API referenceList prices

GET

List prices

GEThttps://api.gpus.io/v1/prices

Returns the current price for every GPU offering — one row per provider · configuration. This is the core feed behind the GPUs.io comparison table.

Request

curl -G https://api.gpus.io/v1/prices \
  -H "Authorization: Bearer $GPUS_API_KEY" \
  --data-urlencode gpu=h100-sxm \
  --data-urlencode rentalType=on_demand \
  --data-urlencode limit=2

Parameters

Query parameters

gpustringOptional

Filter by GPU type. Accepts a key from List GPU types, e.g. h100-sxm.

providerstringOptional

Filter by provider id from List providers.

rentalTypeenumOptional

Pricing model to return.

on_demandspotreserved

regionstringOptional

Restrict to a single region — an ISO 3166-1 alpha-2 country code, e.g. us.

minVramintegerOptional

Minimum per-GPU VRAM in GB.

minPricenumberOptional

Lower bound on pricePerGpuHourUsd (USD).

maxPricenumberOptional

Upper bound on pricePerGpuHourUsd (USD). Must be ≥ minPrice.

limitintegerOptionaldefault: 50

Rows per page. Default 50, maximum 200.

cursorstringOptional

Pagination cursor from pagination.nextCursor of a previous response. See Pagination & errors.

Response

A successful call returns 200 OK with this shape:

Example response

{
  "data": [
    {
      "gpu": {
        "key": "h100-sxm",
        "name": "NVIDIA H100 SXM",
        "vramGb": 80
      },
      "provider": {
        "id": "lambda",
        "name": "Lambda",
        "website": "https://lambdalabs.com"
      },
      "rentalType": "on_demand",
      "commitmentTermMonths": null,
      "gpuCount": 8,
      "pricePerGpuHourUsd": 1.99,
      "totalPricePerHourUsd": 15.92,
      "specs": {
        "vcpu": 208,
        "ramGb": 1800,
        "bootDiskGb": 1024,
        "scratchDiskGb": 22000
      },
      "regions": [
        "us"
      ],
      "available": true,
      "lastUpdated": "2026-06-03T08:12:04Z"
    },
    {
      "gpu": {
        "key": "h100-sxm",
        "name": "NVIDIA H100 SXM",
        "vramGb": 80
      },
      "provider": {
        "id": "runpod",
        "name": "RunPod",
        "website": "https://runpod.io"
      },
      "rentalType": "on_demand",
      "commitmentTermMonths": null,
      "gpuCount": 1,
      "pricePerGpuHourUsd": 2.49,
      "totalPricePerHourUsd": 2.49,
      "specs": {
        "vcpu": 24,
        "ramGb": 125,
        "bootDiskGb": 80,
        "scratchDiskGb": 1024
      },
      "regions": [
        "us",
        "nl"
      ],
      "available": true,
      "lastUpdated": "2026-06-03T08:12:04Z"
    }
  ],
  "pagination": {
    "nextCursor": "eyJpZCI6MTQ4Mn0",
    "limit": 2
  }
}

Response fields

gpu.keystring

GPU type key. Join against List GPU types.

gpu.namestring

Human-readable GPU display name.

gpu.vramGbnumber

Per-GPU VRAM in GB.

provider.idstring

Provider id. Join against List providers.

provider.namestring

Provider display name.

provider.websitestring

Provider's public website.

rentalTypeenum

One of on_demand, spot, reserved.

commitmentTermMonthsinteger | null

Commitment length for reserved pricing, otherwise null.

gpuCountinteger

GPUs in this configuration.

pricePerGpuHourUsdnumber

List price per GPU, per hour, in USD.

totalPricePerHourUsdnumber

Total for the whole configuration (pricePerGpuHourUsd × gpuCount).

specs.vcpuinteger | null

vCPUs included, when known.

specs.ramGbinteger | null

System RAM in GB, when known.

specs.bootDiskGbinteger | null

Boot disk in GB, when known.

specs.scratchDiskGbinteger | null

Local scratch disk in GB, when known.

regionsstring[]

ISO 3166-1 alpha-2 country codes the offering is available in (e.g. us, de).

availableboolean

Whether capacity is currently bookable.

lastUpdatedstring

ISO 8601 timestamp of the last price refresh.

pagination.nextCursorstring | null

Cursor for the next page; null on the last page.

pagination.limitinteger

The page size applied to this response.

Main site Access Support