---
title: "Deploy Rebalance Cancel"
method: POST
path: "/deploy/{deploy_id}/rebalance/cancel"
tags: ["Dedicated Models"]
---

# Deploy Rebalance Cancel

`POST /deploy/{deploy_id}/rebalance/cancel`

Stop an in-flight GPU pool rebalance; instances already moved stay, and
both deployments keep min/max instances fixed at their current counts.

## Path parameters

- `deploy_id` string, required

## Headers

- `xi-api-key` string, nullable
- `x-api-key` string, nullable

## Request body

- RebalanceCancelIn
  - `replace_id` string, nullable — Rebalance to cancel; defaults to the active one.

## Response `200`

Successful Response

- RebalanceCancelOut
  - `replace_id` string, required — Id of the cancelled rebalance.
  - `placed` integer, required — Target instances delivered before the cancel.
  - `count` integer, required — Target instances requested.

## Other responses

- `400` — Bad Request
- `401` — Unauthorized
- `404` — Not Found
- `409` — Conflict
- `422` — Validation Error

---

[API](https://skmtc.net/deepinfra/apis/deepinfra-api.md) · [All operations](https://skmtc.net/deepinfra/apis/deepinfra-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/deepinfra/deepinfra-api/versions/2df28210837a/schema)