Lium Public launch statistics API

The Public launch statistics API from Lium — 1 operation(s) for public launch statistics.

GitHub OpenAPI

Operations 1

GET /public/v1/launch-stats Launch success rate and time to SSH per GPU type #

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/lium-io:lium-io-public-launch-statistics-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. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.

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

OpenAPI Specification

lium-io-public-launch-statistics-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Lium Backend Public launch statistics API
  description: '## 🚀 Lium Backend API


    A comprehensive compute platform that enables users to rent GPU resources from a network of providers/nodes.


    *Built with FastAPI, PostgreSQL and Redis.*'
  contact:
    name: Lium
    url: https://lium.io/
    email: support@lium.io
  license:
    name: MIT
    url: https://opensource.org/licenses/MIT
  version: 1.0.0
servers:
- url: /api
  description: Production API
tags:
- name: Public launch statistics
paths:
  /public/v1/launch-stats:
    get:
      tags:
      - Public launch statistics
      summary: Launch success rate and time to SSH per GPU type
      description: 'For every GPU type and GPU count with at least `min_launches` launches on at least `min_providers` providers in the last `window_days` days: the share of launches that reached RUNNING, and the median and 90th percentile seconds from the rent request to RUNNING. Recomputed from production data every 15 minutes. No authentication. Fields are only ever added; a breaking change ships as /public/v2.'
      operationId: launch_stats_public_v1_launch_stats_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/LaunchStatsResponse'
components:
  schemas:
    LaunchStatsResponse:
      properties:
        generated_at:
          type: string
          format: date-time
          title: Generated At
        window_days:
          type: integer
          title: Window Days
        min_launches:
          type: integer
          title: Min Launches
          description: A GPU type and count with fewer launches in the window is left out.
        min_providers:
          type: integer
          title: Min Providers
          description: A GPU type and count launched on fewer providers in the window is left out.
        methodology_url:
          type: string
          title: Methodology Url
        gpus:
          items:
            $ref: '#/components/schemas/GpuLaunchStats'
          type: array
          title: Gpus
      type: object
      required:
      - generated_at
      - window_days
      - min_launches
      - min_providers
      - methodology_url
      - gpus
      title: LaunchStatsResponse
    GpuLaunchStats:
      properties:
        gpu_type:
          type: string
          title: Gpu Type
          description: The GPU model as the node reports it, e.g. NVIDIA H100 80GB HBM3.
        gpu_count:
          type: integer
          title: Gpu Count
          description: GPUs per pod.
        success_rate:
          type: number
          title: Success Rate
          description: Share of launches in the window that reached RUNNING, 0 to 1.
        time_to_ssh_p50_seconds:
          anyOf:
          - type: number
          - type: 'null'
          title: Time To Ssh P50 Seconds
          description: Median seconds from the rent request to RUNNING.
        time_to_ssh_p90_seconds:
          anyOf:
          - type: number
          - type: 'null'
          title: Time To Ssh P90 Seconds
          description: 90th percentile of the same; null when none succeeded.
      type: object
      required:
      - gpu_type
      - gpu_count
      - success_rate
      - time_to_ssh_p50_seconds
      - time_to_ssh_p90_seconds
      title: GpuLaunchStats
  securitySchemes:
    JwtAccessBearer:
      type: http
      scheme: bearer
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key