Build with AI Auto-Rig
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/tools/model_rig' \
-H 'Authorization: Bearer $SORCERESS_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"modelUrl": "<modelUrl>"
}'Inputs & settings
modelUrlstringRequiredhttps URL of a humanoid character .glb to rig — typically mesh.url from a finished model_generate job. Static/unrigged, roughly T- or A-pose, standing.
extraYawDegnumberExtra turn (0 | 90 | 180 | 270) about the up axis on top of automatic orientation. Only needed if a first rig came back mirrored or facing sideways.
Full input schema
{
"required": [
"modelUrl"
],
"properties": {
"modelUrl": {
"type": "string",
"title": "model Url",
"description": "https URL of a humanoid character .glb to rig — typically mesh.url from a finished model_generate job. Static/unrigged, roughly T- or A-pose, standing.",
"format": "uri"
},
"extraYawDeg": {
"type": "number",
"title": "extra Yaw Deg",
"description": "Extra turn (0 | 90 | 180 | 270) about the up axis on top of automatic orientation. Only needed if a first rig came back mirrored or facing sideways."
}
}
}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.






