---
title: "Scale Deployment to a specific number of replicas or to zero"
method: PATCH
path: "/v1/accounts/{account_id}/deployments/{deployment_id}:scale"
tags: ["Gateway"]
---

# Scale Deployment to a specific number of replicas or to zero

`PATCH /v1/accounts/{account_id}/deployments/{deployment_id}:scale`

## Request

- Base URL: `https://api.fireworks.ai/inference`
- URL: `https://api.fireworks.ai/inference/v1/accounts/{account_id}/deployments/{deployment_id}:scale`
- Auth: HTTP bearer
- TypeScript: <https://skmtc.dev/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api/docs/v1/accounts/:account_id/deployments/:deployment_id:scale/patch.ts> (a function with typed inputs; its response is checked against the schema)

## Path parameters

- `account_id` string, required
- `deployment_id` string, required

## Request body

- GatewayGatewayScaleDeploymentBody
  - `replicaCount` integer: The desired number of replicas.

## Response `200`

A successful response.

- object

---

[API](https://skmtc.dev/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api.md) - [All operations](https://skmtc.dev/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api/llms.txt) - [OpenAPI document](https://skmtc.dev/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api/revisions/954d6bc5d922?raw)