Skip to Content
Overview

LLM Status Docs

Track every AI model your code uses. Find out before any of them retire. Migrate cleanly when they do.

Install in one line, no account needed:

$curl -fsSL https://llmstatus.ai/install.sh | bash

Installs a self-contained binary (~60 MB, no Node required) into /usr/local/bin/mm. Detects arm64 vs x64.

After install you get two binaries — mm (short) and llmstatus (descriptive). Same binary, pick whichever you like to type.

What you’ll do next

  1. Run a free health check — mm status in any repo. No sign-in required.
  2. Sign in for cloud features — mm login opens a browser tab.
  3. Scan + map a project — finds every model call across your code, lets you pick what to track.
  4. Set up alerts — email / Slack / SMS warnings before any of your models retire.
  5. Drop it into CI — fail builds when someone pins a deprecated model.

Or jump straight to the command reference if you’d rather see everything at once.

Why this exists

Providers retire models faster than most teams notice — sometimes weeks, sometimes overnight. LLM Status is the inventory + lifecycle layer: it scans your repo for every model id (OpenAI, Anthropic, Google, Mistral, DeepSeek, xAI, Moonshot, Cohere, and dozens more), joins them to a constantly-updated lifecycle registry, and warns you before a retirement breaks production.

The registry is a date-versioned, signed snapshot published to a CDN — your scans run on-device, fully offline-capable after the first fetch, and never upload secrets.

Install