List LLM backends through the Workspace API¶
List readable LLM backends in the current Workspace.
GET https://api.moi.matrixorigin.cn/v5/workspaces/{workspace_id}/llm/backends
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 object permissions in the same environment.
Request¶
curl --request GET \
"$BASE_URL/workspaces/$WORKSPACE_ID/llm/backends" \
--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. |
|
Path |
string |
Yes |
Workspace ID in the same environment. |
Unpaginated; returns backends/total. Both fields may be omitted for zero results, with SDK defaults of an empty collection/0. Lists filter by model_backend.read and are not the complete routing pool of system-default/deployment models.
Successful response¶
{
"code": 0,
"data": {
"backends": [
{
"id": 12,
"name": "临时后端",
"timeout_seconds": 120,
"models": [
"chat-example"
],
"created_at": 1794445200,
"updated_at": 1794445200,
"provider_origin": "external_provider"
}
],
"total": 1
}
}
HTTP 200。
Field |
Type |
Description |
|---|---|---|
|
integer |
0 on success. |
|
object |
Error responses¶
Errors and result confirmation distinguishes the two protocols. Parse omitted fields, SDK zero values, and empty HTTP responses separately. Confirm writes using the corresponding read operation.