Model Settings - Update APIs

This endpoint updates the settings of a model. You can configure Min/Max Replicas, Timeout and Concurrency Settings

POST /rest/model/settings/update/

Request

curl --location 'https://api.inferless.com/rest/model/settings/update/' \
--header 'Authorization: <workspace-token>' \
--header 'Content-Type: application/json' \
--data '{
    "model_id": "<model-id>",
    "data": {
        "min_replica": 0,
        "max_replica": 2,
        "scale_down_delay": 30,
        "inference_time": 120,
        "is_dedicated": false,
        "machine_type": "T4",
        "container_concurrency": 10,
        "is_input_output_enabled": false
    }
}'

Response

{
    "status": "success",
    "details": "Model updated successfully"
}

Authorizations

---

Authorization · string · required

Your workspace API token. You can find it in Workspace Settings

Body

---

model_id · string · required

The ID of the model whose settings you want to update.

data · object · required

The settings you want to update for the model.

Show properties

min_replica · integer

The minimum number of replicas for the model.

max_replica · integer

The maximum number of replicas for the model.

scale_down_delay · integer

The delay in seconds before scaling down the model.

inference_time · integer

The maximum time in seconds for the model to process an inference request.

is_dedicated · boolean

Whether the model uses a dedicated machine or a shared machine.

machine_type · string

The machine type for the model.

container_concurrency · integer

The number of concurrent requests the model can handle.

is_input_output_enabled · boolean

Whether the model supports input and output tracking.

Request

curl --location 'https://api.inferless.com/rest/model/settings/update/' \
--header 'Authorization: <workspace-token>' \
--header 'Content-Type: application/json' \
--data '{
    "model_id": "<model-id>",
    "data": {
        "min_replica": 0,
        "max_replica": 2,
        "scale_down_delay": 30,
        "inference_time": 120,
        "is_dedicated": false,
        "machine_type": "T4",
        "container_concurrency": 10,
        "is_input_output_enabled": false
    }
}'

Response

{
    "status": "success",
    "details": "Model updated successfully"
}