Grandet

io.github.hanzohanzhe由 GitHub 帳號 hanzohanzhe 發布v0.3.0更新於 Oct 31, 2026

Cheapest API for any model across official, inference and relay providers; find free credits

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取金融AI 與機器學習

概覽

AI 產生的概覽

Grandet 是遠端 MCP 伺服器，讓助理比較某模型在官方 API、推論服務商與中轉站的標價，並查找免費額度。

可以做什麼
  • 比較某模型在官方 API、推論服務商與中轉站的標價，僅依價格排序
  • 查找目前官方免費方案、申請制額度與中轉免費群組，含條件與截止日期
  • 把有歧義的模型名稱解析為公開模型識別碼
  • 在需要細節時讀取某供應商針對某模型的分頁公開聲明
  • 查詢已發布的中轉術語表，未知術語會附上相關常見問題連結
  • 在選擇供應商前讀取共享的 Grandet 應用程式清單與推論設定
適用情境
適合在為某個模型挑選 API 購買管道、想了解最便宜的標價選項時使用，也適合查詢是否有免費方案或試用額度。需要理解中轉行話或核對報價來源時同樣有用。
執行需求
遠端 Streamable HTTP 端點位於 grandet.ai；價格查詢不需註冊或 API 金鑰。另外的 Skill 安裝程式需要 Node.js 20 以上版本，或手動複製資料夾。
安裝前請注意
價格僅為標價，不代表品質、速度或穩定性；美元額度、人民幣額度與現金價格分開列出，互相比較。連接所選供應商須自行完成：自行註冊、儲值並保存金鑰，設定檔僅在確認後才寫入。Skill 安裝程式會傳送一筆匿名安裝回條，除非關閉。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Grandet，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.hanzohanzhe%2Fgrandet/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "grandet": {
      "type": "http",
      "url": "https://grandet.ai/mcp"
    }
  }
}

README

Grandet: find the cheapest API for any model

简体中文 · Website · Installation

Grandet compares listed API prices for each model across official APIs, inference providers and relay sites. Your AI agent can look them up and connect the cheapest one to your app.

Use it asHow
Websitehttps://grandet.ai
Remote MCP serverhttps://grandet.ai/mcp (Streamable HTTP, no sign-up, no API key)
Agent SkillTell your agent: Install Grandet Skill for me: https://grandet.ai/download.md
Gitgit clone --depth 1 --branch skill-v0.3.0-build.20261018b https://github.com/hanzohanzhe/Grandet.git, then see Install with git

Install

Paste this into the agent you already use (Codex, Claude Code, Cursor and others):

text
Install Grandet Skill for me: https://grandet.ai/download.md

The agent does the rest. If it needs you to sign in or approve something, it tells you exactly what to click. Then open a new conversation and ask:

I code in Claude Code. Find me the cheapest Claude Sonnet 4.6 API.

No need to mention Grandet or attach files again. Price lookups need no account or API key. To install by hand, or for apps such as ChatGPT or Claude on the web that take an uploaded skill file, see Manual installation.

Install with git

The website and the install sentence above install build.20261018b (our internal name: j2), marked Latest on GitHub. Cloning its tag gives you the same Skill: the installed folder has the same content hash as the release ZIP.

sh
git clone --depth 1 --branch skill-v0.3.0-build.20261018b https://github.com/hanzohanzhe/Grandet.gitcd Grandetnode scripts/install-price-finder.mjs --app claude-code --receipt-source checkout
  • Replace claude-code with your app: codex, cursor, opencode, gemini-cli, cline, roo-code, kilo-code, windsurf, continue, hermes, openclaw, trae-cn or trae-intl. --list shows every app and the folder it installs to.
  • The installer needs Node.js 20 or later. Without Node, copy the whole skills/grandet-api-price-finder folder into your app's skill folder: ~/.claude/skills/ for Claude Code, ~/.agents/skills/ for Codex, other apps in the per-app guide.
  • Then open a new conversation and ask a price question. The last line of the installed SKILL.md names the build.
  • The installer sends one anonymous install receipt (no path, name or key) so installs can be counted; --receipt-source checkout marks it as a git install. Add --no-telemetry to send nothing.
  • Another version: put its tag from Versions after --branch and run the same install command. It replaces the installed copy and keeps the old one as a backup outside the skill folder. In a clone you already have: git fetch --depth 1 origin tag <tag>, then git checkout <tag>.
  • Clone a tag, not main. main usually matches the latest release, but between releases it can carry changes that have not been tested yet.

MCP server

Add it to any MCP client that supports remote servers:

json
{ "mcpServers": { "grandet": { "url": "https://grandet.ai/mcp" } } }

In Claude Code: claude mcp add --transport http grandet https://grandet.ai/mcp

Tools: grandet_find_cheapest_api, grandet_find_free_credits, grandet_resolve_model, grandet_quote_evidence, grandet_glossary, grandet_list_apps.

What it does

1. Finds the lowest listed price. It compares the relay and official prices on grandet.ai for your model and kind of use (chat, coding, long output) and lists the cheapest few: the site, the group to pick when you create the token, the price, its unit and when it was observed.

  • It ranks by listed price only. It never says which site is "good" and never repeats a site's own claims such as "full strength" or "stable".
  • USD credit, CNY credit and cash prices are listed separately and never compared with each other.
  • Conditions such as a minimum top-up or members-only access are shown as a one-line hint. Prices that contradict the site's own text are listed as a reference. Groups a site limits to one client are folded away when your app is a different one.

2. Finds free credit. Ask "is there anything free?" and it lists official free tiers, trial credit and relay sign-up, check-in and free-group offers, with whether a card, ID check or application is needed. If something you already said makes you eligible for a free offer, it mentions it once.

3. Connects it for you. When you say "connect it":

  1. You sign up and top up on the site yourself, and create the token in the group it names.
  2. You run one command in your own terminal to store the key. Typing is hidden and the key never enters the chat.
  3. It shows the exact configuration change, backs up the file, and writes only after you confirm.
  4. It checks the key, group and model name without spending credit.
  5. Say "undo" to restore the previous setup.

For Codex, Claude Code, OpenCode, Kilo Code, Continue, Gemini CLI, Hermes, OpenClaw and WorkBuddy, the Skill's own connect program (scripts/connect.mjs, also usable as a local MCP server) makes the change the same way every time. Other apps get a field card and their documentation link. In a cloud chat, it can only hand you the command and configuration to run yourself.

Try asking

20 million tokens a month, a quarter input and the rest output, no cache. Which is cheapest, and what does it cost a month?

Is there a free Gemini API? I don't have a credit card.

Use the second one and connect it to Codex on Windows.

What do "官转" and "逆向" mean?

Answers include a link to the price sources. Listed prices and suppliers' claims say nothing about quality. Asked about quality, speed or downgraded models, it reports only what Grandet has on record and says so when there is no measurement.

What Grandet includes

What it does
grandet.aiCompare model API prices across official APIs, inference providers and relays; browse suppliers, free credit and promotions; check sources and observation dates
Grandet SkillFind the lowest price, find free credit and connect the chosen API from inside your agent
MCP serverThe same price and free-credit lookup for any MCP client, anonymous and without a key

Versions

Every build keeps product version 0.3.0; builds differ by build ID. The tag of a build is skill-v0.3.0-build.<build> (for example skill-v0.3.0-build.20261018b), and every tag and its release files stay on GitHub Releases, so any of them can be installed with the git commands above. The website installs 20261018b (j2).

From 20261017 on, each build was tested against the build before it: the same 48 questions, asked in the Hermes agent with deepseek-v4.1-flash and glm-5.3. PASS means every target was met. HOLD means some targets were missed; those builds were published after the misses were reviewed. "Used the Skill" counts sessions that answered through the Skill.

Which one to pick

  • Most people: 20261018b (j2). It is what the website installs and has the best test results so far. When grandet.ai cannot be reached, it still answers from a price snapshot taken on 18 October 2026 and says the date first. The cost: the largest package (ZIP 522 KB, .skill 218 KB).
  • No snapshot, smaller package: 20261018 (i8). ZIP 436 KB. It cannot answer when grandet.ai is unreachable, and in testing 1 of 16 group-condition sessions asked for a page the website has retired.
  • Chinese conversations only, fewer tokens on relay-jargon questions: 20261017 (i5). The English glossary column added in 20261017b doubled the glossary file (33.9 KB → 64.2 KB). 20261017 has no English column, no WorkBuddy connection, no named-site comparison and no 30-second switch to SkillHub.
  • Longer answers: 20261016h or earlier. These have no 8-line limit (median answer 841 characters in h, 484 in 20261017), but call addresses that don't exist far more often (18 bad-parameter errors in 48 questions, against 0). A small check of j2 against 20261016c (32 questions, deepseek-v4.1-flash) found: Skill used 90% → 100%, API errors per question 0.47 → 0.03, median answer 890 → 530 characters.
  • Avoid on native Windows: anything before 20261016d. Its Node installer can fail with EPERM there; copy the folder by hand instead. Builds before 20261016e have no SkillHub download for mainland China, and builds before 20261016h have a description that weaker models pick up less often (47% vs 85% in an A/B test).
  • Each build was written for the website's API at the time. The site has changed since, so older builds are more likely to ask for pages or fields that no longer exist.

All builds

BuildReleased (UTC)What changedTest against the previous build
20261018b (j2) · website · Latest2026-10-18Price snapshot (469 models, 174 free-credit offers) for when grandet.ai is unreachable; group conditions from price data instead of retired pages; carried-over quotes marked; up to five suggestions when a model name isn't foundPASS 18/18 · used the Skill 96/96 (same as 20261018) · quotes matching Grandet's data 97.4% → 100% · tokens ×1.04
20261018 (i8)2026-10-18Sites the user names are compared from 20 board rows; switches to SkillHub after 30 s of slow GitHubPASS 15/15 · used the Skill 95/96 (same) · tokens ×0.90 · named-site questions with side lookups 10/16 → 2/16 · quotes 36/36 matched
20261017b (i7)2026-10-18English glossary column; English answers keep the relay's group name; connects WorkBuddyHOLD 11/13 · used the Skill 95/96 (same) · tokens ×1.03
20261017 (i5)2026-10-17Only the documented requests, no guessed paths; parameter limits; answers within 8 lines and 600 charactersHOLD 10/13 (deepseek only) · used the Skill 47/48 (h 48/48) · bad-parameter errors 18 → 0 · median answer 841 → 484 characters
20261016h2026-10-16Description opens with relay terms (trigger 47% → 85% in an A/B test); exact read-only requests for hosts without MCP tools; credit never compared with cashnot run
20261016g2026-10-16Key files written owner-only (0600); a section listing what the Skill changes on your computer; loading on its own only reads pricesnot run
20261016f2026-10-16Answer fixes from agent reports (coding mix, model IDs kept as given, free-credit deadlines); registry copies pass their own manifest checknot run
20261016e2026-10-16Tencent SkillHub download for mainland China; registries carry the full kitnot run
20261016d2026-10-16Installer works on native Windows; --uninstall; first build on ClawHub and SkillHubnot run
20261016c2026-10-16Connecting hides keys already in an app's settings; connects Hermes and OpenClawnot run
20261016b2026-10-16Homepage install sentence; handles models that only have older quotesnot run
202610162026-10-16Reads official and inference-provider cash prices, listed apart from relay creditnot run
20261015e2026-10-15Connect fixes: undo restores files exactlynot run
20261015d2026-10-15Connect program (scripts/connect.mjs, also a local MCP server)not run
20261015c2026-10-15Glossary lookup fixed; explicit User-Agent and one retry on network errorsnot run
20261015b2026-10-15Reads the website's new free-credit and listing fieldsnot run
202610152026-10-15Rewrite: lowest price, free credit, connecting the API, relay glossarynot run
202610142026-10-14Same Skill as 0.3.0, with the installer and install receiptsnot run
0.3.0 (tag skill-v0.3.0)2026-10-14First public preview; no install receiptsnot run

skill-v0.3.1 was a candidate that was withdrawn before release; don't use it.

Feedback

Please open an issue if something goes wrong, with the app, version, system and the step where it stopped. Don't paste API keys or private conversations.

Data and developer entry points

ContentEntry point
Free credit and promotionsReadable · JSON · Release details
Original catalogue and sourcesCatalogue · JSON · Manifest
Repository data indexMachine-readable index · Reading guide for AI
Agent price lookup (MCP)Anonymous Streamable HTTP: https://grandet.ai/mcp
HTTP price lookuphttps://grandet.ai/api/v1/board · API description
HTTP free-credit lookuphttps://grandet.ai/api/v1/free-credits?q=gemini
Relay jargon glossaryBuilt into the Skill · Online

Local development needs Node.js 20+ and no third-party packages:

sh
node scripts/catalogue.mjs validatenode scripts/catalogue.mjs generate --checknode scripts/validate-public.mjsnode --test tests/*.test.mjsnode scripts/serve.mjs

serve.mjs opens a local browser view at http://127.0.0.1:8787/. These commands check local files only and never update the website's prices.

Sourced corrections and improvements are welcome; see the contributing guide and methodology.

Friends

  • LINUX DO: Chinese-language tech community

Licence

  • Skill files: Apache-2.0.
  • Catalogue code and documents written by Grandet: AGPL-3.0-only; scope in LICENSE.
  • Supplier data, original text and trademarks belong to their owners; the factual compilation carries no blanket open-data licence. See DATA-LICENSE.md, TRADEMARKS.md and each release manifest.

來源：README.md，提交 8994f24

工具

6

grandet_find_cheapest_api

Find a suitable low-cost model API / 寻找便宜且适用的模型 API

Compare Grandet model prices within each unit. Read listings for price-only ordering and conditions; legacy recommended/alternative/cheapest retain their old meanings. Use view=compact for shared connection cards and a short text response. Provide exactly one model or name selector. host records the source only and never selects the inference route. Send targetApp when the user or conversation identifies the intended API application, including explicit use in the current app. With no target, compare directly. An unrecorded app connection permits a price-only recommendation, not a compatibility claim. Omit profile/protocol for a multi-protocol app unless already specified. Existing client remains a legacy target-app alias. Infer coding/chat/long_output from the task; presets are estimates. Use grandet_list_apps only when application facts are needed. Do not request API keys.

輸入參數osmixasOfhostlangnameviewlimitmodelplansclientchannel另有 7 個

grandet_list_apps

Grandet application profiles / Grandet 应用接入清单

Read the shared Grandet application list and inference profiles before selecting a supplier. App profiles determine API compatibility; MCP capability alone does not prove an inference route or Skill installation. Use only when the target app ID, supported protocol or configuration variant is uncertain.

輸入參數apphostlangtargetAppskillBuildskillVersion

grandet_resolve_model

Resolve a model name / 识别模型名称

Look up public model identifiers when a requested name is ambiguous. Results are a page of candidates, not a cheapest-provider ranking. Prefer an exact officialId match; do not silently substitute a different model generation.

輸入參數hostlangname必填pagetargetAppskillBuildskillVersion

grandet_quote_evidence

Inspect a provider quote / 查看报价依据

Read one provider's paged public declarations for a model and optional rowId. Use only when a detail matters, not before every recommendation. A missing row on one page is not proof of absence; follow pagination if needed. This does not test model quality or spend money.

輸入參數asOfhostlangnamemodelrowIdprovider必填offerPagetargetAppreleaseSetskillBuildskillVersion

grandet_glossary

Relay terminology / 中转站术语

Look up the published Grandet relay glossary. Site labels are source claims and glossary terms explain them; they do not verify quality. Query q or category and follow pagination. Unknown terms include up to three related FAQ links.

輸入參數qhostlangpagelimitcategorytargetAppskillBuildskillVersion

grandet_find_free_credits

Find free API credit / 查找免费 API 额度

Find current official free tiers, application-based credits and relay free groups. Return the stated benefit, six requirements, deadline, original observation and claim link. userCanMeet=no_card excludes explicit required/conditional card entries; unknown card requirements remain clearly labelled unknown. Application categories describe programs, not the user’s eligibility. Follow pagination.

輸入參數qasOfhostkindlangpageviewlimittargetAppreleaseSetskillBuilduserCanMeet另有 1 個

版本歷史

1
  1. v0.3.0最新Oct 17, 2026

評分

已滿足適用檢查項的 90%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。