Grok Imagine Video 1.5

POST /v2/videos/generate — model: "grok-imagine-video-1.5"

xAI's latest Grok Imagine video model. It is image-to-video only: supply a source image and describe the motion. Compared with Grok Imagine Video, 1.5 delivers better motion, physics, and temporal consistency. Resolution is fixed at 720p.

See Video Generation overview for common request fields, response format, and error codes.

Model-specific parameters

Parameter	Type	Required	Default	Description
`grokImagineVideo15Params.image`	string	Yes	—	URL of the still image to animate. Supports jpg, jpeg, png, webp
`grokImagineVideo15Params.duration`	number	No	`6`	Video duration in seconds: `6`, `10`, or `15`
`grokImagineVideo15Params.aspect_ratio`	string	No	`"auto"`	Aspect ratio: `"auto"`, `"1:1"`, `"16:9"`, `"9:16"`, `"4:3"`, `"3:4"`, `"3:2"`, `"2:3"`. `"auto"` keeps the source image's native ratio

Credit cost

Variant	Credits
`6s`	144
`10s`	240
`15s`	360

Example result

Once the job is COMPLETED, the result object on GET /v2/jobs/:id looks like:

{
  "videoUrl": "https://cdn2.apiframe.ai/videos/b2c3d4e5-f6a7-8901-bcde-f23456789012.mp4"
}

See Result format for field details.

Code examples

curl -X POST https://api.apiframe.ai/v2/videos/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "slow cinematic push-in as embers drift across the scene",
    "model": "grok-imagine-video-1.5",
    "grokImagineVideo15Params": {
      "image": "https://example.com/still.jpg",
      "duration": 10
    }
  }'

import requests

response = requests.post(
    "https://api.apiframe.ai/v2/videos/generate",
    headers={
        "X-API-Key": "afk_your_api_key_here",
        "Content-Type": "application/json",
    },
    json={
        "prompt": "slow cinematic push-in as embers drift across the scene",
        "model": "grok-imagine-video-1.5",
        "grokImagineVideo15Params": {
            "image": "https://example.com/still.jpg",
            "duration": 10,
        },
    },
)
print(response.json())

const response = await fetch("https://api.apiframe.ai/v2/videos/generate", {
  method: "POST",
  headers: {
    "X-API-Key": "afk_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "slow cinematic push-in as embers drift across the scene",
    model: "grok-imagine-video-1.5",
    grokImagineVideo15Params: {
      image: "https://example.com/still.jpg",
      duration: 10,
    },
  }),
});
console.log(await response.json());

body := `{
  "prompt": "slow cinematic push-in as embers drift across the scene",
  "model": "grok-imagine-video-1.5",
  "grokImagineVideo15Params": {
    "image": "https://example.com/still.jpg",
    "duration": 10
  }
}`
req, _ := http.NewRequest("POST", "https://api.apiframe.ai/v2/videos/generate",
    strings.NewReader(body))
req.Header.Set("X-API-Key", "afk_your_api_key_here")
req.Header.Set("Content-Type", "application/json")

resp, err := http.DefaultClient.Do(req)

Choosing between 1.5 and the base model

	Grok Imagine Video	Grok Imagine Video 1.5
Text-to-video	Yes	No — image required
Image-to-video	Yes (up to 7 reference images)	Yes (one source image)
Motion and physics	Good	Best in the family
Cost (6s)	54 credits	144 credits

Use the base model for text-only prompts and cheaper drafts; use 1.5 when you have a hero still and want the highest-fidelity motion.

Try it

POST/v2/videos/generateTry it

API Key

Request Body (JSON)