---
title: "Get a GPU type"
method: GET
path: "/v2/catalog/gpus/{id}"
tags: ["Catalog"]
---

# Get a GPU type

`GET /v2/catalog/gpus/{id}`

Returns a single GPU type with pricing. Availability details are included only when requested with include=AVAILABILITY.

## Query parameters

- `include` CatalogInclude[]
- `product` Product[]
- `count` integer
- `cloud` 'SECURE' | 'COMMUNITY' — GPU availability cloud filter.
- `minCudaVersion` string

## Response `200`

OK

- GpuType
  - `id` string, required — Individual GPU type identifier (use for pod creation)
  - `name` string, required
  - `pool` string, nullable, required — Serverless GPU pool ID (use for serverless endpoint creation). Null if GPU is not in a serverless pool.
  - `manufacturer` 'NVIDIA' | 'AMD' | 'UNKNOWN', required — Canonical GPU hardware manufacturer.
  - `memory` integer, required — VRAM in GB
  - `secure` boolean, required — Available on secure cloud
  - `community` boolean, required — Available on community cloud
  - `price` object, required
    - `secure` number, float, required
    - `community` number, float, required
  - `maxCount` object, required
    - `secure` integer, required
    - `community` integer, required
  - `availability` 'NONE' | 'LOW' | 'MEDIUM' | 'HIGH' — Catalog stock availability level.
  - `dataCenters` DataCenterAvailability[] — Per-datacenter GPU availability. Present only when requested with include=AVAILABILITY.
    - `id` string, required — Data center identifier.
    - `name` string, required — Human-readable data center name.
    - `availability` 'NONE' | 'LOW' | 'MEDIUM' | 'HIGH', required — Catalog stock availability level.

## Other responses

- `401` — Authentication failed because the bearer token is missing, malformed, expired, or invalid.
- `403` — The bearer token is valid, but it does not grant access to the requested resource or action.
- `404` — The requested resource was not found or is not accessible to the caller.
- `429` — The caller exceeded its per-user rate limit. The response identifies the window that was exceeded and how long to wait. The `RateLimit` and `RateLimit-Policy` headers (per the IETF ratelimit-headers draft) also accompany successful responses, so clients can track quota before a 429.
- `default` — Error

---

[API](https://skmtc.dev/runpod/apis/runpod-rest-api.md) · [All operations](https://skmtc.dev/runpod/apis/runpod-rest-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/runpod/runpod-rest-api/revisions/504cd0394ed6/schema)