简介
models 是一个终端里的“选型面板”:对比服务商与基准,跟踪 coding agents,让你少猜测、多交付。
最适合: 经常比较 LLM 与 agent 工具、希望在终端统一查看的人
适配: macOS/Linux 可用 Homebrew;跨平台可用 Cargo(README 有说明)
配置时间: 3–10 分钟
关键事实(已验证)
- README Highlights 提到:约 4,000+ 模型、覆盖 85+ providers,约 400 条 benchmark 数据。
- 同时跟踪 11+ coding agents 与 22 个 provider 状态(README 描述)。
- GitHub:418 stars · 17 forks;最近更新 2026-05-13(GitHub API 验证)。
正文
让“选型决策”可复盘
把 models 当作终端里的快速核对工具,再把关键事实贴进 PR 或事故记录里。
README 原文节选(verbatim)
models
TUI and CLI for browsing AI models, benchmarks, coding agents, and provider statuses.

Highlights
- ~4,000+ models across 85+ providers from models.dev — filter by capability, price, context, and provider category
- ~400 benchmark entries from Artificial Analysis — compare models head-to-head with scatter plots and radar charts
- 11+ coding agents tracked with version detection, changelogs, and GitHub integration
- 22 provider statuses monitored live across 7 status page platforms
What's New in v0.11.3
- Status CLI —
models status list,show,sources, andstatuscommands with interactive picker and JSON output - Configurable aliases — customize symlink names via
[aliases]in config.toml;models linkcreates all three - Status tab — live provider health monitoring with incidents, maintenance, and customizable tracking
- Agent service health — live operational status from provider status pages in the agents detail panel and CLI
Install
Homebrew (macOS/Linux)
brew install modelsCargo (any platform)
cargo install modelsdevScoop (Windows)
scoop install extras/modelsAUR (Arch Linux)
paru -S models-binPre-built binaries, .deb, and .rpm packages are available on GitHub Releases. See the Installation wiki page for all methods, shell completions, and command aliases.