own shots.

Should I use the preview or grok-imagine-video-1.5?

Use grok-imagine-video-1.5 for steady production output. Use the preview when you want to compare behaviour or are already tuned to it, and expect results to change as xAI updates it.

What inputs does it accept?

A starting image and a text prompt. It does not start from text alone, and it does not edit or extend existing video. It always starts from a picture, so have the key frame ready before you begin.

What video lengths and sizes can I choose?

Durations run from one to fifteen seconds at 480p or 720p, in square, 3:2, 2:3, 4:3, 3:4, 16:9 or 9:16 ratios. Shorter clips are usually easier to keep consistent from start to finish.

How should I test it?

Run a handful of your real images at short durations, review motion, edges and faces, and only then scale up. Image types differ, so a sample from your own work tells you more than a demo.

How much does Grok Imagine Video 1.5 Preview cost?

On TokenLab, Grok Imagine Video 1.5 Preview costs How pricing works . The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Grok Imagine Video 1.5 Preview use?

Use https://api.tokenlab.sh/v1/videos/generations for Grok Imagine Video 1.5 Preview. The request example below shows the matching code shape.

Which operations does Grok Imagine Video 1.5 Preview support?

Grok Imagine Video 1.5 Preview supports Image to video. Select an operation above to see its endpoint and request example.