LLM Hosting Pricing

Official5 toolsLive

by llmhosting

LLM and GPU rental prices: model price lookup, GPU listings, cheapest-GPU search, price history

ai.llmhosting/pricing Model Context Protocol (MCP) Server

This MCP server provides access to LLM and GPU rental pricing data. It supports model price lookup, GPU listings, a cheapest-GPU search, and price history. The server is identified by the slug ai-llmhosting-pricing and exposes 5 tools for querying pricing and availability information.

🛠️ Key Features

Model price lookup
GPU listings
Cheapest-GPU search
Price history
5 available tools

🚀 Use Cases

Retrieve current model rental prices
Browse available GPUs with associated rental pricing
Find the lowest-priced GPU option
Review historical price changes for models and GPUs

⚡ Developer Benefits

Structured pricing queries via MCP tools
Efficient discovery of models and GPUs by price
Access to price history for tracking changes

⚠️ Limitations

Limited to pricing-related operations (LLM/GPU rental prices, listings, cheapest search, and price history) as reflected by its tool set.

Captured live from the server via tools/list.

search_models

Search LLM models by name. Returns matching models with provider count and the cheapest input/output price per 1M tokens.

Parameters1

query

string

required

model name or fragment, e.g. "deepseek" or "llama 70b"

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "model name or fragment, e.g. \"deepseek\" or \"llama 70b\""
    }
  },
  "required": [
    "query"
  ]
}

get_model_prices

All provider prices for one LLM model: input/output/cache price per 1M tokens and context window per provider, cheapest first.

Parameters1

model

string

required

model slug or name, e.g. "deepseek-v4-flash"

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "model slug or name, e.g. \"deepseek-v4-flash\""
    }
  },
  "required": [
    "model"
  ]
}

list_gpus

Every GPU with live rental pricing: cheapest $/hr, provider, tier, and VRAM.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

cheapest_gpu

Cheapest GPU rentals right now, optionally filtered by minimum VRAM (GB).

Parameters1

min_vram_gb

number

optional

minimum VRAM in GB, e.g. 80

Raw schema

{
  "type": "object",
  "properties": {
    "min_vram_gb": {
      "type": "number",
      "description": "minimum VRAM in GB, e.g. 80"
    }
  }
}

gpu_price_history

Daily minimum rental price history for a GPU (recorded daily since 2026-07-06).

Parameters2

gpu	string	required	GPU name, e.g. "H100 SXM" or "RTX 4090"
days	number	optional	how many most-recent days to return (default 30)

Raw schema

{
  "type": "object",
  "properties": {
    "gpu": {
      "type": "string",
      "description": "GPU name, e.g. \"H100 SXM\" or \"RTX 4090\""
    },
    "days": {
      "type": "number",
      "description": "how many most-recent days to return (default 30)"
    }
  },
  "required": [
    "gpu"
  ]
}

Install

Tools (5)

search_modelsget_model_priceslist_gpuscheapest_gpugpu_price_history

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://llmhosting.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "pricing": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://llmhosting.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

ai.llmhosting/pricing Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

search_models

get_model_prices

list_gpus

cheapest_gpu

gpu_price_history

Install

Remote endpoint

Related servers