---
title: "Public GPU availability"
method: GET
path: "/v1/availability"
tags: ["GPU Plans"]
---

# Public GPU availability

`GET /v1/availability`

## Request

- Base URL: `https://gpucloud.ca/api`
- URL: `https://gpucloud.ca/api/v1/availability`
- Auth: none required

PUBLIC, no authentication. Aggregated availability per GPU model and machine size (available true / false), refreshed at most every 15 seconds (Cache-Control: max-age=15). Rate limited to 60 requests per minute per IP. No prices: see /v1/gpu or https://gpucloud.ca/llms.txt.

## Response `200`

Availability per model and size

- object
  - `data` PublicAvailability: Aggregated availability of the GPU catalog: per GPU model and machine size, only whether it can be deployed online right now.
    - `region` string, required
    - `updatedAt` string, date-time, required
    - `models` object[], required
      - `slug` string, required: Model page: https://gpucloud.ca/{fr|en}/gpu/{slug}
      - `name` string, required
      - `sizes` object[], required
        - `id` string, required: Catalog product id (as in /v1/gpu and POST /servers).
        - `gpuCount` integer, required
        - `spot` boolean, required: Interruptible machine, hourly billing only.
        - `available` boolean, required: Deployable online right now.
        - `priceOnRequest` boolean, required: Sold on request only (never deployable online).

## Other responses

- `429`: Rate limit exceeded
- `500`: Internal server error

---

[API](https://skmtc.dev/gpucloud/apis/gpu-cloud-api.md) · [All operations](https://skmtc.dev/gpucloud/apis/gpu-cloud-api/llms.txt) · [OpenAPI document](https://skmtc.dev/gpucloud/apis/gpu-cloud-api/revisions/ed530411f5c7?raw)