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

# List GPUs

> The public GPU catalog. Pass `serverless=true` for the SKUs offered for [Serverless GPU deployments](/guides/serverless-gpus/overview) — without the filter the response can also include rows that only price catalog models and cannot be deployed. No API key required.



## OpenAPI

````yaml /platform-openapi.json get /gpus
openapi: 3.1.0
info:
  title: ModelRunner Platform API
  version: 1.0.0
  description: >-
    Platform APIs: model catalog, search and collections; model pricing rate
    cards; the Serverless GPU catalog and deployment templates; file uploads and
    your asset library; account balance and usage; and webhook delivery
    management. Catalog reads are public; account-scoped routes authenticate
    with your API key (`Authorization: Key <MODELRUNNER_KEY>`). Request
    lifecycle endpoints (submit/status/result and the request list) live on the
    queue host — see the Queue API reference.
servers:
  - url: https://api.modelrunner.run
security: []
paths:
  /gpus:
    get:
      summary: List GPUs
      description: >-
        The public GPU catalog. Pass `serverless=true` for the SKUs offered for
        [Serverless GPU deployments](/guides/serverless-gpus/overview) — without
        the filter the response can also include rows that only price catalog
        models and cannot be deployed. No API key required.
      parameters:
        - name: serverless
          in: query
          schema:
            type: string
            enum:
              - 'true'
          description: Set to `true` to return only deployable serverless SKUs.
      responses:
        '200':
          description: GPU SKUs.
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/Gpu'
components:
  schemas:
    Gpu:
      type: object
      description: >-
        One GPU SKU. `pricePerSecond` is the sell rate for the whole SKU — a
        bundled SKU (`gpu` > 1) is already priced for every GPU it contains, so
        nothing multiplies it further.
      properties:
        id:
          type: string
          format: uuid
        key:
          type: string
          description: >-
            Stable SKU identifier, e.g. `gpu-a6000`. This is what a deployment
            is created against.
          examples:
            - gpu-a6000
        name:
          type: string
          examples:
            - A6000
        vram:
          type: number
          description: VRAM in GB.
        gpu:
          type: number
          description: How many GPUs the SKU bundles.
        pricePerSecond:
          type: number
          description: Sell rate per SKU-second. Multiply by 3600 for the hourly figure.
        availability:
          type:
            - string
            - 'null'
          enum:
            - none
            - low
            - medium
            - high
            - null
          description: >-
            Live capacity signal, refreshed hourly. `none` means no capacity for
            this SKU right now.
        serverlessEnabled:
          type: boolean
          description: True when the SKU can back a Serverless GPU deployment.

````