# Show HN: Find every AI model your code calls and warn before it's retired

> Source: <https://llmstatus.ai>
> Published: 2026-08-20 13:12:55+00:00

Run it in any repo. It finds the models your code calls and flags the ones that are deprecated or retiring, with the date and the replacement.

`mm`

.Installs the `mm`

command — a self-contained binary, no Node needed (60–120 MB, auto-detects your platform). Auto-updates in the background, signature-verified; `MM_NO_AUTO_UPDATE=1`

disables it.

`brew install randomartifact/tap/modelstatus-cli`

· `npm i -g @modelstatus/cli`

· try once with `npx @modelstatus/cli status`

Run `mm`

for the full terminal dashboard: it scans the current repo on launch, then you arrow through every model it calls, browse the registry, and see what's new — live.

Need it scriptable? `mm status`

lists every model the repo calls, soonest retirement first. `mm ci`

exits non-zero when something's on a clock — that's the one for pre-commit hooks and CI. No account.

Both pull the signed registry from `cdn.llmstatus.ai`

once, then run offline. No account. Anonymous usage counts only — `MM_NO_ANALYTICS=1`

turns them off.

`mm`

for the full dashboard.Type `mm`

to open it. Arrow through every model the repo calls, press `f`

to fix one with a diff preview, and watch the ●◐▲✕ counts update as you go. The **Here** and **What's New** tabs read straight off the signed registry, no account, works offline.

`/`

search.`mm fix`

swaps in the replacements.Finding dying models is half the job. One command rewrites them to the registry's replacement, in place.

`gpt-4`

can't rewrite inside `gpt-4o`

or `gpt-4-tuned`

.`--dry-run`

previews, `--json`

for tooling. In the TUI, press `f`

.The GitHub App does the same on pull requests: a failing check grows an **Open fix PR** button, and one click opens this — the diff in the body, the commit verified, re-checked green by the same scan.

Live from the registry — it refreshes every 6 hours from models.dev, OpenRouter, and provider APIs.

No AI provider ships a model-lifecycle feed. We do —
[open the radar](/radar) on your phone, or subscribe:
[RSS](/feed.xml) ·
[JSON](/feed.json) ·
[retirements only](/feed.xml?type=model_retired,model_deprecated)

Add a model-lifecycle check to every PR. Two options, and the difference is whether your source code leaves your runners.

Runs in your own CI; your source never leaves your runners, only model IDs go out. Inline PR annotations and a pass/fail gate.

One click, no workflow YAML or secrets to manage. We scan each PR on our servers (your code is sent to us; use the CI option if that's a dealbreaker) and post a Check Run plus a review comment. A button on the check opens a fix PR that swaps in the replacements.

Plans cover the cloud inventory and alerts. The CLI itself is always free.

A free account stores one project's inventory (up to 15 usages) and emails you before a model retires. Pro lifts the caps and adds Slack, Discord, SMS, webhooks, CI drift, and the API.

| Health | Model | Project | Env | Where used | Retires |
|---|---|---|---|---|---|
| ▲ Retiring soon | AMAmazon Nova Premier |
api-service | prod | workers/classify.py:88 | 2026-09-14in 25d |
| ✕ Retired | MFGPT-5.3 Chat |
rag-pipeline | prod | rag/legacy_index.py:12 | 2026-08-1010d ago |
| ◑ Deprecating | OAGPT-5 |
support-bot | prod | bot/agent/handler.ts:121 | 2026-12-11in 4mo |
| ● Healthy | ANClaude Opus 4.7 |
api-service | prod | services/answer.go:215 | 2027-04-16in 8mo |
| ● Healthy | AMGPT-5.5 |
rag-pipeline | prod | rag/extract.py:71 | — |