search_models
Search models
Search the pricing catalog with provider, workload, context, and price filters.
limitquerycursorproviderworkloadmax_combined_pricemin_context_tokens
io.github.gishh由 GitHub 帳號 gishh 發布v1.0.0更新於 Oct 24, 2026
Source-backed AI model pricing, rankings, history, and benchmark data.
一個遠端 MCP 伺服器,為助理提供有來源的 AI 模型價格、成本估算、基準排名與價格歷史,方便選型。
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。
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.gishh%2Faipricinghub/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。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"ai-pricing-hub": {
"type": "http",
"url": "https://aipricinghub.com/mcp/rpc"
}
}
}該儲存庫沒有 README。
Search models
Search the pricing catalog with provider, workload, context, and price filters.
limitquerycursorproviderworkloadmax_combined_pricemin_context_tokensCompare models
Compare pricing, context, and sourced benchmarks for model IDs.
model_idsCalculate cost
Estimate cost from total input tokens, their cached subset, output tokens and request count. Optional batch_mode uses available batch rates with standard-rate fallback.
model_idrequestsbatch_modeinput_tokensoutput_tokenscached_input_tokensFind cheapest
Find cheapest models by combined listed input plus output token price.
limitcursorproviderworkloadFind best value
Rank models by available benchmark signal per listed token price.
limitcursorproviderbenchmark_idProvider summary
Summarize model count, prices, benchmarks, and changes for a provider.
providerPricing history
Return historical pricing snapshots for a model ID.
model_idBenchmark lookup
Find sourced benchmark rows by model, provider, or benchmark ID.
limitcursormodel_idproviderbenchmark_idLatest changes
Return recent model launches, removals, and pricing changes.
typelimitcursorproviderSearch news
Search AI Pricing Hub news items.
limitquerycursorsourcelanguageRecommend model
Recommend models for a workload using price, context, and benchmark evidence.
limitbudgetproviderworkloadmin_context_tokens已滿足適用檢查項的 75%
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。
請宣告包含 README 的 GitHub 儲存庫,或在 OAuth 受保護資源後設資料中提供 resource_documentation。
請在儲存庫或註冊中心條目中宣告授權條款。