Hundredth Run

Hundredth Run GPU prices API

The GPU prices API from Hundredth Run — 3 operation(s) for gpu prices.

GitHub OpenAPI

Operations 3

GET /api/v1/prices.json Every price row #
GET /api/v1/gpus.json One summary per GPU #
GET /api/v1/models.json Model memory estimates #

Specifications

⚙
OpenAPI
https://artifacts.apis.io/hundredthrun/openapi/hundredthrun-gpu-prices-api-openapi.yml

Schemas & Data

📊
JSONSchema
https://artifacts.apis.io/hundredthrun/json-schema/hundredthrun-price-row-schema.json
📊
JSONSchema
https://artifacts.apis.io/hundredthrun/json-schema/hundredthrun-gpu-summary-schema.json
📊
JSONSchema
https://artifacts.apis.io/hundredthrun/json-schema/hundredthrun-model-estimate-schema.json

Other Resources

🔗
APIsJSON
https://artifacts.apis.io/hundredthrun/apis.yml

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/hundredthrun:hundredthrun-gpu-prices-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

hundredthrun-gpu-prices-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Hundredth Run GPU prices API
  version: 1.0.0
  description: Free, keyless JSON API of public cloud GPU rental prices (US dollars per GPU-hour) from 25+ providers. Every row keeps its source URL and the date it was read. Static files, CORS open, refreshed about weekly.
  license:
    name: CC BY 4.0
    url: https://creativecommons.org/licenses/by/4.0/
  contact:
    name: Hundredth Run
    url: https://hundredthrun-compute-desk.pages.dev/open-data
  x-logo:
    url: https://hundredthrun-compute-desk.pages.dev/apple-touch-icon.png
servers:
- url: https://hundredthrun-compute-desk.pages.dev
tags:
- name: GPU prices
paths:
  /api/v1/prices.json:
    get:
      operationId: listPrices
      summary: Every price row
      description: All providers and price types (on-demand, spot, reserved) with source URL, date checked and confidence.
      tags:
      - GPU prices
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                properties:
                  license:
                    type: string
                  attribution:
                    type: string
                  units:
                    type: string
                  name:
                    type: string
                  generated_from:
                    type: string
                  date_checked_latest:
                    type: string
                  count:
                    type: integer
                  rows:
                    type: array
                    items:
                      $ref: '#/components/schemas/PriceRow'
  /api/v1/gpus.json:
    get:
      operationId: listGpus
      summary: One summary per GPU
      description: Lowest, median and priciest public on-demand price, provider count and the cheapest listing for each GPU.
      tags:
      - GPU prices
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                properties:
                  license:
                    type: string
                  attribution:
                    type: string
                  units:
                    type: string
                  gpus:
                    type: array
                    items:
                      $ref: '#/components/schemas/GpuSummary'
  /api/v1/models.json:
    get:
      operationId: listModels
      summary: Model memory estimates
      description: Estimated VRAM by precision and fine-tune mode for popular open models.
      tags:
      - GPU prices
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                properties:
                  license:
                    type: string
                  attribution:
                    type: string
                  overhead:
                    type: number
                  method:
                    type: string
                  models:
                    type: array
                    items:
                      $ref: '#/components/schemas/ModelEstimate'
components:
  schemas:
    ModelEstimate:
      type: object
      properties:
        slug:
          type: string
        name:
          type: string
        params_b:
          type: number
          description: Parameters in billions.
        architecture:
          type: string
        source_url:
          type: string
        date_checked:
          type: string
        vram_gb:
          type: object
          additionalProperties:
            type: number
          description: 'Estimated VRAM GB by mode: fp16, fp8, int4, lora, qlora, full.'
    PriceRow:
      type: object
      properties:
        provider:
          type: string
        gpu:
          type: string
        variant:
          type: string
        gpus_per_unit:
          type: string
        price_type:
          type: string
        term:
          type: string
        region:
          type: string
        billing_unit:
          type: string
        price_as_listed:
          type: string
        derivation:
          type: string
        availability_note:
          type: string
        lead_time_class:
          type: string
        source_url:
          type: string
          description: Page the price was read from.
        date_checked:
          type: string
          description: Date the price was read, YYYY-MM-DD.
        fetch_method:
          type: string
        confidence:
          type: string
        notes:
          type: string
        price_usd_per_gpu_hr:
          type:
          - number
          - 'null'
          description: US dollars per GPU-hour. Null when the provider publishes no price.
    GpuSummary:
      type: object
      properties:
        gpu:
          type: string
        slug:
          type: string
        vram_gb:
          type:
          - number
          - 'null'
        rows:
          type: integer
        on_demand:
          type:
          - object
          - 'null'
          properties:
            min:
              type: number
            median:
              type: number
            max:
              type: number
            n:
              type: integer
            providers:
              type: integer
        cheapest:
          type:
          - object
          - 'null'
          properties:
            provider:
              type: string
            variant:
              type: string
            price_usd_per_gpu_hr:
              type: number
            source_url:
              type: string
        page:
          type:
          - string
          - 'null'
          description: Price page on this site.
        last_checked:
          type: string
externalDocs:
  description: Docs and examples
  url: https://hundredthrun-compute-desk.pages.dev/open-data