xAI: Grok Imagine Video 1.5

Video model for image-to-video generation, editing, and extension workflows

grok-imagine-video-1.5

AvailablexAIVideoAsyncNew

Price: From $0.08
Released: Jun 16, 2026
Modalities: Video

About Grok Imagine Video 1.5

Grok Imagine Video 1.5 is xAI's newer Imagine video model for image-to-video. It turns a supplied still image into a clip of up to fifteen seconds, at 480p or 720p and several aspect ratios. The still sets the look of the opening frame. Use it when you already have the key frame and need it to move.

Where it works well

Animates an existing image, keeping the composition you already approved as the starting frame.
Durations from one to fifteen seconds let you match short loops or longer shots.
Seven aspect ratios cover square, landscape and portrait publishing.
Newer generation than the original Imagine video model, per xAI's documentation.
480p and 720p options allow cheap tests before a higher-resolution render.

When to choose another model

It works from a starting image only; for text-only starts or footage edits use grok-imagine-video.
Maximum resolution is 720p, which may be too low for large-screen delivery.
Fast or complex motion can distort details, so test on representative images first.

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",
  "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

Official: How pricing works
Official price: How pricing works

	Official priceper second	Officialper 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 in Console with a prompt ready to edit or send.

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

Use cases

Animating key art
Take a poster, illustration or product render and add camera movement or subject motion for a short social clip.
Storyboard to motion
Turn approved storyboard frames into moving previews to judge pacing before committing to full production.
Portrait-format ads
Generate vertical 9:16 clips from still creative to fit stories and short-form feeds.

Prompt examples

Slow push-in on the lantern as embers drift upward and the paper flickers, eight seconds.

The model turns her head toward the window and smiles, light shifting across her face.

Gentle parallax: clouds move across the mountain range while the foreground grass sways.

FAQ

What does Grok Imagine Video 1.5 do?

It takes a starting image plus a text prompt and produces a short video from it. You choose duration up to fifteen seconds, 480p or 720p, and an aspect ratio.

Is it different from the preview version?

The preview is an earlier test release of the same 1.5 line, and this model is the full release. Both animate an input image, so use this one for production work and the preview only if you want to compare.

Can I start from text only?

The 1.5 model works from a starting image. If you need to start from text, references or existing footage, grok-imagine-video covers those modes. Use that model for those starts.

Which aspect ratios are available?

Square, 3:2, 2:3, 4:3, 3:4, 16:9 and 9:16. Pick 9:16 for vertical feeds and 16:9 for landscape players. Square suits many social grids, so choose by where the clip will be shown.

How long can a clip be?

Between one and fifteen seconds. Shorter clips are easier to keep consistent, so many users generate several brief shots and cut them together. Edit them into a longer sequence afterwards.

How much does Grok Imagine Video 1.5 cost?

On TokenLab, Grok Imagine Video 1.5 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 use?

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

Which operations does Grok Imagine Video 1.5 support?

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