Create an LLM backend through the root API

Save LLM backend configuration and get a new backend ID.

POST https://api.moi.matrixorigin.cn/v5/llm/backends

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 --request POST \
  "$BASE_URL/llm/backends" \
  --header "X-API-Key: $MOI_KEY" \
  --header "X-Workspace-ID: $WORKSPACE_ID" \
  --header "Content-Type: application/json" \
  --data-raw '{"name":"临时后端","type":"OPENAI","api_key":"provider-key-example","models":["chat-example"]}'

Parameter

Location

Type

Required

Description

X-Workspace-ID

Headers

string

Yes

Workspace ID in the same environment.

name

Body

string

Yes

Nonempty name after trimming whitespace.

type

Body

string

No

OPENAI/OLLAMA/VLLM/QIANWEN/DOUBAO/DEV_LLM/HTTP. Omission or invalid values use OPENAI. Embedding rejects DEV_LLM.

api_key

Body

string

Conditionally required

Required for OPENAI/QIANWEN/DOUBAO; separate from MOI_KEY.

models

Body

array (strings)

Yes

At least one valid model name.

timeout_seconds

Body

integer

No

Positive seconds. Omission or nonpositive values use 120.

reasoning_control_protocol

Body

string

No

LLM reasoning control protocol; defaults to NONE. Embedding does not use reasoning control.

address

Body

string

No

A nonempty Embedding address can also create an endpoint. This LLM creation action ignores the address; create endpoints separately.

Requires workspace model_backend.create. Save the returned id, then read details and endpoints. Configuration does not verify model connectivity or inference capabilities. Ordinary workspace-style creation does not automatically create endpoints. DEV adapters have special internal behavior and are not a production integration method.

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"
  }
}

HTTP 200。

Field

Type

Description

code

string

OK on success.

msg

string

OK on success.

data

object

Actual objects for this protocol.

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.

Last updated on