Generate reference to video with Grok Imagine Video 1.5 (xAI): native audio, up to 15 seconds, via one simple API endpoint. Generate videos with Grok Imagine Video 1.5 (xAI) guided by multiple reference images, with native audio, up to 15 seconds.
Generate videos with Grok Imagine Video 1.5 (xAI) guided by multiple reference images, with native audio, up to 15 seconds.
About this model
Grok Imagine Video 1.5 Reference-to-Video is xAI's flagship video model on a dedicated Muapi endpoint. Generate clips of 1 to 15 seconds with a native audio track in 480p or 720p, across nine aspect ratios from 16:9 and 9:16 to 21:9 and 5:2. It is suited to cinematic shots, product videos and social content where motion quality and audio matter.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.08/sec at 480p, $0.14/sec at 720p, $0.25/sec at 1080p (8s at 480p = $0.64) — reference-to-video supports 480p and 720p | Pay-as-you-go with no subscription required. |
Pay-as-you-go with no subscription required.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Text description of the video. | A dog running on a sunny beach, cinematic slow motion. |
| Reference Images | array | Reference image URLs that guide the video. | undefined |
| Aspect Ratio | Enum (9 options) | Aspect ratio of the video. | 16:9 |
| Resolution | Enum (2 options) | Output resolution. | 480p |
| Duration (seconds) | int | Video duration in seconds. | 8 |
| Generate Audio | boolean | Generate a native audio track. Turn off for a silent video. | true |
Text description of the video.
A dog running on a sunny beach, cinematic slow motion.Reference image URLs that guide the video.
undefinedAspect ratio of the video.
16:9Output resolution.
480pVideo duration in seconds.
8Generate a native audio track. Turn off for a silent video.
trueDeveloper documentation
Input: Provide a prompt and up to 7 reference images in images_list to guide the subject and style.
Set duration, resolution and audio: 1-15 seconds (default 8), resolution 480p or 720p, and generate_audio on or off.
Submit and poll: The API returns a request_id; poll GET /api/v1/predictions/{request_id}/result until status is completed.
curl -X POST "https://api.muapi.ai/api/v1/grok-imagine-video-1-5-reference-to-video" \
-H "x-api-key: $MUAPI_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"The character from the references walks through a neon city at night.","images_list":["https://example.com/ref1.jpg","https://example.com/ref2.jpg"],"aspect_ratio":"16:9","duration":8,"resolution":"720p"}'
Frequently asked
Yes. generate_audio defaults to true and produces a native audio track. Set it to false for a silent video.
From 1 to 15 seconds, with a default of 8 seconds.
480p and 720p for reference-to-video.
16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9 and 5:2.
$0.08/sec at 480p, $0.14/sec at 720p, $0.25/sec at 1080p (8s at 480p = $0.64) — reference-to-video supports 480p and 720p