AIAssistantsCustomModelConfig
Explicit model endpoint configuration for all four tiers (embedding, low_iq, normal_iq, high_iq) used in a custom deployment. On write, supply api_url and api_key per tier. For GCP-backed embedding tiers, api_key may be omitted when GCP service-account authentication is used. On read, all fields including backend-resolved values are returned.
{
"low_iq": {
"model_id": "string",
"model_name": "string",
"sdk_provider": "string",
"api_url": "string",
"api_key": "string"
},
"normal_iq": {
"model_id": "string",
"model_name": "string",
"sdk_provider": "string",
"api_url": "string",
"api_key": "string"
},
"high_iq": {
"model_id": "string",
"model_name": "string",
"sdk_provider": "string",
"api_url": "string",
"api_key": "string"
},
"embedding": {
"model_id": "string",
"model_name": "string",
"sdk_provider": "string",
"api_url": "string",
"api_key": "string"
}
}Configuration for a single model tier (embedding or reasoning). On write, supply model_id, api_url, and api_key (when required). On read, all fields except api_key are returned.
Configuration for a single model tier (embedding or reasoning). On write, supply model_id, api_url, and api_key (when required). On read, all fields except api_key are returned.
Configuration for a single model tier (embedding or reasoning). On write, supply model_id, api_url, and api_key (when required). On read, all fields except api_key are returned.
Configuration for a single model tier (embedding or reasoning). On write, supply model_id, api_url, and api_key (when required). On read, all fields except api_key are returned.