---
title: "Scale Endpoint Replicas"
method: POST
path: "/endpoints/{endpoint_id}/scale"
tags: ["Endpoints"]
---

# Scale Endpoint Replicas

`POST /endpoints/{endpoint_id}/scale`

Scale the number of replicas for an active endpoint. Autoscaling must be disabled.

## Path parameters

- `endpoint_id` string, required

## Request body

- ScaleReplicasInput
  - `num_replicas` integer, required — Desired number of replicas (1-100).

## Response `200`

Scale result.

- ScaleReplicasResponse
  - `endpoint_id` string — Unique endpoint ID.
  - `previous_replicas` integer — Replica count before scaling.
  - `current_replicas` integer — Replica count after scaling.
  - `message` string — Result message.

## Other responses

- `400` — Endpoint is inactive or autoscaling is enabled.

---

[API](https://skmtc.net/aieev/apis/aircloud-external-api.md) · [All operations](https://skmtc.net/aieev/apis/aircloud-external-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/aieev/aircloud-external-api/versions/5cb76994bce9/schema)