---
title: "Add a LoRA adapter to an endpoint"
method: POST
path: "/endpoints/{endpointId}/adapters"
tags: ["Endpoints"]
---

# Add a LoRA adapter to an endpoint

`POST /endpoints/{endpointId}/adapters`

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.

## Request body

- object
  - `model_id` string, required — Combined identifier in format "endpoint_name:adapter_model_name".

## Response `200`

Adapter successfully bound to endpoint

- object
  - `model_id` string

## Other responses

- `400` — Bad Request — invalid model_id format, endpoint name mismatch, LoRA not enabled, incompatible base model, or adapter already bound
- `403` — Forbidden — adapter model not found or not owned
- `404` — Not Found — endpoint does not exist

---

[API](https://skmtc.net/together/apis/together-apis.md) · [All operations](https://skmtc.net/together/apis/together-apis/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/together/together-apis/revisions/1fab430e87d6/schema)