Grok Imagine Video 1.5

Grok Imagine Video 1.5 (x-ai/grok-imagine-video-1.5) is a video generation model from SpaceXAI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject and camera motion, pacing, atmosphere, and physical behavior while maintaining visual continuity, and can generate synchronized sound effects, ambience, and dialogue. Generation is asynchronous: POST /v1/videos returns a job, then you poll the status and download the mp4.

Parameters

Field	Description
model	x-ai/grok-imagine-video-1.5 (or the short grok-imagine-video-1.5)
prompt	Scene description, required
seconds	Any integer from 1 to 15; defaults to 1
size	A WxH size from the table below; defaults to 1280x720
input_reference	Image-to-video: one image as the starting frame, {"image_url": "data:image/...;base64,..."}
input_references	Reference-to-video: 2 to 7 images as an array, also data: URLs only — the xAI upstream caps it at 7
seed	Not supported: the model’s seed is false; a request with the field returns 400

Twenty-one allowed sizes — seven aspect ratios at three resolutions:

Aspect	480p	720p	1080p
16:9	852x480	1280x720	1920x1080
9:16	480x852	720x1280	1080x1920
1:1	480x480	720x720	1080x1080
4:3	640x480	960x720	1440x1080
3:4	480x640	720x960	1080x1440
3:2	720x480	1080x720	1620x1080
2:3	480x720	720x1080	1080x1620

A value outside the list returns 400 with the allowed options listed — check the sizes field in the catalog when in doubt.

Examples

Text-to-video

Python

import requests

job = requests.post(
    "https://api.mixen.ai/v1/videos",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
        "model": "x-ai/grok-imagine-video-1.5",
        "prompt": "A sports car accelerates down a night highway, neon reflecting off the wet asphalt, the camera overtakes and swings wide",
        "seconds": "6",
        "size": "1280x720",
    },
).json()
print(job["id"], job["status"])

cURL

curl https://api.mixen.ai/v1/videos \
  -H "Authorization: Bearer $MIXEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-imagine-video-1.5",
    "prompt": "A sports car accelerates down a night highway, neon reflecting off the wet asphalt, the camera overtakes and swings wide",
    "seconds": "6",
    "size": "1280x720"
  }'

Image-to-video from a starting frame

The image goes in as a single data: URL — external links are not accepted:

import base64
import requests

with open("scene.jpg", "rb") as f:
    img = "data:image/jpeg;base64," + base64.b64encode(f.read()).decode()

job = requests.post(
    "https://api.mixen.ai/v1/videos",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
        "model": "x-ai/grok-imagine-video-1.5",
        "prompt": "The camera pushes in slowly on the hero, wind tugging at the clothes, rain audible",
        "seconds": "8",
        "size": "1280x720",
        "input_reference": {"image_url": img},
    },
).json()
print(job["id"], job["status"])

Reference-to-video from several images

Two to seven references — the model assembles the scene from them:

{
  "model": "x-ai/grok-imagine-video-1.5",
  "prompt": "The character from the first frame surveys the location from the second, wary movement",
  "seconds": "6",
  "size": "1280x720",
  "input_references": [
    "data:image/png;base64,iVBORw0...",
    "data:image/png;base64,iVBORw0..."
  ]
}

From there it is the usual loop: GET /v1/videos/{id} every 5–10 seconds until completed, then GET /v1/videos/{id}/content for the mp4. Full cycle — video guide.

Price

Billing is per second and depends on the resolution: 480p — 10.6954 ₽ ($0.12) per second, 720p — 18.717 ₽ ($0.21), 1080p — 33.4232 ₽ ($0.375). On top of the per-second rate, every input image — the starting frame or a reference — adds $0.01 to the clip’s cost. You are charged actual duration × the size’s rate. Current prices — catalog.

Strengths and limits

• Durations from 1 to 15 seconds — a continuous range and the shortest minimum among the catalog’s video models.
• Seven frame formats, including the uncommon 3:2 and 2:3, at 480p, 720p, and 1080p.
• Synced audio: sound effects, ambience, and dialogue are generated with the clip.
• Directing lives in the prompt: subject and camera motion, pacing, atmosphere, and physical behavior.
• Images are data: URLs only: one starting frame or up to 7 references (other video models accept up to 9).
• Every input image adds $0.01 to the price — noticeable on clips with a full set of references.

All models — in the catalog. The general video workflow — video guide.