---
title: "List GPU models"
method: GET
path: "/sandboxes/gpus"
tags: ["Sandboxes"]
---

# List GPU models

`GET /sandboxes/gpus`

## Request

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

Every GPU model your workspace can run, at its price after your
discount. 404 while sandboxes are not enabled for your workspace.

## Response `200`

Successful Response

- SandboxGpuListResponse
  - `data` SandboxGpu[], required: Every GPU model you can run.
    - `gpu_model` string, required: The GPU model, as `accelerator` names it (`h100`).
    - `gpu_memory_gb` integer, required: Memory per GPU, in GB.
    - `usd_per_gpu_hour` number, required: One GPU-hour at your workspace's price, after its discount.
    - `available` boolean, nullable: Whether one more sandbox of this model fits in the GPUs free right now, by the recorded size of the pools that serve it, shared with other workspaces; null when that is unknown. `false` means a new sandbox may wait for GPUs to free up. `true` does not promise an immediate start: the sandbox is placed in one pool, a machine may be out of service, a request for several GPUs may need more than are free or than one machine holds, and sandboxes already waiting take free GPUs first.
  - `next_cursor` string, nullable, required: Opaque cursor for the next page, or null when this response completes the list. Always present. Endpoints that serve the whole collection at once always return null.

## 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.
- `503`: Sandboxes are temporarily unavailable, or are still being set up for your workspace; retry shortly.

## Changes

- **2026-11-04** `6ef35a11cefe`: 1 info
  - added the optional property `data/items/available` to the response with the `200` status
- **2026-10-23** `e733493214f4`: 1 info
  - endpoint added

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