vitas/dsh-model-pricing

Name: vitas/dsh-model-pricing
Author: vitas

Plugin插件 Native原生 ⭐ 2 Apache-2.0 Usage & Cost用量与计费 Models & Routing模型与路由 Productivity & Tasks效率与任务

Compare LLM API prices before you pick a model — and see what you actually paid after you used it. A plugin for DeepSeek Harness (DSH) that puts a model pricing and capability table directly into your DSH settings (7,250 priced models, 213 providers), and then reads your own session logs through the same catalog:

catalog descriptioncatalog 简介 / catalog description：Model pricing & capability board for DeepSeek Harness: ~7,250 models across 213 providers, honest lowest-listed comparison, session costs priced by the route you actually called, and cache-leak attribution. Local-first, no server.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

dsh-model-pricing is a native plugin built specifically for the DeepSeek Harness (DSH) and is installed through the DSH package manager with dsh plugin --profile web add dsh-model-pricing, after which a model pricing and capability table appears at the bottom of the DSH Settings → Models page; it ships a bundle-manifest for the DSH plugin runtime and is published on npm under the same name, while its GitHub topic explicitly tags it as a deepseek-harness-plugin. The catalog merges ~7,250 priced models across 213 providers from models.dev with the @earendil-works/pi-ai routing catalog that DSH already bundles, and it flags rows where the public price diverges from the harness's authoritative routed price by more than 10%, including cross-provider lowest-listed badges and ⚠ flags for suspiciously cheap routes. Capability tags (Coding, Agentic, Vision, Long context, Open weights, Structured output) are computed from structured catalog fields and remain user-configurable.

In daily workflow, a DSH user stops opening three browser tabs to compare providers because the same table they browse is now the route-selection surface inside the harness itself, with verified, time-boxed community promos rendered as badges with provenance tooltips and one-click filtering through promos/README.md pull requests validated by CI. After sessions are run, the plugin replays the harness's own log files, including mid-session model switches, to compute per-workspace spend per (provider, model) with an explicit confidence ladder (routed > listed > estimated range > nothing shown) alongside promo-adjusted savings versus list price, and it attributes cache-leak spend to idle gaps past documented provider TTLs, route switches, or unattributed causes, explicitly excluding compaction. A price × speed quadrant plots your own median TTFT and tokens/second against list price once at least five samples exist, so “cheap and slow” becomes a fact about your history.

Dependencies are intentionally minimal: the plugin runs entirely on the user's machine with no server of its own, performs an anonymous read of the public models.dev catalog and the bundled pi-ai catalog on first load, caches results locally, and parses session logs that already live under the DSH home directory, so nothing leaves the device. It is licensed Apache-2.0, distributed on npm and via the awesome-dsh-plugin registry (accepted 2026-09-11), localized with parity-checked English, Chinese, and Russian UIs, and clearly labels every displayed number with its source and freshness while reminding users that prices, costs, and leak figures are model-selection estimates only — the provider's invoice is the sole billing authority. From-source development follows git clone → npm install → npm run snapshot && npm run build → dsh plugin --profile web add ..

dsh-model-pricing 是面向 DeepSeek Harness（DSH）的原生插件，通过 dsh plugin --profile web add dsh-model-pricing 安装并在 DSH 的"设置 → Models"页面底部加载一张可筛选的模型价格与能力表格，覆盖来自 models.dev 的约 7,250 个模型、213 家提供商，并叠加 DSH 自带的 @earendil-works/pi-ai 路由目录作为权威价格，对偏差超过 10% 的条目逐行标红，同时呈现经过 CI 审核的限时促销徽章。

典型使用场景：在 DSH 内直接对比输入、输出、缓存读取的每百万 token 单价、上下文窗口与最大输出，能力标签（编程、Agent、视觉、长上下文、开源权重、结构化输出）由目录字段推导并支持用户自定义规则；插件还会重放本地会话日志，按实际调用路由汇总每个项目支出、归因缓存泄露（空闲超 TTL、路由切换等），并在价格 × 速度象限中用 TTFT 与 tok/s 的中位数对模型做出基于自身历史而非博客的评判。

依赖方面，插件完全本地运行，不持有自建服务，首次加载会拉取目录并本地缓存；会话成本与泄露统计全部来自 DSH 主目录下的本地日志，绝不上传，UI 提供英语、中文、俄语三语并行。许可证为 Apache-2.0，所有价格、成本与泄露数字仅为模型选型估算，最终计费以提供商账单为准。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-model-pricing（vitas/dsh-model-pricing）
仓库：https://github.com/vitas/dsh-model-pricing
本站详情页：https://www.yhbd.top/plugins/vitas-dsh-model-pricing/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 Apache-2.0 · ⭐ 2 · 最近提交 2026-09-30 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 2 stars - very few users, little community feedback星标只有 2，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add dsh-model-pricing

把 vitas/dsh-model-pricing 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

6.8 KB · 缓存于 2026-09-27 22:08:40 · 6.8 KB

dsh-model-pricing

Compare LLM API prices before you pick a model — and see what you actually paid after you used it. A plugin for DeepSeek Harness (DSH) that puts a model pricing and capability table directly into your DSH settings (~7,250 priced models, 213 providers), and then reads your own session logs through the same catalog: per-project spend priced by the route you actually called, and the dollars your prompt cache is silently losing.

dsh-model-pricing pricing table rendered in the DSH Models settings page

The pricing table in the DSH Settings → Models page: cross-provider lowest listed badges, capability tags, and per-1M-token prices.

dsh-model-pricing session costs panel: spend per workspace, cache-leak attribution and the route performance quadrant

The session costs panel: per-workspace spend by the route actually called, cache leaks by cause, and a price × speed quadrant measured from your own history.

Why

Choosing a coding agent model today means opening three browser tabs: your provider's price page, a comparison site, and someone's spreadsheet of which API is discounting this month. dsh-model-pricing collapses that into the harness you are already in: one table, filtered to what you can actually call, refreshed from public catalogs on your own machine.

Features

Pricing table for every connectable model — input / output / cache-read price per 1M tokens, context window, and max output (213 providers, ~7,250 priced models)
Capability tags computed from structured catalog fields: Coding, Agentic, Vision, Long context, Open weights, Structured output — with user-configurable rules
Authoritative routing prices: for models DSH can actually invoke, the harness's own bundled pi-ai catalog overrides the public catalog, and price divergences larger than 10% are flagged row by row
Honest cross-provider comparison: the winner badge says lowest listed — a claim about the catalog, not the market — $0 free tiers compare only against free tiers, and a route listed below half the first-party price is flagged ⚠ to verify
Community promotion feed: verified, time-boxed offers rendered as badges with provenance tooltips and a one-click filter; contributed through reviewed pull requests and validated by CI (promos/README.md)
Session costs, priced by the actual route: replays the harness's own session logs — including mid-session model switches — and sums what each project spent per (provider, model), with an explicit confidence ladder (routed > listed > estimated range > nothing shown) and promo-adjusted savings next to list price
Cache-leak attribution: what share of your spend is history re-billed at full input price instead of cached price, split by cause — idle gaps past documented provider TTLs, route switches, unattributed — and never charging compaction, which is the opposite of a leak
Route performance quadrant: time-to-first-token and tokens/second per (provider, model), medians over your own window — paired with the list price, so “cheap & slow” is a fact about your history, not a blog post; five samples or more before anything is labelled
English, Chinese and Russian UI, parity-checked in CI

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 vitas/dsh-model-pricing 的 README.md。在 GitHub 查看原文 →