Video model by xAI
Grok Imagine Video 1.5 API
model: grok-imagine-video-1.5
Call Grok Imagine Video 1.5 with your KeelRouter API key, the same key you use for every other model. From $0.015 per second, paid per call from a prepaid balance. Failed calls are free.
Pricing
| Option | Price |
|---|---|
| 480p | $0.015 per second |
| 720p | $0.029 per second |
| 1080p | $0.052 per second |
Call it
Async: POST /v1/video/generations returns a taskId; poll the same path with ?task_id= or pass a callback_url.
curl https://api.keelrouter.com/v1/video/generations \
-H "Authorization: Bearer $KEELROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-video-1.5",
"prompt": "A paper boat drifting down a rainy street, slow camera follow",
"resolution": "480p"
}'Parameters
| Name | Type | Notes |
|---|---|---|
| model | string | Required. grok-imagine-video-1.5 |
| prompt | string | |
| images | array | Range …–7. |
| resolution | string | One of 480p, 720p, 1080p. Default 720p. |
| duration | number | Range 1–15. Default 10. |
| aspect_ratio | string | One of 16:9, 9:16, 1:1, 3:2, 2:3. Default 16:9. |
| callback_url | string | Optional https URL; we POST the result when the task ends |
FAQ
- How much does the Grok Imagine Video 1.5 API cost on KeelRouter?
- From $0.015 per second. You pay per call from a prepaid USD balance; failed calls are not charged.
- How do I call Grok Imagine Video 1.5?
- POST to /v1/video/generations with model "grok-imagine-video-1.5". You get a taskId back; poll the same endpoint with ?task_id= or pass a callback_url.
- Is this the official Grok Imagine Video 1.5 API?
- No. KeelRouter is an independent API gateway. Requests run on Grok Imagine Video 1.5 through our upstream providers, and the video model keeps its own safety filters.
- How long are results kept?
- Result files are kept for 30 days, then deleted. Download what you want to keep.
KeelRouter is an independent service and is not affiliated with xAI. Grok Imagine Video 1.5 is a trademark of its owner, used here only to name the model a request runs on.