Endpoints

Remove a LoRA adapter from an endpoint

Removes the routing rule that binds an adapter to an endpoint. The adapter must be currently bound to this specific endpoint.

Authorization

bearerAuth

AuthorizationBearer <token>

In: header

Path Parameters

endpointId*string

The endpoint ID

Request Body

application/json

model_id*string

Combined identifier in format "endpoint_name:adapter_model_name".

Response Body

`application/json`

`application/json`

`application/json`

`application/json`

curl -X DELETE "https://example.com/endpoints/string/adapters" \  -H "Content-Type: application/json" \  -d '{    "model_id": "string"  }'

{  "model_id": "string",  "deleted": true}

Add a LoRA adapter to an endpoint POST

Adds a LoRA adapter model to a dedicated endpoint. After this call, inference requests to the adapter model name will be routed to the specified endpoint. The endpoint must have LoRA enabled, and the adapter's base model must be compatible with the endpoint's model. The endpoint name prefix in model_id must match the resolved endpoint.

List available hardware configurations GET

Returns a list of available hardware configurations for deploying models. When a model parameter is provided, it returns only hardware configurations compatible with that model, including their current availability status.