Stalemodel

io.github.GillMacedoPublished by GitHub account GillMacedov0.1.1Updated Nov 3, 2026

Catch outdated AI model names, and look up current models, prices and limits.

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

Checks AI model IDs in code against a live catalog, flags deprecated or missing ones, and lists current models with prices and context limits.

What you can do
  • Check model IDs and get a status plus a suggested newer model in the same family
  • List current models by provider, price, context size or tool support, newest first
  • Scan a file or directory for quoted model IDs that are deprecated or missing, returning locations only
When to use it
Useful when a coding agent writes model IDs from training data and you want to catch outdated OpenAI, Claude, Gemini, Grok, DeepSeek or Mistral names before they ship, or when you need current pricing and context limits for choosing a model.
Requirements
Runs as a local stdio process from the npm package stalemodel, requiring Node 22.19 or newer. No API key or account is needed. It fetches catalog data from models.dev and falls back to a bundled snapshot when offline.
Before you install
All three tools are read-only and no code is sent anywhere, though catalog data is fetched from models.dev. Suggestions are based on family and release date, so verify price and behavior before switching. Scan only sees quoted IDs and misses IDs built at runtime.

Installation

In SourceWeft

  1. Open Stalemodel in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

stalemodel: find deprecated AI model names in your code

[npm] [CI] [MIT license] [MCP Registry]

Catch outdated OpenAI, Claude and Gemini model IDs before your coding agent ships them, and look up current LLM prices and context limits.

Coding agents write model IDs from old training data, so new code often calls models that are deprecated or gone, and fails with errors like "model not found". stalemodel checks IDs against a live catalog, suggests the newest model in the same family, and gives agents current LLM pricing and limits. It's an MCP server and a CLI. It needs no API key or account, sends no code anywhere, and falls back to a bundled snapshot when offline.

It covers Anthropic Claude, OpenAI GPT, Google Gemini, xAI Grok, DeepSeek and Mistral.

What you can ask your agent

  • "Which Claude model ID should I use, and what does it cost?"
  • "Why do I get 'model not found' for claude-3-5-sonnet-20241022?"
  • "Check this repo for deprecated model names."
  • "What's the cheapest current model with tool calling and a 1M context window?"

Install

As a Claude Code plugin, which adds the MCP server and a skill that tells Claude when to use it:

claude plugin marketplace add GillMacedo/stalemodelclaude plugin install stalemodel@stalemodel-marketplace

For other MCP clients, run it from npm. You need Node 22.19 or newer. It's also in the official MCP Registry as io.github.GillMacedo/stalemodel.

json
{  "mcpServers": {    "stalemodel": {      "command": "npx",      "args": ["-y", "stalemodel", "serve"]    }  }}

Usage

Without installing anything, run npx stalemodel scan .. The examples below run from a clone of this repo.

Scan a project. Only quoted strings count, and scan exits 1 on findings, so it can run in CI.

$ node plugin/dist/stalemodel.js scan examplesexamples/app.py:2  claude-3-5-sonnet-20241022  not in catalog  try claude-sonnet-5-5examples/app.py:3  gpt-3.5-turbo  deprecated  try gpt-5.5examples/app.py:4  gemini-1.5-pro  not in catalog  try gemini-2.5-pro3 findings in 1 files

Check an ID.

$ node plugin/dist/stalemodel.js check gpt-4o claude-opus-5-5gpt-4o  current  try gpt-5.5claude-opus-5-5  current

Find current models, newest first, with prices per million tokens.

$ node plugin/dist/stalemodel.js find --provider anthropic --limit 2claude-haiku-5-5  anthropic  2026-10-07  $0.1/$0.5 per MTok  1000000 contextclaude-sonnet-5-5  anthropic  2026-09-28  $2/$10 per MTok  1000000 context

Add --json for machine-readable output, or --offline to use only the bundled snapshot. These examples use the snapshot from 2026-10-31, so live results will change.

MCP tools

ToolWhat it does
models_checkSays whether IDs are current, deprecated or unknown, and suggests a newer model
models_findLists models by provider, name, price, context size or tool support
models_scanFinds outdated IDs in a file or folder, returning locations only

All three are read-only.

Limits

  • Data comes from models.dev, so it can lag behind providers or contain errors.
  • "Not in catalog" can also mean a new, private or misspelled model.
  • try is a suggestion based on family and release date. Check price and behavior before switching.
  • scan only sees quoted IDs, so it misses IDs built at runtime. It also doesn't flag bare gpt-4o-style IDs that are old but still current.

FAQ

How do I find deprecated LLM models in my code? Run npx stalemodel scan .. It exits 1 on findings, so it also works as a CI check.

Where does the pricing data come from? From models.dev, fetched live, with a snapshot bundled for offline use.

Does it work outside Claude Code? It's a standard MCP server, so it should work in any MCP client. So far it has only been tested in Claude Code.

Contributing

Contributions are welcome, from people and from people working with AI agents. See CONTRIBUTING.md. Good first issues:

  • Add a GitHub Action that runs scan on pull requests
  • Add an option to flag current models that have a newer version
  • Support Bedrock and Vertex model ID formats
  • Add a --fix option that shows a diff of suggested replacements
  • Add a plugin icon

How pull requests work

  1. Open a PR. Fork the repo, work on a branch, and keep it to one change. Write a title that says what changes for users, because it becomes the changelog line: feat: goes under Added and fix: under Fixed.
  2. Automatic check. Code changes need tests, and make test must pass. Changes over 30 lines need a linked open issue (Closes #<number>), and a PR can have at most 800 changed lines. If something is missing, a comment tells you what to fix.
  3. Review. Claude reviews each PR automatically. Code PRs also get a security review and are tested in a sandbox. The review then merges the PR or asks for changes. PRs that change CI, agent settings, npm or Python dependencies, vendored code or build files can't be merged this way, and a comment says so. The same goes for anything the security review doesn't clear.
  4. Release. A merge that changes what users install becomes a new version within about two hours, with a GitHub Release and, if the project has one, its npm package. Docs and CI changes wait for the next release.

AI disclosure

This project was largely generated with Claude Code and reviewed by its maintainer.

About me

I'm Giulliano Macedo, and I build developer tools at GoTech Solutions. Follow along or get in touch:

If stalemodel helped you, a star helps others find it.

MIT licensed. Model data from models.dev (MIT).

Built by Giulliano Macedo, GoTech Solutions · LinkedIn · X

Source: README.md at commit f931659

Tools

3

models_check

Check model names

Checks whether AI model IDs are current, deprecated or missing from the catalog, and suggests the newest model in the same family. Use before writing a model ID into code or config, because IDs from training data are often out of date. Status unknown can also mean a new or private model.

Parametersmodel_idsrequired

models_find

Find current models

Lists non-deprecated AI models, newest first, with price per million tokens and context size. Use to choose a model or get a current ID, price or limit.

Parameterslimitqueryprovidermin_contextrequires_toolsmax_input_price

models_scan

Scan files for outdated model names

Scans a file or directory for quoted AI model IDs that are deprecated or missing from the catalog. Read-only. Skips dependency and build folders, and returns locations and IDs, not file contents.

Parameterspathrequired

Version history

1
  1. v0.1.1LatestOct 31, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts