Submit a request
Create an async generation task and poll the task endpoint for terminal status updates.
Kling V2.6 Motion Control supports motion control and is suitable for video generation that needs controllable motion paths.
Submit a task to MindVideo with your platform model slug. The response includes a request ID, task ID, normalized status, and estimated cost.
For production retries, send a unique Idempotency-Key per business request. Reusing the same key with the same payload returns the original task without charging again; reusing it with different input returns 409.
curl -X POST https://api.mindvideo.ai/api/v1/tasks \
-H "Authorization: Bearer mv_live_xxx" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: task_$(date +%s)" \
-d '{
"model": "kling-v2-6-motion-control",
"input": {
"prompt": "保持人物面部特征一致,按参考视频完成转身挥手动作,电影感光影",
"character_orientation": "image",
"image_url": "https://example.com/ref-image.png",
"keep_original_sound": "yes",
"mode": "std",
"video_url": "https://example.com/ref-video-8s.mp4"
}
}'Every server-side request must include an API key in the Authorization header. Keys can be created, disabled, and deleted from the dashboard.
The platform maps runtime states into queued, processing, succeeded, failed, or cancelled so clients do not depend on model-specific fields.
Create an async generation task and poll the task endpoint for terminal status updates.
curl https://api.mindvideo.ai/api/v1/tasks/task_demo_model \
-H "Authorization: Bearer mv_live_xxx"curl https://api.mindvideo.ai/api/v1/tasks/task_demo_model/events \
-H "Authorization: Bearer mv_live_xxx"{
"request_id": "req_demo_model",
"task_id": "task_demo_model",
"status": "succeeded",
"cost_estimate": 0.06426,
"cost_actual": 0.06426,
"output": {
"videos": [
{
"url": "https://example.com/output/demo.mp4"
}
]
}
}Inputs can reference hosted files or compact data URIs depending on model constraints. Production apps should prefer stable hosted URLs.
{
"type": "object",
"required": [
"image_url",
"video_url",
"character_orientation",
"mode"
],
"properties": {
"mode": {
"enum": [
"std",
"pro"
],
"type": "string",
"title": "Mode",
"default": "std"
},
"prompt": {
"type": "string",
"title": "Prompt",
"minLength": 1,
"description": "Optional text prompt to refine motion, camera, and style.",
"x-playground": {
"rows": 6,
"widget": "textarea"
}
},
"image_url": {
"type": "string",
"title": "Reference image",
"description": "Required reference image URL.",
"x-playground": {
"accept": "image/*",
"widget": "file-upload",
"uploadKind": "image"
}
},
"video_url": {
"type": "string",
"title": "Reference video",
"description": "Required reference video URL. probes the real video duration on the server side.",
"x-playground": {
"accept": "video/*",
"widget": "file-upload",
"uploadKind": "video"
}
},
"watermark_info": {
"type": "object",
"title": "Watermark",
"properties": {
"enabled": {
"type": "boolean",
"default": false
}
},
"x-playground": {
"advanced": true
},
"additionalProperties": false
},
"keep_original_sound": {
"enum": [
"yes",
"no"
],
"type": "string",
"title": "Keep original sound",
"default": "yes"
},
"character_orientation": {
"enum": [
"image",
"video"
],
"type": "string",
"title": "Character orientation",
"default": "image",
"description": "image requires a 3-10s reference video; video requires a 3-30s reference video."
}
},
"additionalProperties": false
}{
"request_id": "req_demo_model",
"task_id": "task_demo_model",
"status": "succeeded",
"cost_estimate": 0.06426,
"cost_actual": 0.06426,
"output": {
"videos": [
{
"url": "https://example.com/output/demo.mp4"
}
]
}
}