> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aireserve.com/llms.txt
> Use this file to discover all available pages before exploring further.

# List GPU types

> Returns available GPU models, per-data-center availability, and current list prices for the Secure Cloud on-demand pool. Browsing the catalog does not reserve capacity — availability and pricing are rechecked at quote time. Results may be cached server-side for up to 15 minutes.



## OpenAPI

````yaml /api-reference/openapi.json get /v1/gpu/catalog/gpus
openapi: 3.0.3
info:
  title: AI Reserve Gateway API
  description: >-
    The AI Reserve API surface — OpenAI-compatible chat completions,
    Anthropic-compatible messages, Bedrock Converse, images, video, files,
    text-to-speech, realtime voice sessions, and GPU Compute pod/volume
    management — all behind one endpoint and one API key.
  version: 1.0.0
servers:
  - url: https://api.aireserve.com
security:
  - bearerAuth: []
paths:
  /v1/gpu/catalog/gpus:
    get:
      tags:
        - GPU Compute
      summary: List GPU types
      description: >-
        Returns available GPU models, per-data-center availability, and current
        list prices for the Secure Cloud on-demand pool. Browsing the catalog
        does not reserve capacity — availability and pricing are rechecked at
        quote time. Results may be cached server-side for up to 15 minutes.
      responses:
        '200':
          description: GPU catalog.
          content:
            application/json:
              schema:
                type: object
                properties:
                  data:
                    type: array
                    items:
                      $ref: '#/components/schemas/ComputeGpuType'
components:
  schemas:
    ComputeGpuType:
      type: object
      description: >-
        A GPU type available in the RunPod Secure Cloud on-demand pool.
        Availability is rechecked at pod creation time — catalog browsing does
        not reserve capacity.
      required:
        - id
        - displayName
        - memoryGb
      properties:
        id:
          type: string
          description: >-
            GPU type identifier to pass in pod create requests (e.g.
            `NVIDIA_A40`).
        displayName:
          type: string
          description: Human-readable GPU name.
        memoryGb:
          type: integer
          description: VRAM in GiB.
        maxCount:
          type: integer
          description: Maximum number of GPUs allocatable per pod for this type.
        securePriceUsdPerHour:
          type: number
          description: >-
            List GPU price per GPU per hour in USD. Storage is billed
            separately. Price is rechecked at quote time.
        dataCenterAvailability:
          type: array
          items:
            type: object
            properties:
              dataCenterId:
                type: string
              availability:
                type: string
                enum:
                  - NONE
                  - LOW
                  - MEDIUM
                  - HIGH
          description: Per-data-center availability for this GPU type.
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Your AI Reserve API key (aireserve_api_…) from the API Keys page in the
        portal (https://portal.aireserve.com/keys).

````