ComputeGpu Gpu API

The Gpu API from ComputeGpu — 9 operation(s) for gpu.

Documentation GitHub OpenAPI

Operations 9

0 of 9 operations are conformant: apis.io called them with no credentials and the responses matched this contract; 1 more answered but could not be checked against a schema. Checked 2026-11-12. how this works · status file

GET /api/v1/gpu/types List the live GPU catalogue with current pricing (authoritative — do not cache… observed #

GET /api/v1/gpu/cheapest Find cheapest GPU for a VRAM requirement #

POST /api/v1/gpu/deploy Deploy an on-demand GPU instance #

GET /api/v1/gpu/pods List your active GPU instances #

PUT /api/v1/gpu/pods/{id}/stop Pause instance (billing pauses, volume kept) #

DELETE /api/v1/gpu/pods/{id} Destroy instance permanently. Returns final cost #

GET /api/v1/gpu/account Who am I: email, verified, balance, and the next step (verify | topup | null) #

POST /api/v1/gpu/account/resend-verify Email the account owner a fresh $0 card-verification link (valid 5 minutes) #

POST /api/v1/gpu/billing/request-topup Email account owner to add credits #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this

find_apisBrowse and filter every API in the catalog.
get_api_artifactsOne API's artifacts, grouped by type.
get_openapiThe primary OpenAPI for this API.
find_similar_apisAPIs that look like this one.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This API

curl "https://apis.io/api/v1/apis/computegpu-com:computegpu-com-gpu-api"

All apis

curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openapi: 3.2.0
info:
  title: Computegpu Com Gpu API
  version: 1.2.3
  description: 'Operations tagged Gpu across 2 of this provider''s published API definitions: computegpu-com-openapi.json, computegpu-com-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://computegpu.com
security:
- bearerAuth: []
tags:
- name: Gpu
paths:
  /api/v1/gpu/types:
    get:
      operationId: listGpuTypes
      summary: List the live GPU catalogue with current pricing (authoritative — do not cache…
      security: []
      responses:
        '200':
          description: Array of GPU types with pricePerHour, vramGb, spotPrice.
      tags:
      - Gpu
    servers:
    - url: https://computegpu.com
  /api/v1/gpu/cheapest:
    get:
      operationId: cheapestGpu
      summary: Find cheapest GPU for a VRAM requirement
      security: []
      parameters:
      - name: vram
        in: query
        required: true
        schema:
          type: integer
        description: Minimum VRAM in GB
      responses:
        '200':
          description: Cheapest GPU matching VRAM requirement.
      tags:
      - Gpu
    servers:
    - url: https://computegpu.com
  /api/v1/gpu/deploy:
    post:
      operationId: deployGpu
      summary: Deploy an on-demand GPU instance
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - gpuType
              properties:
                gpuType:
                  type: string
                  description: GPU model name (e.g. RTX 4090)
                gpuCount:
                  type: integer
                  default: 1
                models:
                  type: array
                  items:
                    type: string
                  description: Ollama models to preload
                instanceType:
                  type: string
                  enum:
                  - ollama
                  default: ollama
                  description: Access mode for the instance.
                volumeGb:
                  type: integer
                  description: Persistent volume size in GB
      responses:
        '201':
          description: Instance deploying. Returns pod object with id, status, pricePerHour.
        '402':
          description: Insufficient credits. Response includes balance, required amount, and requestTopup endpoint.
        '422':
          description: GPU type not available.
      tags:
      - Gpu
    servers:
    - url: https://computegpu.com
  /api/v1/gpu/pods:
    get:
      operationId: listPods
      summary: List your active GPU instances
      responses:
        '200':
          description: Array of active pods with status, cost, billing info.
      tags:
      - Gpu
    servers:
    - url: https://computegpu.com
  /api/v1/gpu/pods/{id}/stop:
    put:
      operationId: stopPod
      summary: Pause instance (billing pauses, volume kept)
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Instance paused.
      tags:
      - Gpu
    servers:
    - url: https://computegpu.com
  /api/v1/gpu/pods/{id}:
    delete:
      operationId: destroyPod
      summary: Destroy instance permanently. Returns final cost
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Instance destroyed. Final cost returned.
      tags:
      - Gpu
    servers:
    - url: https://computegpu.com
  /api/v1/gpu/account:
    get:
      operationId: getAccount
      summary: 'Who am I: email, verified, balance, and the next step (verify | topup | null)'
      responses:
        '200':
          description: Account state for this API key.
      tags:
      - Gpu
    servers:
    - url: https://computegpu.com
  /api/v1/gpu/account/resend-verify:
    post:
      operationId: resendVerify
      summary: Email the account owner a fresh $0 card-verification link (valid 5 minutes)
      responses:
        '200':
          description: Link sent, or already verified.
      tags:
      - Gpu
    servers:
    - url: https://computegpu.com
  /api/v1/gpu/billing/request-topup:
    post:
      operationId: requestTopup
      summary: Email account owner to add credits
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                amount:
                  type: number
                  default: 1
                  minimum: 1
                  description: Requested top-up amount in USD (always emailed to the account owner)
                reason:
                  type: string
                  description: Why credits are needed
      responses:
        '200':
          description: Email sent to account owner.
      tags:
      - Gpu
    servers:
    - url: https://computegpu.com
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: GPU API key. Get one via POST /api/signup.
x-refined-from:
- computegpu-com-openapi.json
- computegpu-com-openapi.yml