Set LLM endpoint status through the workspace API¶
Set the specified LLM endpoint online or offline.
PUT https://api.moi.matrixorigin.cn/v5/workspaces/{workspace_id}/llm/backends/{backend_id}/endpoints/{endpoint_id}/status
Before you call this API¶
Set BASE_URL to the product API prefix https://api.moi.matrixorigin.cn/v5; use the corresponding product API URL for a dedicated deployment.
Configure identity, workspace, and object permissions in the same environment.
Request¶
curl --include --request PUT \
"$BASE_URL/workspaces/$WORKSPACE_ID/llm/backends/$BACKEND_ID/endpoints/$ENDPOINT_ID/status" \
--header "X-API-Key: $MOI_KEY" \
--header "X-Workspace-ID: $WORKSPACE_ID" \
--header "Content-Type: application/json" \
--data-raw '{"status":1}'
Parameter |
Location |
Type |
Required |
Description |
|---|---|---|---|---|
|
Headers |
string |
Yes |
Workspace ID in the same environment. |
|
Path |
string |
Yes |
Workspace ID in the same environment. |
|
Path |
integer |
Yes |
Positive ID returned by a preceding read. |
|
Path |
integer |
Yes |
Positive ID returned by a preceding read. |
|
Body |
integer |
No |
0 online, 1 offline. Omission/null use 0; other integers rejected. |
Requires backend update permission. Path backend_id/endpoint_id selects the target; duplicate IDs in the body do not override the path. The Embedding DAO may treat zero matches as success; reread to confirm.
Successful response¶
HTTP/1.1 204 No Content
HTTP 204。
HTTP 204 has no response body.
Error responses¶
Errors and result confirmation distinguishes the two protocols. Parse omitted fields, SDK zero values, and empty HTTP responses separately. Confirm writes with the corresponding reads.