claudeers.
// Claude Plugins

modelplan

Which AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan.ai, in Claude Code,…

// Claude Plugins[ cli ][ api ][ desktop ][ web ][ claude ]#claude#agent-skills#ai-coding#claude-code#claude-code-plugin#cli#codex#coding-agents#plugins◷ MIT$open-sourceupdated about 1 month ago
Actively maintained
100/100
last commit 17 days ago
last release 17 days ago
releases 58
open issues 8

Install with your AI

Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.

Install and set up modelplan (claude-plugin project) into my current project.
Found on https://claudeers.com/modelplan
Repo: https://github.com/modelplan/modelplan
Homepage/docs: https://modelplan.ai
Detected install method: claude-plugin → /plugin install modelplan@modelplan/modelplan
Category: plugins. Platforms: cli, api, desktop, web.
Read the repo's README for exact setup and env vars, then install it and wire it into my project.

Claudeers Health Verdict:
active; community-verified: false. Confirm the source before running anything.
// or install directly (claude-plugin)
/plugin marketplace add modelplan/modelplan
/plugin install modelplan@modelplan/modelplan
// or clone
git clone https://github.com/modelplan/modelplan

// compatibility

Platformscli, api, desktop, web
Operating systems—
AI compatibilityclaude
LicenseMIT
Pricingopen-source
LanguageJavaScript

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

Model Plan: which coding model, at which effort, on which plan

Which AI coding model should you use, at which reasoning effort, and is one more step up worth it?
Model Plan answers from live, checkable public data, on the web and inside Claude Code, Codex and your terminal.

Website · Quick start · Screenshots · How it works · FAQ · Methodology · 简体中文

Why Model Plan

Most leaderboards compare every model at its top setting. But inside one model, going from Low to Max often costs several times more and takes several times longer, for a few points of ability. What you actually run is a model at an effort.

  • ★ Recommended effort. Every model gets its best-value effort, and you see exactly what one more step up buys (+4.8 ability) and costs (×1.37).
  • A leaderboard at that effort. Models are ranked at their own ★ effort, the setup you would really use, with cost per reference coding task and task time beside ability. Outclassed models (costlier and no stronger) are called out, and if you are on one, the CLI tells you once what to switch to: Fable 5.1 → Opus 5.5 (+2.5 points at ×0.52), GPT-6 Astra → GPT-6.1 Sol (about the same at ×0.18).
  • Your own quota. The Skill and CLI read your local Claude Code and Codex 5-hour and weekly windows (never uploaded). The CLI also keeps a local history of how much of each window you used and under which model and effort (modelplan history), the basis for suggesting a default effort from your own weeks, and measures your own speed per model, effort and Fast: output tok/s, time to first token, turn time and tokens, against ★ (modelplan effort, modelplan history; read from the harness logs' timestamps and token counts only). Plenty left before a reset? Step up, or turn on Codex Fast. Tight, or a recent burst that would use it up within three hours? Stay at ★ or step down, with the time it runs out. After a reset, it reminds you once to go back to the model and effort you used before (and to turn Codex Fast off).
  • Other plans (optional). modelplan codexbar enable cursor zai reads Copilot, Cursor, Z.ai / GLM, Kiro or OpenCode Go usage through the open-source CodexBar CLI, fetched at a pinned, checksum-checked release (macOS and Linux only). CodexBar keeps the sign-ins; this client keeps only percentages and reset times. Tell it which plan pays (modelplan declare zhipu-global-pro legacy-v2) and advice follows how that plan counts: on a per-request plan it never says step down, and points to the next off-peak hours instead.
  • Plans and windows. Coding plan prices and quotas by maker, model and price band; off-peak hours, peaks and public quota resets on a week calendar.
  • In your tools. One open-source Skill for any agent, plugins for Claude Code and Codex, and a single-binary CLI, all reading the same verified publication as the website.

Quick start

The Skill works in Claude Code, Codex, Cline, Amp and 15+ other agents:

npx skills add modelplan/modelplan

Then ask your agent: "Which model and effort should I use for this refactor?" or "My 5-hour window resets in 40 minutes, should I step up?"

Claude Code plugin: the Skill, /modelplan:* commands and a status line
/plugin marketplace add modelplan/modelplan
/plugin install modelplan@modelplan

The plugin fetches its own modelplan CLI (a pinned release, checksum-checked) in the background, so there is nothing else to install or upgrade; /modelplan:setup checks each part. Commands: /modelplan:plan, /modelplan:effort, /modelplan:lineup, and /modelplan:statusline to add the status line (asks before changing your settings). More

Codex plugin: the Skill plus a GPT effort dashboard
codex plugin marketplace add modelplan/modelplan --sparse .agents --sparse codex
codex plugin add modelplan-codex@modelplan

Ask Codex to "Open the Model Plan dashboard". Needs Node.js 22+, found automatically when Codex has one. Setup check, optional CLI and uninstall: more

modelplan CLI: a single static binary for macOS, Linux and Windows
curl -fsSL https://raw.githubusercontent.com/modelplan/modelplan/main/install.sh | sh
modelplan lineup --dev anthropic

Windows: download from Releases. With Go: go install github.com/modelplan/modelplan/cli/cmd/modelplan@latest. The Skill and plugins use it when it is installed and work without it. More

Skill by hand

Copy skills/model-plan into ~/.claude/skills/model-plan or your agent's skills directory. It needs only a shell and anonymous HTTPS.

What you get

★ The effort that is worth it, and what the next step costs

Move the throttle and see ability, cost and task time for every native effort; switch on ⚡ Fast or ⚡⚡ Ultrafast to see how plan quota and time change.

Effort console: GPT-6 Astra from Med to Max, then Fast and Ultrafast Lift-off: every model climbs to its ability at its recommended effort; dragging turns the axes Which engine: ability against cost, the gold line joins the models worth picking

Advice that knows your quota, inside Claude Code and Codex

Claude Code status line: live model and effort, 5-hour and weekly usage, the reset countdown, and a hint when it is worth acting (↑High ×1.37 before a reset with allowance left, ↓ when a window is tight, ↺★ after a reset).

Claude Code status line

CLI: lineups, effort ladders, quota and advice.

modelplan lineup and modelplan effort output

Codex dashboard: GPT models at their ★ effort, the effort curves with a ⚡ switch, your Codex quota and public reset notices.

Model Plan dashboard in Codex

Coding plans, off-peak hours and resets

Plan Depot: coding plans by maker

Not just another leaderboard

Typical leaderboardModel Plan
Setting comparedeach model's top settingeach model's ★ recommended effort, plus every other effort
Costprice per million tokenscost of one reference coding task, at every effort
Timerarelytask time at every effort (estimates marked)
One step upnot shown+ability and ×cost for each step
Your quotanolocal Claude Code and Codex windows, never uploaded
Plansnoprices, quotas, off-peak hours and resets
Wherea web pageweb, API, Skill, CLI, Claude Code and Codex

How it works

flowchart LR
  S["Public sources<br/>benchmarks · vendor pages · plan pages · news"] --> P["Model Plan publication<br/>verified, content-hashed, rebuilt every few hours"]
  P --> W["modelplan.ai"]
  P --> A["Read-only API<br/>/v1/client · llms.txt"]
  A --> K["Skill"]
  A --> C["modelplan CLI"]
  C --> CC["Claude Code plugin<br/>status line · hooks"]
  C --> CX["Codex plugin<br/>dashboard · hooks"]
  Q["Your quota files<br/>(stay on your machine)"] --> C
  Q --> K

Every client reads only Model Plan's verified public publication and the quota files your harness already writes locally. Rankings, verdicts and multipliers come from the publication; clients never compute their own. Formulas and sources: METHODOLOGY.md.

Principles: open source (MIT) · read-only · anonymous, no account, no telemetry · quota is read on your machine only · it never switches your model or effort for you.

FAQ

What is the ★ recommended effort?

For each model, the native effort (Low, Medium, High, XHigh, Max…) with the best balance of ability, cost and task time. Higher efforts are shown with what they add and cost, so you can decide when a task deserves them. See Methodology.

Why isn't ★ the top effort, or the vendor's default?

By design. ★ is the best-value effort among a model's own efforts; the top effort is always listed beside it, and the website can switch every model to its top effort. Cheap models often get higher efforts than expensive ones because one step up costs cents rather than dollars. Vendor defaults also weigh responsiveness and rate limits, so they are shown beside ★ as a reference, not copied. The ability score is a frozen scale (50 = the September 2026 frontier average), so it can be below 0 or above 100.

Where do the numbers come from, and how fresh are they?

Ability comes from public benchmarks (such as Artificial Analysis) on one scale; cost is the API cost of one reference coding task at official prices; time comes from public task timings, estimated and marked where missing. Plans come from official pages. A new publication is built and verified every few hours; the website and every client show when it was published.

Does anything about me leave my machine?

No. Clients download the public publication anonymously. Your Claude Code and Codex quota is read from local files and only used on your machine. There is no account and no telemetry.

Will it change my model or effort?

Never. It advises; you switch. Quota hints are shown to you, not your agent; the agent gets one short task-start brief per session and stays quiet about models unless the setting clearly does not fit the task.

Which models and plans are covered?

Current coding models from OpenAI, Anthropic, Google, xAI, Zhipu, Moonshot (Kimi), Xiaomi, MiniMax, Meta, Alibaba, DeepSeek, Tencent and others, and their coding plans. The live list is on modelplan.ai and in /v1/client.

Can I use the data in my own tool or agent?

Yes: the read-only API needs no key (OpenAPI), agents can start from llms.txt, and the off-peak and reset calendar is available as ICS.

Repository

DirectoryWhat it is
Model Plan Skillskills/model-plan/The main client, for any agent with Skills: model and effort choice, the multiplier for each step up, planning around your remaining quota and reset times
Claude Code pluginclaude-code/The Skill, /modelplan:* commands, status line and a prompt hook that shows you new hints and gives Claude a short task-start brief once per session
Codex plugincodex/The Skill and a GPT effort dashboard with a ⚡ Fast / Ultrafast switch, your Codex quota and public reset notices
Desktop app (preview)desktop/A macOS menu bar app: the quota left and the current hint in the menu bar, a popover with your sessions, quota and effort curves, and a notification once per piece of advice. Unsigned builds for now
modelplan CLIcli/Single static binary: lineup, effort, models, quota, advise, statusline, sync, doctor
Open datadata/The reviewed data behind the site: plan tiers, prices, quota metering, calendars, model identities and effort policies. Mirrored from modelplan.ai on every change, one pull request each
MethodologyMETHODOLOGY.mdHow ability, cost, time and the ★ effort are worked out, and the sources

Contributing

Wrong price, quota, effort or news item? Report a data problem; the Report links on modelplan.ai fill in the page and item for you. Bugs, ideas and pull requests are welcome: see CONTRIBUTING.md. Release notes are in CHANGELOG.md.

If Model Plan saves you quota or money, a ⭐ helps others find it.

Star History Chart

License

Code: MIT. Data in data/ and from the API: CC BY 4.0, crediting Model Plan; third-party figures keep their sources' terms. Model Plan is independent and not affiliated with any model vendor; vendor names and marks belong to their owners.

// faq

What is modelplan?

Which AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan.ai, in Claude Code, Codex and the terminal (plugins, Skill, CLI).. It is open-source on GitHub.

Is modelplan free to use?

modelplan is open-source under the MIT license, so it is free to use.

What category does modelplan belong to?

modelplan is listed under plugins in the Claudeers registry of Claude-compatible tools.

10 views
★ 41 stars
unclaimed
updated about 1 month ago

// embed badge

modelplan on Claudeers
[![Claudeers](https://claudeers.com/api/badge/modelplan.svg)](https://claudeers.com/modelplan)

// retro hit counter

modelplan hit counter
[![Hits](https://claudeers.com/api/counter/modelplan.svg)](https://claudeers.com/modelplan)

// reviews

// guestbook

0/500

// related in Claude Plugins

🔓

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

// pluginsmultica-ai/★ 230,631[ claude ]
🔓

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explainin…

// pluginsanthropics/⟨Python⟩★ 154,558[ claude ]
🔓

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

// pluginsHKUDS/⟨Python⟩★ 58,467◷ Apache-2.0[ claude ]
🔓

financial-services — a Claude ecosystem project on GitHub.

// pluginsanthropics/⟨Python⟩★ 41,027◷ Apache-2.0[ claude ]
→ see how modelplan connects across the ecosystem