Build with Kling 2.5 Turbo Pro
Make your first request
Use your Sorceress API key on your server. The playground uses your signed-in account; your application uses the same model with an API key.
curl -X POST 'https://sorceress.games/api/v1/jobs' \
-H 'Authorization: Bearer $SORCERESS_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "kwaivgi/kling-v2.5-turbo-pro",
"input": {
"duration": "5",
"guidance_scale": 0.5,
"aspect_ratio": "16:9",
"generation_mode": "i2v",
"prompt": "<prompt>"
}
}'Inputs & settings
promptstringRequiredDescribe what you would like to create.
durationstringVideo length (5 or 10 seconds)
Options: 5, 10
guidance_scalenumberHow closely to follow the prompt
aspect_ratiostringVideo aspect ratio (T2V mode)
Options: 16:9, 9:16, 1:1
generation_modestringOptions: i2v, t2v
image_urlsarrayUpload a file or enter one public HTTPS URL per line.
Full input schema
{
"required": [
"prompt"
],
"properties": {
"prompt": {
"type": "string",
"title": "Prompt",
"description": "Describe what you would like to create."
},
"duration": {
"type": "string",
"title": "Duration (seconds)",
"default": "5",
"enum": [
"5",
"10"
],
"description": "Video length (5 or 10 seconds)"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 0.5,
"minimum": 0,
"maximum": 1,
"description": "How closely to follow the prompt"
},
"aspect_ratio": {
"type": "string",
"title": "Aspect Ratio",
"default": "16:9",
"enum": [
"16:9",
"9:16",
"1:1"
],
"description": "Video aspect ratio (T2V mode)"
},
"generation_mode": {
"type": "string",
"title": "Mode",
"enum": [
"i2v",
"t2v"
],
"default": "i2v"
},
"image_urls": {
"type": "array",
"title": "Reference images",
"items": {
"type": "string",
"format": "uri"
},
"maxItems": 1,
"description": "Upload a file or enter one public HTTPS URL per line."
}
}
}Results, saved runs & billing
Media requests return a job ID. Poll GET /api/v1/jobs/:id until it succeeds or fails; keep the same ID while it is processing. Long chat requests can also return a saved job to poll. Completed outputs are stored in your account, and successful work is billed using your model's current rates.
A multi-step workflow may include separately billed successful actions. If a connection drops, check your saved run before submitting it again.
