Grok Imagine Video overview
Grok Imagine Video by xAI
Grok Imagine Video is xAI's image-to-video generation model that converts static images into dynamic video content. Accessible through AIML API for fast and easy integration.
Grok Imagine Video specs
- Model ID
x-ai/grok-imagine-video- Developer
- xAI
- Input
- Text, Image
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
What exactly is Grok Imagine Video?
Grok Imagine Video is xAI's image-to-video generation model that animates static images into short video clips using a text motion prompt. It is the production-ready predecessor to the 1.5 Preview release, stable, cost-efficient, and well-suited for workflows that require consistent video output at scale.
Architecture: what makes it work
Image-anchored generationThe source image defines the visual starting state of the video. The model generates subsequent frames conditioned on both the image embedding and the text prompt, maintaining subject identity and scene composition throughout the clip.
Motion-aware decodingFrame transitions are computed to reflect physically plausible motion, the model is not interpolating between keyframes but generating each frame with awareness of prior context, producing fluid rather than stuttery animation.
Prompt-driven scene controlText input describes the desired motion: camera direction, subject behavior, environmental effects. The model blends semantic intent from the prompt with spatial information from the image to produce targeted, controllable output.
Core capabilities
Image-to-video animationConvert any image into an animated video clip. Suitable for product photography, illustrations, portraits, architectural renders, and graphic design assets.
Consistent subject preservationThe primary subject of the source image is maintained across frames, faces, objects, and branded elements do not distort or drift over the course of the clip.
Scalable video productionLow cost per second of output makes Grok Imagine Video practical for high-volume workflows, batch processing product catalogs, automating social content pipelines, or generating variations at scale.
Who should use Grok Imagine Video?
E-commerce and retail teamsTeams animating product images for ads, landing pages, or marketplace listings without manual video editing.
Marketing automation pipelinesContent operations teams generating short video variations from existing image libraries, at volume, without per-asset production cost.
Developers and platform buildersEngineers integrating video generation into creative tools, CMS platforms, or media workflows where cost efficiency and API simplicity are the primary requirements.
Startups and indie creatorsCost-conscious teams that need reliable image-to-video output without the per-second pricing of higher-tier models.
Use cases
Grok Imagine Video is documented as suited to generating videos from text prompts, including text-to-video workflows. It is also documented for image-to-video use, where a still image is animated into a video.
It is documented for reference-to-video generation, using reference images to guide the output and preserve specific visual elements. It is also documented for extending an existing video by continuing from its last frame.
Grok Imagine Video API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.05 | second |
The final price depends on request parameters such as resolution or duration.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Grok Imagine Video vs other video models: prices
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
| $0.05 | |
| $0.05 | |
| $0.05 | |
| $0.05 | |
| $0.08 |
How to use the Grok Imagine Video API
View docsBuild with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "x-ai/grok-imagine-video"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "x-ai/grok-imagine-video"
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "x-ai/grok-imagine-video"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
Related articles
Grok Imagine Video FAQ
What inputs and outputs does Grok Imagine Video support?
Grok Imagine Video takes image, text, video as input and returns video.
How much does Grok Imagine Video cost?
Grok Imagine Video costs $0.05 per second on AI/ML API, billed as you go with no subscription.
How is Grok Imagine Video billed?
Grok Imagine Video costs $0.05 per second on AI/ML API, billed as you go with no subscription.
Can Grok Imagine Video take an existing image as input?
Yes, Grok Imagine Video accepts image input as well as a text prompt.
Who created Grok Imagine Video?
Grok Imagine Video was built by xAI .
How do I call Grok Imagine Video on AI/ML API?
Use x-ai/grok-imagine-video as the model id on AI/ML API.
Is Grok Imagine Video available through a single API key?
Yes. Grok Imagine Video is served through AI/ML API, so the same key and endpoint format used for other models applies.
Does Grok Imagine Video accept text prompts in addition to images?
Yes, it takes image and text inputs together with video and produces video output.
What is Grok Imagine Video designed to do?
It transforms static images into short animated video clips with coherent motion and visual consistency.
What category of model is Grok Imagine Video?
It is classified as a video generation model.

