List routed models¶
Combines currently readable Workspace declarations with system/deployment models allowed by the permission scope.
GET https://api.moi.matrixorigin.cn/v5/models
Before you call this API¶
Set BASE_URL to the product API prefix https://api.moi.matrixorigin.cn/v5. For private deployments, use the corresponding product API URL.
Configure identity, Workspace, and model information in the same environment.
Request¶
curl --request GET \
"$BASE_URL/models" \
--header "X-API-Key: $MOI_KEY" \
--header "X-Workspace-ID: $WORKSPACE_ID"
Parameter |
Location |
Type |
Required |
Description |
|---|---|---|---|---|
|
Headers |
string |
Yes |
Workspace ID in the same environment. |
|
Queries |
string |
No |
Defaults to chat. Supports chat/vision/ocr/reasoning/embedding/rerank; embeddings aliases embedding at this entry point. |
|
Queries |
string |
No |
Registered service slot ID; applies its configuration as an additional filter, not an arbitrary scenario name. |
Combines currently readable Workspace declarations with system/deployment models allowed by the permission scope. System/TaaS supplementation requires collection filtering to be all. An empty restricted-object read does not establish a global lack of models. rerank currently returns empty; embedding follows embedding-list rules. Results do not prove model capability or successful inference.
Successful response¶
{
"code": "OK",
"msg": "OK",
"data": {
"models": [
{
"model": "chat-example",
"backend_id": 12,
"backend_name": "workspace-llm",
"model_type": "chat",
"source": "workspace",
"system_default": false
}
]
}
}
Field |
Type |
Description |
|---|---|---|
|
string |
OK on success. |
|
object |
Error responses¶
States and errors distinguishes string and numeric protocols. Confirm probe candidates, saved configuration, and actual inference separately.