MCP MeasureMCP Measure

索引已观测

AI Pricing Hub

Source-backed AI model pricing, rankings, history, and benchmark data.

我该使用它吗

质量与安全性

A
描述质量
84%
模式完整度
90%
命名质量
89%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现（4）

  • LOWTool 'compare_models' description lacks action verb在 compare_models 中
  • LOWTool 'calculate_cost' description lacks action verb在 calculate_cost 中
  • LOWTool 'pricing_history' description lacks action verb在 pricing_history 中
  • LOWTool 'latest_changes' description lacks action verb在 latest_changes 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,224token 数（工具定义）
~1.1 KB典型响应大小
对注意力有中等影响（占 128k 上下文窗口的 0.96%）

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中：

{
  "mcpServers": {
    "aipricinghub": {
      "url": "https://aipricinghub.com/mcp/rpc"
    }
  }
}

远程端点

https://aipricinghub.com/mcp/rpcstreamable-http

它能做什么

工具清单

工具（11）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_models(query, provider, workload, max_combined_price, min_context_tokens, ...)

Search the pricing catalog with provider, workload, context, and price filters.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "query"
    },
    "provider": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "provider"
    },
    "workload": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "workload"
    },
    "max_combined_price": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "max combined price"
    },
    "min_context_tokens": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "min context tokens"
    },
    "limit": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "limit"
    },
    "cursor": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "cursor"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢compare_models(model_ids)

Compare pricing, context, and sourced benchmarks for model IDs.

输入模式

{
  "type": "object",
  "properties": {
    "model_ids": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "model ids"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢calculate_cost(model_id, input_tokens, output_tokens, cached_input_tokens, requests)

Estimate cost from model pricing and token volumes.

输入模式

{
  "type": "object",
  "properties": {
    "model_id": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "model id"
    },
    "input_tokens": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "input tokens"
    },
    "output_tokens": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "output tokens"
    },
    "cached_input_tokens": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "cached input tokens"
    },
    "requests": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "requests"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢find_cheapest(provider, workload, limit, cursor)

Find cheapest models by combined listed input plus output token price.

输入模式

{
  "type": "object",
  "properties": {
    "provider": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "provider"
    },
    "workload": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "workload"
    },
    "limit": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "limit"
    },
    "cursor": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "cursor"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢find_best_value(provider, benchmark_id, limit, cursor)

Rank models by available benchmark signal per listed token price.

输入模式

{
  "type": "object",
  "properties": {
    "provider": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "provider"
    },
    "benchmark_id": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "benchmark id"
    },
    "limit": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "limit"
    },
    "cursor": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "cursor"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢provider_summary(provider)

Summarize model count, prices, benchmarks, and changes for a provider.

输入模式

{
  "type": "object",
  "properties": {
    "provider": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "provider"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢pricing_history(model_id)

Return historical pricing snapshots for a model ID.

输入模式

{
  "type": "object",
  "properties": {
    "model_id": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "model id"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢benchmark_lookup(model_id, provider, benchmark_id, limit, cursor)

Find sourced benchmark rows by model, provider, or benchmark ID.

输入模式

{
  "type": "object",
  "properties": {
    "model_id": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "model id"
    },
    "provider": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "provider"
    },
    "benchmark_id": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "benchmark id"
    },
    "limit": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "limit"
    },
    "cursor": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "cursor"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢latest_changes(provider, type, limit, cursor)

Return recent model launches, removals, and pricing changes.

输入模式

{
  "type": "object",
  "properties": {
    "provider": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "provider"
    },
    "type": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "type"
    },
    "limit": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "limit"
    },
    "cursor": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "cursor"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢search_news(query, language, source, limit, cursor)

Search AI Pricing Hub news items.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "query"
    },
    "language": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "language"
    },
    "source": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "source"
    },
    "limit": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "limit"
    },
    "cursor": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "cursor"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢recommend_model(workload, provider, budget, min_context_tokens, limit)

Recommend models for a workload using price, context, and benchmark evidence.

输入模式

{
  "type": "object",
  "properties": {
    "workload": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "workload"
    },
    "provider": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "provider"
    },
    "budget": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "budget"
    },
    "min_context_tokens": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "min context tokens"
    },
    "limit": {
      "type": [
        "string",
        "number",
        "array"
      ],
      "description": "limit"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本11 个工具
已验证未记录版本11 个工具
已验证未记录版本11 个工具