Build with MiniMax H3
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": "minimax-h3-text-to-video",
"input": {
"duration": 6,
"resolution": "2K",
"prompt": "<prompt>",
"aspect_ratio": "<aspect_ratio>"
}
}'Inputs & settings
promptstringRequiredVideo generation prompt, length is between 1 and 7000 characters.
durationintegerRequiredGenerated video duration, supports integer values from 4 to 15 seconds.
Options: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
resolutionstringVideo resolution.
Options: 768P, 2K
aspect_ratiostringRequiredVideo aspect ratio. Required for text-to-video, adaptive is not supported.
Options: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Full input schema
{
"type": "object",
"required": [
"prompt",
"aspect_ratio",
"duration"
],
"properties": {
"prompt": {
"type": "string",
"title": "Prompt",
"maxLength": 7000,
"minLength": 1,
"description": "Video generation prompt, length is between 1 and 7000 characters."
},
"duration": {
"enum": [
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15
],
"type": "integer",
"title": "Duration",
"default": 6,
"maximum": 15,
"minimum": 4,
"description": "Generated video duration, supports integer values from 4 to 15 seconds."
},
"resolution": {
"enum": [
"768P",
"2K"
],
"type": "string",
"title": "Resolution",
"default": "2K",
"description": "Video resolution."
},
"aspect_ratio": {
"enum": [
"21:9",
"16:9",
"4:3",
"1:1",
"3:4",
"9:16"
],
"type": "string",
"title": "Aspect ratio",
"description": "Video aspect ratio. Required for text-to-video, adaptive is not supported."
}
}
}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.
