Text to video
Elo with audio · text-to-video arena
Grok Imagine Video 1.5 Preview overview
Grok Imagine Video 1.5 Preview by xAI
Grok Imagine Video 1.5 Preview is xAI's advanced image-to-video generation model. It transforms static images into smooth, realistic video sequences.
Grok Imagine Video 1.5 Preview specs
- Model ID
x-ai/grok-imagine-video-1.5-preview- Developer
- xAI
- Input
- Text, Image
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
What exactly is Grok Imagine Video 1.5 Preview?
Grok Imagine Video 1.5 Preview is xAI's latest image-to-video generation model, designed to transform static images into smooth, high-fidelity video sequences. It builds on the original Grok Imagine Video with improved temporal coherence, motion quality, and prompt adherence, delivering cinematic output from a single image and a text description.
Architecture: what makes it work
Image-conditioned video synthesisThe model uses the input image as a visual anchor for the first frame. Subsequent frames are generated autoregressively while maintaining consistency with the original composition, lighting, and subject identity, producing natural-looking motion rather than a slideshow of unrelated frames.
Temporal coherence modelingGrok Imagine Video 1.5 Preview is trained to preserve object continuity and scene geometry across frames. Motion is physically plausible, subjects move, deform, and interact with the scene in ways consistent with the source image rather than drifting arbitrarily.
Text-guided motion controlA text prompt specifies the type and direction of motion. The model combines visual grounding from the image with semantic direction from the prompt, allowing precise control over what moves, how it moves, and at what intensity.
Use cases
It is suited to turning a still image into a short animated video sequence with coherent motion and visual consistency. It is also suited to creating fluid, cinematic video from a single starting image, with camera moves, atmosphere, and physics controlled by natural-language prompts. It is documented as working well for sequences, where frames can be staged and chained into longer scenes that keep a consistent look across a project. It is also suited to image-to-video generation with synchronized audio, including background music, sound effects, and lip-synced dialogue.
Grok Imagine Video 1.5 Preview benchmarks by 
Artificial Analysis
Human-preference results for Grok Imagine Video 1.5 Preview in text to video, silent video and image to video, next to models available on AI/ML API. Data retrieved Nov 3, 2026.
Models on AI/ML API
Arena results for models you can call with the same API key.
Text to video
Blind votes on clips with generated sound, made from a text prompt. Grok Imagine Video 1.5 Preview ranks #13 of 31.
Silent video
The same text-to-video task, judged as silent video. Grok Imagine Video 1.5 Preview ranks #14 of 36.
Image to video
Blind votes on clips with sound animated from a start image. Grok Imagine Video 1.5 Preview ranks #13 of 29.
Silent image to video
Clips animated from a start image, judged as silent video. Grok Imagine Video 1.5 Preview ranks #13 of 34.
Grok Imagine Video 1.5 Preview API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.08 | per 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 1.5 Preview vs other video models: prices
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
 Grok Imagine Video 1.5 Preview | $0.08 |
| Grok Imagine Video | $0.05 |
 Luma Dream Machine Ray-2 | $0.0796 |
 VEED Fabric 1.0 | $0.08 |
 Veo 3.1 Fast | $0.08 |
How to use the Grok Imagine Video 1.5 Preview API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
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-1.5-preview",
"image_url": "https://example.com/input.jpg"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "x-ai/grok-imagine-video-1.5-preview",
"image_url": "https://example.com/input.jpg"
}
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-1.5-preview",
"image_url": "https://example.com/input.jpg"
}),
});
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.
Models similar to Grok Imagine Video 1.5 Preview
Related articles
Grok Imagine Video 1.5 Preview FAQ
What inputs and outputs does Grok Imagine Video 1.5 Preview support?
Grok Imagine Video 1.5 Preview takes image, text, video as input and returns video.
How much does Grok Imagine Video 1.5 Preview cost?
Grok Imagine Video 1.5 Preview costs $0.08 per second on AI/ML API, billed as you go with no subscription.
How is Grok Imagine Video 1.5 Preview billed?
Grok Imagine Video 1.5 Preview costs $0.08 per second on AI/ML API, billed as you go with no subscription.
Can Grok Imagine Video 1.5 Preview take an existing image as input?
Yes, Grok Imagine Video 1.5 Preview accepts image input as well as a text prompt.
Who created Grok Imagine Video 1.5 Preview?
Grok Imagine Video 1.5 Preview was built by xAI .
How do I call Grok Imagine Video 1.5 Preview on AI/ML API?
Use x-ai/grok-imagine-video-1.5-preview as the model id on AI/ML API.
Is Grok Imagine Video 1.5 Preview available through a single API key?
Yes. Grok Imagine Video 1.5 Preview is served through AI/ML API, so the same key and endpoint format used for other models applies.
What is Grok Imagine Video 1.5 Preview typically used for?
It is designed for turning images into short animated videos, useful for social media content, visual concepts, and motion generation.
What is the Grok Imagine Video 1.5 Preview model ID?
Use x-ai/grok-imagine-video-1.5-preview as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.