Get a GPU type

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

GET /v2/catalog/gpus/{id}

Error

A valid request URL is required to generate request examples

200

{
  "id": "NVIDIA GeForce RTX 4090",
  "name": "RTX 4090",
  "pool": "ADA_24",
  "manufacturer": "NVIDIA",
  "memory": 24,
  "secure": true,
  "community": true,
  "price": {
    "secure": 0.44,
    "community": 0.31
  },
  "maxCount": {
    "secure": 8,
    "community": 4
  },
  "dataCenters": [
    {
      "id": "US-CA-2",
      "name": "US California 2"
    }
  ]
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

id · string · required

Query Parameters

include · enum<string>[]

Comma-separated optional expansions. Supported value today: AVAILABILITY. This may expand with more include values in the future.

Maximum array length: 1

Catalog include expansion. Only AVAILABILITY is supported today; additional include values may be added in the future.

Available options: AVAILABILITY

product · enum<string>[]

Comma-separated availability product contexts. Supported values: POD, CLUSTER, SERVERLESS. Valid only with include=AVAILABILITY. Upstream default when omitted: POD.

Catalog product availability context.

Available options: POD, CLUSTER, SERVERLESS

count · integer · default: 1

GPU count for availability and lowest-price calculations. Valid only with include=AVAILABILITY. Defaults to 1.

Required range: x >= 1

cloud · enum<string>

Cloud type for availability and lowest-price calculations. Valid only with include=AVAILABILITY. Supported values: SECURE, COMMUNITY. Upstream default when omitted: SECURE. GPU availability cloud filter.

Available options: SECURE, COMMUNITY

minCudaVersion · string

Minimum CUDA version for availability and lowest-price calculations. Valid only with include=AVAILABILITY. Format: integer major or major.minor, e.g. 12 or 12.1.

Response

200

application/json

OK

id · string · required

Individual GPU type identifier (use for pod creation)

Example:

"NVIDIA GeForce RTX 4090"

name · string · required

Example:

"RTX 4090"

pool · string | null · required

Serverless GPU pool ID (use for serverless endpoint creation). Null if GPU is not in a serverless pool.

Example:

"ADA_24"

manufacturer · string · required

Example:

"NVIDIA"

memory · integer · required

VRAM in GB

Example:

24

secure · boolean · required

Available on secure cloud

Example:

true

community · boolean · required

Available on community cloud

Example:

true

price · object · required

Show child attributes

maxCount · object · required

Show child attributes

availability · enum<string>

Overall GPU availability. Present only when requested with include=AVAILABILITY.

Available options: NONE, LOW, MEDIUM, HIGH

dataCenters · object[]

Per-datacenter GPU availability. Present only when requested with include=AVAILABILITY.

Show child attributes