curl --request POST \
--url https://api.tikway.ai/v1/videos \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "minimax-h3",
"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": 5,
"resolution": "2K",
"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 MiniMax H3 video
Create MiniMax H3 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 |
|---|---|---|---|---|---|
minimax-h3 | 768p / 2K | 4–15 seconds | Vincent, first frame, last frame, first and last frame, full-modal reference | Native audio output; no generate_audio switch | 9 images / 3 video / 3 audio |
Source: MiniMax H3 Video Generation V2 API. 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": "minimax-h3",
"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": 5,
"resolution": "2K",
"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 MiniMax H3 video job. Parameters are narrowed according to the current Tikway gateway capabilities; for differences between models, see operation description and x-model-capabilities.
MiniMax H3 Model ID.
minimax-h3 Video generation or editing prompt words.
1Required. MiniMax H3 supports integer durations of 4–15 seconds.
4 <= x <= 15Output resolution. Available values for different models or modes are shown in the model capabilities table.
768p, 2K Video aspect ratio. When producing videos, some models will automatically determine the proportions based on the input material.
adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 The first frame or the last frame reference picture; at most one of the same type.
2Full-modal reference material: up to 9 images, 3 videos, and 3 audios. Reference mode and first/last frame mode are mutually exclusive.
15- 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, audio_url Material usage. When omitted, normal reference material is inferred from the URL field.
reference_image, reference_video, reference_audio Video URL string.
1Audio URL string.
1Preset patch ID; only used by some models that support patch references.
1User task callback address. Called by Tikway after the task status changes, it is not directly passed to the model upstream.
^https://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"

