---
title: "Create a dedicated endpoint"
method: POST
path: "/endpoints"
tags: ["Endpoints"]
---

# Create a dedicated endpoint

`POST /endpoints`

Creates a new dedicated endpoint for serving models. The endpoint starts automatically after creation. You can deploy any supported model on hardware configurations that meet the model's requirements.

## Request body

- CreateEndpointRequest
  - `display_name` string — A human-readable name for the endpoint
  - `model` string, required — The model to deploy on this endpoint
  - `hardware` string, required — The hardware configuration to use for this endpoint
  - `autoscaling` Autoscaling, required — Configuration for automatic scaling of replicas based on demand.
    - `min_replicas` integer, required — The minimum number of replicas to maintain, even when there is no load
    - `max_replicas` integer, required — The maximum number of replicas to scale up to under load
  - `disable_prompt_cache` boolean — This parameter is deprecated and no longer has any effect.
  - `disable_speculative_decoding` boolean — Whether to disable speculative decoding for this endpoint
  - `state` 'STARTED' | 'STOPPED' — The desired state of the endpoint
  - `inactive_timeout` integer, nullable — The number of minutes of inactivity after which the endpoint stops automatically. Set to null, omit, or set to 0 to disable automatic timeout.
  - `availability_zone` string — Create the endpoint in a specified availability zone (e.g., us-central-4b)

## Response `200`

200

- DedicatedEndpoint — Details about a dedicated endpoint deployment
  - `object` 'endpoint', required — The object type, which is always `endpoint`.
  - `id` string, required — Unique identifier for the endpoint
  - `name` string, required — System name for the endpoint
  - `display_name` string, required — Human-readable name for the endpoint
  - `model` string, required — The model deployed on this endpoint
  - `hardware` string, required — The hardware configuration used for this endpoint
  - `type` 'dedicated', required — The type of endpoint
  - `owner` string, required — The owner of this endpoint
  - `state` 'PENDING' | 'STARTING' | 'STARTED' | 'STOPPING' | 'STOPPED' | 'ERROR', required — Current state of the endpoint
  - `autoscaling` Autoscaling, required — Configuration for automatic scaling of replicas based on demand.
    - `min_replicas` integer, required — The minimum number of replicas to maintain, even when there is no load
    - `max_replicas` integer, required — The maximum number of replicas to scale up to under load
  - `created_at` string, date-time, required — Timestamp when the endpoint was created

## Other responses

- `403` — Unauthorized
- `500` — Internal error

---

[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/468edbdc879c/schema)