Get an LLM backend (root endpoint)¶
Read configuration of the specified LLM backend.
GET https://api.moi.matrixorigin.cn/v5/llm/backends/{backend_id}
Before you call this API¶
BASE_URL uses the product API prefix https://api.moi.matrixorigin.cn/v5. For a dedicated deployment, use its corresponding product API address.
Configure identity, Workspace, and object permissions in the same environment.
Request¶
curl --request GET \
"$BASE_URL/llm/backends/$BACKEND_ID" \
--header "X-API-Key: $MOI_KEY" \
--header "X-Workspace-ID: $WORKSPACE_ID"
Parameter |
Location |
Type |
Required |
Description |
|---|---|---|---|---|
|
Header |
string |
Yes |
Workspace ID in the same environment. |
|
Path |
integer |
Yes |
Positive ID returned by an earlier read. |
Responses contain no credentials. LLM includes online endpoints only; Embedding can include both states. model_backend.read does not grant modification or model runtime permissions.
Successful response¶
{
"code": "OK",
"msg": "OK",
"data": {
"id": 12,
"name": "临时后端",
"type": "OPENAI",
"timeout_seconds": 120,
"models": [
"chat-example"
],
"created_at": 1794445200,
"updated_at": 1794445200,
"reasoning_control_protocol": "REASONING_CONTROL_NONE",
"endpoints": [
{
"id": 21,
"backend_id": 12,
"address": "https://provider.example.invalid/v1",
"status": "ONLINE",
"created_at": 1794445200,
"updated_at": 1794445200
}
]
}
}
HTTP 200。
Field |
Type |
Description |
|---|---|---|
|
string |
OK on success. |
|
string |
OK on success. |
|
object |
Error response¶
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.