com.infercpi由 infercpi.com 發布官方發布者v1.0.0更新於 Oct 29, 2026
AI inference price index: token prices, cost per capability, open vs closed, hosts, cost per task.
唯讀 MCP 伺服器，提供 InferCPI 的 AI 推論價格指數：token 價格、單位能力成本、開源與閉源比較、託管商及單一任務成本。
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/com.infercpi%2Fapi/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": {
"infercpi": {
"type": "http",
"url": "https://infercpi.com/mcp"
}
}
}InferCPI tracks what AI inference costs: list prices, what buyers actually pay, the cost of a fixed level of capability, open vs closed models, third-party hosts, self-hosting, and cost per completed task. Site: https://infercpi.com.
This repo holds the public API docs, examples and the MCP server. The data is free, needs no key, and is licensed CC BY 4.0: cite as InferCPI, infercpi.com.
Static JSON at https://infercpi.com/v1/. Full reference: https://infercpi.com/api.html.
More in examples/.
mcp_server.py gives agents ten read-only tools over the API: index_latest, index_series, index_catalogue, basket, model_price, events, speed, open_vs_closed, self_hosting, cost_per_task.
Hosted, no key: https://infercpi.com/mcp (streamable HTTP).
Claude.ai and Claude Desktop: Settings → Connectors → Add custom connector, paste the URL.
Or run it yourself:
Claude Desktop (claude_desktop_config.json):
It reads https://infercpi.com by default; set INFERCPI_BASE to point elsewhere.
How every series is built: https://infercpi.com/methodology.html. Inputs: LiteLLM and pydantic/genai-prices (MIT), Epoch AI Capabilities Index (CC BY 4.0), OpenRouter rankings (CC BY 4.0), SEC filings (public domain). Speed and cost per task are our own measurements.
Code in this repo: MIT. Index data: CC BY 4.0. Questions, corrections or a series you need: open an issue.
來源：README.md，提交 1e7403e
Latest value of every index series (list-price chained/composition/hedonic, usage-weighted paid price, Törnqvist, OpenRouter shares, TPI replica) with dates, the latest editorial note, and the licence/attribution line. Start here.
無需輸入參數。
Full weekly history of one series as [[unix_ts, value], ...] plus its method string. signal: price_index | weighted_index | or_rankings | implied_margin | self_host | task_cost | hf_downloads | gpu_spot | gpu_neocloud | aws_gpu | speed | hyperscaler_capex | seller_revenue | cloud_revenue | token_price ... key: see index_catalogue. since: optional ISO date to cut the history.
key必填sincesignal必填Every series the index publishes: signal/key, point count, first and last date, method string.
無需輸入參數。
Every model priced in this week's list-price index: provider, blended $/1M (0.75 in + 0.25 out), Epoch capability score where matched.
無需輸入參數。
Priced events in first-party price lists, newest first: launch, price_cut, price_increase, removed, each with key, provider, old/new blended $/1M and pct. since: ISO date; kind: filter to one kind.
kindsinceLatest daily speed run, measured by the index: per model and route (openrouter default routing, openrouter_pinned to the first-party host, anthropic and openai direct), median time to first token (ms), visible output tokens per second, host that served it. Same prompt every day.
無需輸入參數。
Blended list $/1M for one model by any common name ('Claude Opus 5.5', 'anthropic/claude-opus-5.5', 'gpt-5.5'); matches by the index's name normaliser and returns every basket entry that matches.
name必填Cheapest blended $/1M at each capability level (Epoch ECI 130/145/160) for closed models, open models at their lab's price and open models at the cheapest third-party host; the open discount; DeepSeek's floor lift (cheapest price without DeepSeek / cheapest overall, at lab and at host prices); and the host discount per open model (lab price / cheapest host).
無需輸入參數。
What it costs per 1M tokens to leave the APIs: desk boxes (Mac Studio lease, RTX 5090 bought) at full and 25% duty, H100 rented by source (Vast, AWS, RunPod, CoreWeave, Lambda, Nebius) and owned, against the API price of the same open model and of the cheapest closed model at equal capability; break-even volume and how far hardware cost must fall. Plus posted GPU-hour prices and Hugging Face download counts.
無需輸入參數。
Monthly measurement: dollars and tokens per completed task for the most-used models (fixed 8-task suite via OpenRouter at default settings, charged cost), reasoning share of output tokens, accuracy, and medians.
無需輸入參數。
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。
請在儲存庫或註冊中心條目中宣告授權條款。
curl -s https://infercpi.com/v1/latest.json | jq '.latest["weighted_index/paid_usd_1m"]'claude mcp add --transport http infercpi https://infercpi.com/mcp # Claude Codemkdir -p ~/.local/share/infercpicurl -so ~/.local/share/infercpi/mcp_server.py https://raw.githubusercontent.com/Infer-CPI/api/main/mcp_server.pypip install mcp # mcp 1.x or 2.x both workclaude mcp add infercpi -s user -- python3 ~/.local/share/infercpi/mcp_server.py # Claude Codepython3 ~/.local/share/infercpi/mcp_server.py --http # or: streamable HTTP on :8765{ "mcpServers": { "infercpi": { "command": "python3", "args": ["/home/YOU/.local/share/infercpi/mcp_server.py"] } } }