Agent Cost Hub

com.agentcosthub由 agentcosthub.com 发布官方发布者v1.0.1更新于 Nov 3, 2026

每日核验的LLM API价格与AI智能体成本估算。只读成本查询工具。

AI 翻译由 AI 模型根据下方的原文描述翻译,可能有误。

原文描述

LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools.

已验证Streamable HTTP可网页运行金融AI 与机器学习

概览

Agent Cost Hub 的托管 MCP 服务(agentcosthub.com),由 agentcosthub.com 发布;无需登录;Streamable HTTP;5 个工具。

暂无 AI 概览:以下信息来自注册中心条目和服务本身。

发布者
agentcosthub.com
端点
agentcosthub.com
最近检查

安装

在 SourceWeft 中

  1. 打开 控制台中的 Agent Cost Hub,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.agentcosthub%2Fagent-cost-hub/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "agent-cost-hub": {
      "type": "http",
      "url": "https://agentcosthub.com/mcp"
    }
  }
}

README

Agent Cost Hub MCP server

A free, read-only MCP server that lets AI assistants (Claude, Cursor, and other MCP clients) answer: "What will this AI agent cost me per month?"

It uses the same price list and formula as agentcosthub.com. The price list covers 79 models and is checked daily.

  • Endpoint: https://agentcosthub.com/mcp (Streamable HTTP, no sign-in, no API key)
  • Setup page: https://agentcosthub.com/mcp/
  • Official MCP Registry: com.agentcosthub/agent-cost-hub
  • The server makes no model calls, needs no secrets, and doesn't store your queries.

Connect

Claude (claude.ai: Pro, Max, Team) Settings → Connectors → Add custom connector → paste https://agentcosthub.com/mcp → choose No sign-in.

Claude Desktop (claude_desktop_config.json; Desktop uses stdio, so it bridges with mcp-remote):

json
{ "mcpServers": { "agentcosthub": { "command": "npx", "args": ["-y", "mcp-remote", "https://agentcosthub.com/mcp"] } } }

Cursor (~/.cursor/mcp.json):

json
{ "mcpServers": { "agentcosthub": { "url": "https://agentcosthub.com/mcp" } } }

Then ask, for example: "What's the cheapest model for a coding agent?" or "Compare Claude Sonnet 5.5 and GPT-5 for a RAG chatbot."

Tools

ToolWhat it does
list_modelsModels with price per 1M input / output / cached tokens (filter by provider, search, popular)
get_model_priceOne model's prices plus example monthly agent costs
estimate_costMonthly cost for one model, from a preset or your own numbers
compare_models2–5 models side by side for one workload
cheapest_models_forCheapest models for a preset or custom workload

Presets

PresetTokens in / out per callVolumeStepsCached
chatbot800 / 3001,000 calls/day10%
rag4,000 / 400500 calls/day10%
coding_agent20,000 / 1,50050 tasks/day1550%
research_agent8,000 / 1,000100 tasks/day1050%

Formula steps × (in × (1−cached%) × in_price + in × cached% × cached_price + out × out_price) ÷ 1M × calls/day × 30

The estimate uses list prices and leaves out cache-write fees. Every result includes prices_last_verified and a link to the matching agentcosthub.com page.

Example outputs (live, 2 Nov 2026)

cheapest_models_for { "preset": "coding_agent" }, top 5:

ModelMonthlyPer task
Claude Haiku 5.5$41.63$0.028
Llama 4 Maverick$75.46$0.050
DeepSeek V4.1 Flash$109$0.073
GPT-5 Mini$129$0.086
Mistral Large 4$244$0.163

estimate_cost { "model": "anthropic/claude-opus-5.5", "preset": "coding_agent" } → $1,620/month. With "cached_percent": 90 it drops to $936/month.

The trimmed raw response looks like this:

json
{  "workload": { "input_tokens": 20000, "output_tokens": 1500, "calls_per_day": 50,                "steps_per_task": 15, "cached_percent": 50, "preset": "coding_agent" },  "ranking": [ { "model": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5",                 "monthly_usd": 41.625, "monthly": "$41.63", "per_task_usd": 0.02775,                 "page": "https://agentcosthub.com/models/anthropic--claude-haiku-5.5/" } ],  "prices_last_verified": "2026-11-02",  "source": "https://agentcosthub.com"}

Prices change, so these numbers are a snapshot. A live call always returns the current figures.

Try it from a terminal:

bash
curl -s https://agentcosthub.com/mcp -H 'content-type: application/json' \  -H 'accept: application/json, text/event-stream' \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"cheapest_models_for","arguments":{"preset":"chatbot"}}}'

Or use the MCP Inspector:

bash
npx @modelcontextprotocol/inspector --cli https://agentcosthub.com/mcp --transport http --method tools/list

Repo layout

  • src/mcp-core.mjs is the JSON-RPC MCP server, written with no SDK. It's a source reference: it imports the price data and formula from the agentcosthub.com site build, which isn't in this repo.
  • dist/mcp-core.js is a self-contained bundle that includes a price snapshot. The hosted endpoint is always the current version.
  • src/worker.mjs and src/wrangler.toml are an optional standalone Cloudflare Worker.
  • server.json is the MCP Registry manifest.

Notes

  • Estimates only. Cheaper models aren't always as capable, so test on your own tasks.
  • AI tools helped build this project, and every price is checked against the providers' official pages.
  • Issues and suggestions are welcome. You can also email [email protected].

MIT licensed. Made by Agent Cost Hub.

来源:README.md,提交 2b08aeb

工具

5

list_models

List models

List LLMs tracked by Agent Cost Hub with API list prices per 1M tokens. Optional filter by provider or text.

输入参数searchproviderpopular_only

get_model_price

Get model price

Current API list price of one model (input, output, cached input per 1M tokens) plus example monthly agent costs.

输入参数model必填

estimate_cost

Estimate agent cost

Estimate the monthly API cost of an AI agent or chatbot on one model. Easiest: pass model + preset (chatbot, rag, coding_agent, research_agent). Or give input_tokens, output_tokens and calls_per_day (plus optional steps_per_task, cached_percent); explicit numbers override the preset.

输入参数model必填presetinput_tokenscalls_per_dayoutput_tokenscached_percentsteps_per_task

compare_models

Compare models

Compare 2-5 models on price and (optionally) on the monthly cost of one workload.

输入参数models必填presetinput_tokenscalls_per_dayoutput_tokenscached_percentsteps_per_task

cheapest_models_for

Cheapest models for a workload

Rank models by monthly cost for a workload. Use a preset (chatbot, rag, coding_agent, research_agent) or give token numbers.

输入参数limitpresetinput_tokenspopular_onlycalls_per_dayoutput_tokenscached_percentsteps_per_task

版本历史

2
  1. v1.0.1最新Nov 3, 2026
  2. v1.0.0Nov 1, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分