✓It Still Works
  • Home
  • Search
  • Discover
  • Catalogue
  • Categories
  • What changed
  • Developer repos
  • How we check
  • Coding and upskilling
  • Developer utilities
  • Draw and diagram
  • Everyday tools
  • Games and play
  • Images and photos
  • Music and audio
  • Save and convert media
  • Testin category
  • Writing and publishing
  • Cloudflare (4)
  • Vercel (3)
  • GitHub Pages (2)
  • Google Cloud (2)
  • nginx (self-hosted) (2)
  • Google (1)
  • Netlify (1)
712 checks loggedEvery listing, every sweepSign in
Theme
✓It Still Works
Sign in

Every listing is checked on a schedule. No numbers we cannot measure.

How we checkGraveyardSubmit something
  • Discover
  • Catalogue
  • Changes
  • Repos

I understood

route different kinds of request to different models automatically

Not what you meant?

  • switch model providers without changing application code
  • keep a service running when one model provider goes down
  • try several image models on the same prompt without separate accounts
  • generate a marketing image without deciding which model suits it

Tools(5)

route different kinds of request to different models automatically · route different kinds of work to different models · route coding-agent prompts to a cheaper model · pick up an agent session from a different machine

5 listings shown. Every result was live at its last check.

  1. Run Codex CLI and Claude Code against whichever model you want

    Why this one

    • route different kinds of request to different models automatically
    • use a cheaper model behind a coding CLI you already know
    • keep using Codex when the model you want is somewhere else

    On the record

    • Free
    • Your own API key

    Last checked 2 days ago

    Open↗
  2. Power intelligence and agentic memory for Hermes Agent

    Why this one

    • route different kinds of work to different models
    • install Hermes Agent skills and memory in one command

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗
  3. Sends each prompt to the cheapest model that can do the job

    Why this one

    • route coding-agent prompts to a cheaper model
    • cut LLM inference cost without changing tools

    On the record

    • Free tier
    • Needs an account

    Last checked 2 days ago

    Open↗
  4. Keeps coding agents running in real terminals after you close the laptop

    Why this one

    • pick up an agent session from a different machine
    • leave a long agent task running after shutting the laptop

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗
  5. A local multi-provider LLM proxy, model router and control plane for AI coding agents

    Why this one

    • route several coding agents through one local proxy
    • track provider cost and credential health on your machine

    On the record

    • Your own API key
    • No signup

    Last checked 2 days ago

    Open↗