02-Image-to-Video
Image-to-Video
Doc version：v1.0.0 | Last updated：2026-06-11 This platform fully supports the Grok (xAI) official video generation API. Requests and responses are transparently proxied; parameter semantics are identical to the official API.
Create Task
POST https://platform.dataeyes.ai/grok/v1/videos/generationsRequest Headers
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
Content-Type | string | Yes | application/json | Data exchange format |
Authorization | string | Yes | Authentication, refer to API authorization |
Request Body
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Yes | grok-imagine-video | Model identifier |
prompt | string | Yes | Text prompt for video generation | |
image | string | Yes | Image URL (public URL, Base64 data URL, or file_id from xAI Files API) | |
duration | integer | No | 8 | Video duration in seconds Range：1-15 |
aspect_ratio | string | No | 16:9 | Output video aspect ratio Options： 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3Defaults to input image native aspect ratio; if specified, image is stretched to match |
resolution | string | No | 480p | Output video resolution Options： 480p, 720p |
Request Example
curl --request POST \
--url 'https://platform.dataeyes.ai/grok/v1/videos/generations' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "grok-imagine-video",
"prompt": "A glowing crystal-powered rocket launching from the red dunes of Mars",
"image": "https://example.com/image.png",
"duration": 10,
"aspect_ratio": "16:9",
"resolution": "720p"
}'Response Example
{
"request_id": "req_abc123def456"
}Query Task
GET https://platform.dataeyes.ai/grok/v1/videos/{request_id}request_id.Request Headers
| Parameter | Type | Required | Description |
|---|---|---|---|
Authorization | string | Yes | Bearer {API_KEY} |
Request Example
curl --request GET \
--url 'https://platform.dataeyes.ai/grok/v1/videos/{request_id}' \
--header 'Authorization: Bearer <token>'Response Example
{
"status": "done",
"video": {
"url": "https://vidgen.x.ai/.../video.mp4",
"duration": 10,
"respect_moderation": true
},
"model": "grok-imagine-video"
}{
"status": "pending",
"model": "grok-imagine-video"
}{
"status": "failed",
"error": {
"code": "invalid_argument",
"message": "Prompt cannot be empty. Please provide a prompt."
}
}Query Response Fields
| Field | Type | Description |
|---|---|---|
status | string | Task status：pending, done, failed, expired |
video.url | string | Temporary URL of the generated video (valid 24 hours) |
video.duration | integer | Duration of the generated video (seconds) |
video.respect_moderation | boolean | Whether content passes moderation; if false, url is empty |
model | string | Model used |
error.code | string | Error code |
error.message | string | Error description |
Error Handling
error object with code and message fields. The possible error codes are:| Code | Meaning | Action |
|---|---|---|
invalid_argument | Invalid request input (unsupported duration, invalid image/video, prompt too long, conflicting modes, or content blocked by moderation) | Fix the request parameters or input media, then submit a new request |
permission_denied | The API key does not have permission for the requested operation | Verify API key permissions |
failed_precondition | The operation is not available for the selected model or settings | Change the model, mode, resolution, or other settings |
service_unavailable | Video generation is temporarily overloaded | Retry the request later |
internal_error | Internal service failure | Retry the request; if persistent, contact support with the request_id |
Authentication errors, missing models, and rate limits are returned synchronously as standard API errors before a video job is created.