Skip to content
youbot
Grok Imagine cover

Grok Imagine

grok-imagine-image-to-video
GrokCommercial use API verifiedVideo generationAspect ratiosDuration

Grok Imagine — high-quality AI video generation.

by Grok

View as Markdown
Model Type:

Pricing: 480P: 2.93 credits/s (≈ $0.0293/s), 720P: 4.3 credits/s (≈ $0.043/s).

41% cheaperthan the official Grok API — pay only for successful runs

24H Status Monitor

Operational
24h agonow

Input

image_urls
Drag and drop or click to upload your imageSupported formats: JPEG, PNG, WEBP · Maximum file size: 10MB; Maximum files: 7Select files

Provide one external image URL as a reference for video generation (only one image is supported). This is one of two image input options — you can either upload an external image or specify a task_id + index from a Grok-generated image below. Do not provide both image_urls and task_id at the same time.In your prompt, reference an uploaded image by typing @image(n) followed by a space (for example: @image1 a sunset over the ocean).

task_id

Enter the task_id of an image previously generated with the Grok model on you.bot. Use it together with the index below to select a specific image from that generation. When using this method, do not provide image_urls. Unlike external images, this method supports Spicy mode.

index

When using a task_id, specify which image to use (Grok generates 6 images per task). This parameter only works with task_id and is ignored if image_urls is used(0-based).

prompt145 / 5000 characters
145 / 5000

The text prompt describing the desired video motion

mode

Note: When generating videos using external image inputs, Spicy mode is not supported and will automatically switch to Normal.

aspect_ratio

The aspect ratio of the video. This parameter is invalid if it is a single image.

duration

The duration of the generated video in seconds

resolution

Resolution of the generated video

nsfw_checker

A configurable parameter. Defaults to true in the Playground.

≈ 17.68 cr / run

Output

output typevideo
View full history

Explore more video models

Veo 3.1
Google

Veo 3.1

State-of-the-art text & image to video with native audio.

Google

Veo 3.1 Fast

Lower-latency Veo for rapid iteration and previews.

Kuaishou

Kling 3.0

Cinematic text & image to video with native sound and multi-shot support.

ByteDance

Seedance V1

Seedance V1 — high-quality AI video generation.

Alibaba

HappyHorse-1.0

HappyHorse-1.0 — high-quality AI video generation.

Wan 2.7 Video
Wan

Wan 2.7 Video

Wan 2.7 Video — high-quality AI video generation.