curl --request POST \
--url https://api.tikway.ai/v1/videos \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "grok-imagine-video-1.5-fast",
"prompt": "A golden retriever runs on the beach at sunset. The camera follows smoothly, and the picture has a natural and delicate film quality.",
"duration": 10,
"resolution": "720p",
"aspect_ratio": "16:9"
}
'{
"id": "9552de3d-171f-4cca-b492-7baa56523239",
"status": "pending",
"polling_url": "https://api.tikway.ai/v1/videos/9552de3d-171f-4cca-b492-7baa56523239"
}Create a Grok Imagine Video video
Create Grok Imagine Video video tasks via unified POST /v1/videos. Model capabilities are subject to the actual callable range of the current Tikway gateway.
| Model | Resolution | Duration | Supported Modes | Audio | Reference Limitations |
|---|---|---|---|---|---|
grok-imagine-video-1.5-fast | 480p / 720p | 6–30 seconds | Vincent, up to 7 picture reference, first and last frames | Upstream defaults to sound; the current unified field cannot be turned off | Unofficial high-speed channel |
grok-imagine-video-1.5 | 480p / 720p / 1080p | 1–15 seconds | Up to 7 reference images and 4 keyframes; up to 3 preset voices | Default is sound; the current unified field cannot be turned off | Supports first and last frames |
grok-imagine-video | 480p / 720p | Generate 1–15 seconds; extend 1–10 seconds | Vincent, multi-image reference, video extension | Upstream has sound by default; the current unified field cannot be turned off | End frame is not supported |
Source: xAI Video Generation Documentation. The difference between the official website capabilities and the current unopened capabilities of the gateway can be found in this audit report.
curl --request POST \
--url https://api.tikway.ai/v1/videos \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "grok-imagine-video-1.5-fast",
"prompt": "A golden retriever runs on the beach at sunset. The camera follows smoothly, and the picture has a natural and delicate film quality.",
"duration": 10,
"resolution": "720p",
"aspect_ratio": "16:9"
}
'{
"id": "9552de3d-171f-4cca-b492-7baa56523239",
"status": "pending",
"polling_url": "https://api.tikway.ai/v1/videos/9552de3d-171f-4cca-b492-7baa56523239"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Create a Grok Imagine Video video task. Parameters are narrowed according to the current Tikway gateway capabilities; for differences between models, see operation description and x-model-capabilities.
Grok Imagine Video Model ID.
grok-imagine-video-1.5, grok-imagine-video Video generation or editing prompt words.
1Model related: 6–30 seconds for 1.5 Fast; 1–15 seconds for 1.5 and Basic; 1–10 seconds for Basic video extension.
1 <= x <= 30Video aspect ratio. When producing videos, some models will automatically determine the proportions based on the input material.
2:3, 3:2, 1:1, 9:16, 16:9 Output resolution. Available values for different models or modes are shown in the model capabilities table.
480p, 720p, 1080p 1.5 Fast supports the first and last frames; 1.5 and the basic version can only use one picture as the first frame and cannot pass last_frame.
2Up to 7 ordinary reference images map to refer_images. The 1.5 series supports up to 4 keyframe images with a seconds timestamp, mapped to keyframes. Grok 1.5 supports up to 3 preset voices using only reference_voice and role=reference_audio; audio_url is not required. Video input is available for extension on the base model only.
14- Option 1
- Option 2
- Option 3
Hide child attributes
Hide child attributes
Image URL string.
1Optional. Material type; if provided, must be consistent with the corresponding URL field.
image_url, video_url Material usage. When omitted, normal reference material is inferred from the URL field.
reference_image, keyframe, source_video, first_clip, reference_audio Video URL string.
1Preset voice ID. Grok 1.5 reference_audio uses this without audio_url.
1Target timestamp in seconds for a keyframe image.
User task callback address. Called by Tikway after the task status changes, it is not directly passed to the model upstream.
^https://Grok extension parameters. It is recommended to use unified fields first.
Response
POST /v1/videos Response parameters after the video task is successfully created. The interface returns HTTP 202.
The unique identifier of the video generation task, used for subsequent query of task status.
1"9552de3d-171f-4cca-b492-7baa56523239"
Task creation status. pending means that the task has been created and is waiting for submission; queue means that the task has entered the generation queue.
pending, queue "queue"
Video task query address, the client can poll the task status through GET request.
^https://"https://api.example.com/v1/videos/9552de3d-171f-4cca-b492-7baa56523239"