---
title: "Get the GPUs left in your quota"
method: GET
path: "/sandboxes/quota"
tags: ["Sandboxes"]
---

# Get the GPUs left in your quota

`GET /sandboxes/quota`

## Request

- Base URL: `https://api.hedra.com/v3`
- URL: `https://api.hedra.com/v3/sandboxes/quota`
- Auth: one of:
  - API key in header `Authorization`
  - HTTP bearer

How many more GPUs your workspace's sandboxes can hold under its GPU
quota. 404 while sandboxes are not enabled for your workspace.

## Response `200`

Successful Response

- SandboxQuota: How much of your workspace's GPU quota is left.
  - `gpu_quota_remaining` integer, required: GPUs left under your workspace's GPU quota: the quota less the GPUs its `creating`, `active` and `stopping` sandboxes were created with, every member's included. A create can still answer 429 with GPUs left, because your workspace's sandbox quota also limits its running instances, every replica counted. A sandbox counts at its full `replicas` until Hedra records it ended: usually a minute or two after a stop or the end of `ttl_seconds`, about 15 minutes after its last replica exits on its own, and for as long as any replica still runs.

## Other responses

- `400`: Invalid or failed-validation request.
- `401`: Authentication failed: missing, malformed, or invalid credentials.
- `403`: Insufficient scope or plan.
- `404`: Resource not found.
- `429`: Rate limit exceeded.
- `500`: Internal error.

## Changes

- **2026-11-04** `6ef35a11cefe`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/hedra-labs/apis/hedra-api/changes/sandboxes/quota/get.md)

---

[API](https://skmtc.dev/hedra-labs/apis/hedra-api.md) - [All operations](https://skmtc.dev/hedra-labs/apis/hedra-api/llms.txt) - [OpenAPI document](https://skmtc.dev/hedra-labs/apis/hedra-api/revisions/6ef35a11cefe?raw)